Image Classification

In this project, you'll classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. You'll preprocess the images, then train a convolutional neural network on all the samples. The images need to be normalized and the labels need to be one-hot encoded. You'll get to apply what you learned and build a convolutional, max pooling, dropout, and fully connected layers. At the end, you'll get to see your neural network's predictions on the sample images.

Get the Data

Run the following cell to download the CIFAR-10 dataset for python.



In [1]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
from urllib.request import urlretrieve
from os.path import isfile, isdir
from tqdm import tqdm
import problem_unittests as tests
import tarfile

cifar10_dataset_folder_path = 'cifar-10-batches-py'

class DLProgress(tqdm):
    last_block = 0

    def hook(self, block_num=1, block_size=1, total_size=None):
        self.total = total_size
        self.update((block_num - self.last_block) * block_size)
        self.last_block = block_num

if not isfile('cifar-10-python.tar.gz'):
    with DLProgress(unit='B', unit_scale=True, miniters=1, desc='CIFAR-10 Dataset') as pbar:
        urlretrieve(
            'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz',
            'cifar-10-python.tar.gz',
            pbar.hook)

if not isdir(cifar10_dataset_folder_path):
    with tarfile.open('cifar-10-python.tar.gz') as tar:
        tar.extractall()
        tar.close()


tests.test_folder_path(cifar10_dataset_folder_path)









    



All files found!

Explore the Data

The dataset is broken into batches to prevent your machine from running out of memory. The CIFAR-10 dataset consists of 5 batches, named data_batch_1, data_batch_2, etc.. Each batch contains the labels and images that are one of the following:

airplane
automobile
bird
cat
deer
dog
frog
horse
ship
truck

Understanding a dataset is part of making predictions on the data. Play around with the code cell below by changing the batch_id and sample_id. The batch_id is the id for a batch (1-5). The sample_id is the id for a image and label pair in the batch.

Ask yourself "What are all possible labels?", "What is the range of values for the image data?", "Are the labels in order or random?". Answers to questions like these will help you preprocess the data and end up with better predictions.



In [2]:

    
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import helper
import numpy as np

# Explore the dataset
batch_id = 1
sample_id = 5
helper.display_stats(cifar10_dataset_folder_path, batch_id, sample_id)









    



Stats of batch 1:
Samples: 10000
Label Counts: {0: 1005, 1: 974, 2: 1032, 3: 1016, 4: 999, 5: 937, 6: 1030, 7: 1001, 8: 1025, 9: 981}
First 20 Labels: [6, 9, 9, 4, 1, 1, 2, 7, 8, 3, 4, 7, 7, 2, 9, 9, 9, 3, 2, 6]

Example of Image 5:
Image - Min Value: 0 Max Value: 252
Image - Shape: (32, 32, 3)
Label - Label Id: 1 Name: automobile

Implement Preprocess Functions

Normalize

In the cell below, implement the normalize function to take in image data, x, and return it as a normalized Numpy array. The values should be in the range of 0 to 1, inclusive. The return object should be the same shape as x.



In [128]:

    
def normalize(x):
    """
    Normalize a list of sample image data in the range of 0 to 1
    : x: List of image data.  The image shape is (32, 32, 3)
    : return: Numpy array of normalize data
    """
    # TODO: Implement Function
    max_x = np.max(x)
    min_x = np.min(x)
    
    return (x - min_x) / (max_x - min_x)

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_normalize(normalize)









    



Tests Passed

One-hot encode

Just like the previous code cell, you'll be implementing a function for preprocessing. This time, you'll implement the one_hot_encode function. The input, x, are a list of labels. Implement the function to return the list of labels as One-Hot encoded Numpy array. The possible values for labels are 0 to 9. The one-hot encoding function should return the same encoding for each value between each call to one_hot_encode. Make sure to save the map of encodings outside the function.

Hint: Don't reinvent the wheel.



In [151]:

    
def one_hot_encode(x):
    """
    One hot encode a list of sample labels. Return a one-hot encoded vector for each label.
    : x: List of sample Labels
    : return: Numpy array of one-hot encoded labels
    """
                   
    # TODO: Implement Function
    one_hot_encoded = np.zeros((len(x), 10))
    
    one_hot_encoded[list(range(len(x))), x] = 1
    
    return one_hot_encoded


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_one_hot_encode(one_hot_encode)









    



Tests Passed

Randomize Data

As you saw from exploring the data above, the order of the samples are randomized. It doesn't hurt to randomize it again, but you don't need to for this dataset.

Preprocess all the data and save it

Running the code cell below will preprocess all the CIFAR-10 data and save it to file. The code below also uses 10% of the training data for validation.



In [130]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
# Preprocess Training, Validation, and Testing Data
helper.preprocess_and_save_data(cifar10_dataset_folder_path, normalize, one_hot_encode)

Check Point

This is your first checkpoint. If you ever decide to come back to this notebook or have to restart the notebook, you can start from here. The preprocessed data has been saved to disk.



In [127]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import pickle
import problem_unittests as tests
import helper

# Load the Preprocessed Validation data
valid_features, valid_labels = pickle.load(open('preprocess_validation.p', mode='rb'))

Build the network

For the neural network, you'll build each layer into a function. Most of the code you've seen has been outside of functions. To test your code more thoroughly, we require that you put each layer in a function. This allows us to give you better feedback and test for simple mistakes using our unittests before you submit your project.

If you're finding it hard to dedicate enough time for this course a week, we've provided a small shortcut to this part of the project. In the next couple of problems, you'll have the option to use TensorFlow Layers or TensorFlow Layers (contrib) to build each layer, except "Convolutional & Max Pooling" layer. TF Layers is similar to Keras's and TFLearn's abstraction to layers, so it's easy to pickup.

If you would like to get the most of this course, try to solve all the problems without TF Layers. Let's begin!

Input

The neural network needs to read the image data, one-hot encoded labels, and dropout keep probability. Implement the following functions

Implement neural_net_image_input
- Return a TF Placeholder
- Set the shape using image_shape with batch size set to None.
- Name the TensorFlow placeholder "x" using the TensorFlow name parameter in the TF Placeholder.
Implement neural_net_label_input
- Return a TF Placeholder
- Set the shape using n_classes with batch size set to None.
- Name the TensorFlow placeholder "y" using the TensorFlow name parameter in the TF Placeholder.
Implement neural_net_keep_prob_input
- Return a TF Placeholder for dropout keep probability.
- Name the TensorFlow placeholder "keep_prob" using the TensorFlow name parameter in the TF Placeholder.

These names will be used at the end of the project to load your saved model.

Note: None for shapes in TensorFlow allow for a dynamic size.



In [131]:

    
import tensorflow as tf

def neural_net_image_input(image_shape):
    """
    Return a Tensor for a bach of image input
    : image_shape: Shape of the images
    : return: Tensor for image input.
    """
    # TODO: Implement Function
    image_input = tf.placeholder(tf.float32, (None, image_shape[0], image_shape[1], image_shape[2]), name="x")
    
    
    return image_input


def neural_net_label_input(n_classes):
    """
    Return a Tensor for a batch of label input
    : n_classes: Number of classes
    : return: Tensor for label input.
    """
    # TODO: Implement Function
    label_input = tf.placeholder(tf.float32, (None, n_classes), name="y")
    
    return label_input


def neural_net_keep_prob_input():
    """
    Return a Tensor for keep probability
    : return: Tensor for keep probability.
    """
    # TODO: Implement Function
    keep_prob = tf.placeholder(tf.float32, name="keep_prob")
    return keep_prob


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tf.reset_default_graph()
tests.test_nn_image_inputs(neural_net_image_input)
tests.test_nn_label_inputs(neural_net_label_input)
tests.test_nn_keep_prob_inputs(neural_net_keep_prob_input)









    



Image Input Tests Passed.
Label Input Tests Passed.
Keep Prob Tests Passed.

Convolution and Max Pooling Layer

Convolution layers have a lot of success with images. For this code cell, you should implement the function conv2d_maxpool to apply convolution then max pooling:

Create the weight and bias using conv_ksize, conv_num_outputs and the shape of x_tensor.
Apply a convolution to x_tensor using weight and conv_strides.
- We recommend you use same padding, but you're welcome to use any padding.
Add bias
Add a nonlinear activation to the convolution.
Apply Max Pooling using pool_ksize and pool_strides.
- We recommend you use same padding, but you're welcome to use any padding.

Note: You can't use TensorFlow Layers or TensorFlow Layers (contrib) for this layer. You're free to use any TensorFlow package for all the other layers.



In [165]:

    
def conv2d_maxpool(x_tensor, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides):
    """
    Apply convolution then max pooling to x_tensor
    :param x_tensor: TensorFlow Tensor
    :param conv_num_outputs: Number of outputs for the convolutional layer
    :param conv_strides: Stride 2-D Tuple for convolution
    :param pool_ksize: kernal size 2-D Tuple for pool
    :param pool_strides: Stride 2-D Tuple for pool
    : return: A tensor that represents convolution and max pooling of x_tensor
    """
    # TODO: Implement Function
    
    F_W = tf.Variable(tf.truncated_normal([conv_ksize[0], conv_ksize[1], x_tensor.get_shape()[-1].value, conv_num_outputs], stddev=0.1))
    F_b = tf.Variable(tf.zeros(conv_num_outputs))
    strides_1 = [1, conv_strides[0], conv_strides[1], 1]
    padding = "SAME"
    
    conv2d_layer_1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x_tensor, F_W, strides_1, padding), F_b)) 
    
    # TODO: Set the ksize (filter size) for each dimension (batch_size, height, width, depth)
    ksize = [1, pool_ksize[0], pool_ksize[1], 1]
    strides_2 = [1, pool_strides[0], pool_strides[1], 1]
    max_pool_layer = tf.nn.max_pool(conv2d_layer_1, ksize, strides_2, padding)

    return max_pool_layer 


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_con_pool(conv2d_maxpool)









    



Tests Passed

Flatten Layer

Implement the flatten function to change the dimension of x_tensor from a 4-D tensor to a 2-D tensor. The output should be the shape (Batch Size, Flattened Image Size). You can use TensorFlow Layers or TensorFlow Layers (contrib) for this layer.



In [133]:

    
def flatten(x_tensor):
    """
    Flatten x_tensor to (Batch Size, Flattened Image Size)
    : x_tensor: A tensor of size (Batch Size, ...), where ... are the image dimensions.
    : return: A tensor of size (Batch Size, Flattened Image Size).
    """
    # TODO: Implement Function
    shape = x_tensor.get_shape().as_list()
    dim = np.prod(shape[1:])   
    
    x_reshaped = tf.reshape(x_tensor, [-1, dim])
    
    return x_reshaped


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_flatten(flatten)









    



Tests Passed

Fully-Connected Layer

Implement the fully_conn function to apply a fully connected layer to x_tensor with the shape (Batch Size, num_outputs). You can use TensorFlow Layers or TensorFlow Layers (contrib) for this layer.



In [166]:

    
def fully_conn(x_tensor, num_outputs):
    """
    Apply a fully connected layer to x_tensor using weight and bias
    : x_tensor: A 2-D tensor where the first dimension is batch size.
    : num_outputs: The number of output that the new tensor should be.
    : return: A 2-D tensor where the second dimension is num_outputs.
    """
    # TODO: Implement Function
    dim = x_tensor.get_shape().as_list()[-1]
    weights = tf.Variable(tf.truncated_normal([dim, num_outputs], stddev=0.1))
    biases = tf.Variable(tf.zeros(num_outputs))
    
    return tf.nn.relu(tf.matmul(x_tensor, weights) + biases)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_fully_conn(fully_conn)









    



Tests Passed

Output Layer

Implement the output function to apply a fully connected layer to x_tensor with the shape (Batch Size, num_outputs). You can use TensorFlow Layers or TensorFlow Layers (contrib) for this layer.

Note: Activation, softmax, or cross entropy shouldn't be applied to this.



In [136]:

    
def output(x_tensor, num_outputs):
    """
    Apply a output layer to x_tensor using weight and bias
    : x_tensor: A 2-D tensor where the first dimension is batch size.
    : num_outputs: The number of output that the new tensor should be.
    : return: A 2-D tensor where the second dimension is num_outputs.
    """
    # TODO: Implement Function
    dim = x_tensor.get_shape().as_list()[-1]
    weights = tf.Variable(tf.truncated_normal([dim, num_outputs]))
    biases = tf.Variable(tf.zeros(num_outputs))
    
    return tf.matmul(x_tensor, weights) + biases


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_output(output)









    



Tests Passed

Create Convolutional Model

Implement the function conv_net to create a convolutional neural network model. The function takes in a batch of images, x, and outputs logits. Use the layers you created above to create this model:

Apply 1, 2, or 3 Convolution and Max Pool layers
Apply a Flatten Layer
Apply 1, 2, or 3 Fully Connected Layers
Apply an Output Layer
Return the output
Apply TensorFlow's Dropout to one or more layers in the model using keep_prob.



In [173]:

    
def conv_net(x, keep_prob):
    """
    Create a convolutional neural network model
    : x: Placeholder tensor that holds image data.
    : keep_prob: Placeholder tensor that hold dropout keep probability.
    : return: Tensor that represents logits
    """
    # TODO: Apply 1, 2, or 3 Convolution and Max Pool layers
    #    Play around with different number of outputs, kernel size and stride
    # Function Definition from Above:
    
    
    # Set parameters
    conv_num_outputs = 64
    conv_ksize = (5, 5) 
    conv_strides = (2, 2) 
    pool_ksize = (2, 2)
    pool_strides = (2, 2) 
    
    # Conv 1 
    x = tf.nn.dropout(conv2d_maxpool(x, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides), keep_prob)
    
    # Conv 2 
    x = conv2d_maxpool(x, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides)

    # TODO: Apply a Flatten Layer
    # Function Definition from Above:
    x = flatten(x)
    
    
    # TODO: Apply 1, 2, or 3 Fully Connected Layers
    #    Play around with different number of outputs
    # Function Definition from Above:
    
    
    # Set up Fully Connected layers
    
    # FC 1
    x = tf.nn.dropout(fully_conn(x, 1024), keep_prob)
    
    # TODO: Apply an Output Layer
    #    Set this to the number of classes
    # Function Definition from Above:
    #   output(x_tensor, num_outputs)
    
    output_tensor = output(x, 10)
    # TODO: return output
    return output_tensor


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""

##############################
## Build the Neural Network ##
##############################

# Remove previous weights, bias, inputs, etc..
tf.reset_default_graph()

# Inputs
x = neural_net_image_input((32, 32, 3))
y = neural_net_label_input(10)
keep_prob = neural_net_keep_prob_input()

# Model
logits = conv_net(x, keep_prob)

# Name logits Tensor, so that is can be loaded from disk after training
logits = tf.identity(logits, name='logits')

# Loss and Optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
optimizer = tf.train.AdamOptimizer().minimize(cost)

# Accuracy
correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32), name='accuracy')

tests.test_conv_net(conv_net)









    



Neural Network Built!

Train the Neural Network

Single Optimization

Implement the function train_neural_network to do a single optimization. The optimization should use optimizer to optimize in session with a feed_dict of the following:

x for image input
y for labels
keep_prob for keep probability for dropout

This function will be called for each batch, so tf.global_variables_initializer() has already been called.

Note: Nothing needs to be returned. This function is only optimizing the neural network.



In [174]:

    
def train_neural_network(session, optimizer, keep_probability, feature_batch, label_batch):
    """
    Optimize the session on a batch of images and labels
    : session: Current TensorFlow session
    : optimizer: TensorFlow optimizer function
    : keep_probability: keep probability
    : feature_batch: Batch of Numpy image data
    : label_batch: Batch of Numpy label data
    """
    # TODO: Implement Function
    
    session.run(optimizer, feed_dict={x : feature_batch, 
                                      y: label_batch, 
                                      keep_prob: keep_probability})
    


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_train_nn(train_neural_network)









    



Tests Passed

Show Stats

Implement the function print_stats to print loss and validation accuracy. Use the global variables valid_features and valid_labels to calculate validation accuracy. Use a keep probability of 1.0 to calculate the loss and validation accuracy.



In [162]:

    
def print_stats(session, feature_batch, label_batch, cost, accuracy):
    """
    Print information about loss and validation accuracy
    : session: Current TensorFlow session
    : feature_batch: Batch of Numpy image data
    : label_batch: Batch of Numpy label data
    : cost: TensorFlow cost function
    : accuracy: TensorFlow accuracy function
    """
    # TODO: Implement Function
    batch_loss, batch_accuracy = session.run([cost, accuracy], feed_dict={x : feature_batch, 
                                                                         y: label_batch, 
                                                                         keep_prob : 1.0})
    
    valid_loss, valid_accuracy = session.run([cost, accuracy], feed_dict={x : valid_features, 
                                                                     y: valid_labels, 
                                                                     keep_prob : 1.0})

    print("Batch Loss - {}; Batch Accuracy - {:>.2}".format(batch_loss, batch_accuracy))
    print("Valid Loss - {}; Valid Accuracy - {:>.2}".format(valid_loss, valid_accuracy))

Hyperparameters

Tune the following parameters:

Set epochs to the number of iterations until the network stops learning or start overfitting
Set batch_size to the highest number that your machine has memory for. Most people set them to common sizes of memory:
- 64
- 128
- 256
- ...
Set keep_probability to the probability of keeping a node using dropout



In [158]:

    
# TODO: Tune Parameters
epochs = 200
batch_size = 256
keep_probability = 0.5

Train on a Single CIFAR-10 Batch

Instead of training the neural network on all the CIFAR-10 batches of data, let's use a single batch. This should save time while you iterate on the model to get a better accuracy. Once the final validation accuracy is 50% or greater, run the model on all the data in the next section.



In [176]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
print('Checking the Training on a Single Batch...')

with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:
    # Initializing the variables
    sess.run(tf.global_variables_initializer())
    
    # Training cycle
    for epoch in range(epochs):
        batch_i = 1
        for batch_features, batch_labels in helper.load_preprocess_training_batch(batch_i, batch_size):
            train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels)
        print('Epoch {:>2}, CIFAR-10 Batch {}:  '.format(epoch + 1, batch_i), end='')
        print_stats(sess, batch_features, batch_labels, cost, accuracy)









    



Checking the Training on a Single Batch...
Epoch  1, CIFAR-10 Batch 1:  Batch Loss - 2.3098745346069336; Batch Accuracy - 0.1
Valid Loss - 2.310272216796875; Valid Accuracy - 0.097
Epoch  2, CIFAR-10 Batch 1:  Batch Loss - 2.3063931465148926; Batch Accuracy - 0.05
Valid Loss - 2.30383563041687; Valid Accuracy - 0.097
Epoch  3, CIFAR-10 Batch 1:  Batch Loss - 2.308915138244629; Batch Accuracy - 0.05
Valid Loss - 2.305217742919922; Valid Accuracy - 0.097
Epoch  4, CIFAR-10 Batch 1:  Batch Loss - 2.304004669189453; Batch Accuracy - 0.1
Valid Loss - 2.302351474761963; Valid Accuracy - 0.097
Epoch  5, CIFAR-10 Batch 1:  Batch Loss - 2.296966314315796; Batch Accuracy - 0.15
Valid Loss - 2.296201467514038; Valid Accuracy - 0.11
Epoch  6, CIFAR-10 Batch 1:  Batch Loss - 2.2722280025482178; Batch Accuracy - 0.15
Valid Loss - 2.2761616706848145; Valid Accuracy - 0.14
Epoch  7, CIFAR-10 Batch 1:  Batch Loss - 2.261202812194824; Batch Accuracy - 0.17
Valid Loss - 2.262296199798584; Valid Accuracy - 0.13
Epoch  8, CIFAR-10 Batch 1:  Batch Loss - 2.2679083347320557; Batch Accuracy - 0.12
Valid Loss - 2.1893491744995117; Valid Accuracy - 0.16
Epoch  9, CIFAR-10 Batch 1:  Batch Loss - 2.26381254196167; Batch Accuracy - 0.12
Valid Loss - 2.1711201667785645; Valid Accuracy - 0.19
Epoch 10, CIFAR-10 Batch 1:  Batch Loss - 2.256701946258545; Batch Accuracy - 0.12
Valid Loss - 2.132398843765259; Valid Accuracy - 0.21
Epoch 11, CIFAR-10 Batch 1:  Batch Loss - 2.1897788047790527; Batch Accuracy - 0.18
Valid Loss - 2.1041929721832275; Valid Accuracy - 0.21
Epoch 12, CIFAR-10 Batch 1:  Batch Loss - 2.134012222290039; Batch Accuracy - 0.28
Valid Loss - 2.0741207599639893; Valid Accuracy - 0.24
Epoch 13, CIFAR-10 Batch 1:  Batch Loss - 2.1031973361968994; Batch Accuracy - 0.28
Valid Loss - 2.0381789207458496; Valid Accuracy - 0.25
Epoch 14, CIFAR-10 Batch 1:  Batch Loss - 2.0748746395111084; Batch Accuracy - 0.33
Valid Loss - 2.043717861175537; Valid Accuracy - 0.24
Epoch 15, CIFAR-10 Batch 1:  Batch Loss - 1.968799352645874; Batch Accuracy - 0.4
Valid Loss - 1.9577515125274658; Valid Accuracy - 0.28
Epoch 16, CIFAR-10 Batch 1:  Batch Loss - 2.001239061355591; Batch Accuracy - 0.28
Valid Loss - 1.9900619983673096; Valid Accuracy - 0.26
Epoch 17, CIFAR-10 Batch 1:  Batch Loss - 1.9351155757904053; Batch Accuracy - 0.28
Valid Loss - 1.9378236532211304; Valid Accuracy - 0.28
Epoch 18, CIFAR-10 Batch 1:  Batch Loss - 1.8845093250274658; Batch Accuracy - 0.28
Valid Loss - 1.9332958459854126; Valid Accuracy - 0.28
Epoch 19, CIFAR-10 Batch 1:  Batch Loss - 1.8257238864898682; Batch Accuracy - 0.38
Valid Loss - 1.8571033477783203; Valid Accuracy - 0.3
Epoch 20, CIFAR-10 Batch 1:  Batch Loss - 1.798523187637329; Batch Accuracy - 0.45
Valid Loss - 1.8141368627548218; Valid Accuracy - 0.32
Epoch 21, CIFAR-10 Batch 1:  Batch Loss - 1.7288577556610107; Batch Accuracy - 0.45
Valid Loss - 1.7998576164245605; Valid Accuracy - 0.32
Epoch 22, CIFAR-10 Batch 1:  Batch Loss - 1.7155382633209229; Batch Accuracy - 0.48
Valid Loss - 1.7838352918624878; Valid Accuracy - 0.33
Epoch 23, CIFAR-10 Batch 1:  Batch Loss - 1.6550045013427734; Batch Accuracy - 0.48
Valid Loss - 1.7240384817123413; Valid Accuracy - 0.36
Epoch 24, CIFAR-10 Batch 1:  Batch Loss - 1.6647083759307861; Batch Accuracy - 0.45
Valid Loss - 1.7781119346618652; Valid Accuracy - 0.34
Epoch 25, CIFAR-10 Batch 1:  Batch Loss - 1.629422664642334; Batch Accuracy - 0.4
Valid Loss - 1.7577799558639526; Valid Accuracy - 0.34
Epoch 26, CIFAR-10 Batch 1:  Batch Loss - 1.5527737140655518; Batch Accuracy - 0.45
Valid Loss - 1.6878464221954346; Valid Accuracy - 0.37
Epoch 27, CIFAR-10 Batch 1:  Batch Loss - 1.5140039920806885; Batch Accuracy - 0.48
Valid Loss - 1.6964589357376099; Valid Accuracy - 0.37
Epoch 28, CIFAR-10 Batch 1:  Batch Loss - 1.482884407043457; Batch Accuracy - 0.43
Valid Loss - 1.6757797002792358; Valid Accuracy - 0.37
Epoch 29, CIFAR-10 Batch 1:  Batch Loss - 1.475799560546875; Batch Accuracy - 0.5
Valid Loss - 1.6734312772750854; Valid Accuracy - 0.37
Epoch 30, CIFAR-10 Batch 1:  Batch Loss - 1.4384335279464722; Batch Accuracy - 0.53
Valid Loss - 1.6752755641937256; Valid Accuracy - 0.38
Epoch 31, CIFAR-10 Batch 1:  Batch Loss - 1.4433021545410156; Batch Accuracy - 0.53
Valid Loss - 1.6597038507461548; Valid Accuracy - 0.38
Epoch 32, CIFAR-10 Batch 1:  Batch Loss - 1.4385485649108887; Batch Accuracy - 0.53
Valid Loss - 1.6129162311553955; Valid Accuracy - 0.4
Epoch 33, CIFAR-10 Batch 1:  Batch Loss - 1.3419891595840454; Batch Accuracy - 0.6
Valid Loss - 1.6032633781433105; Valid Accuracy - 0.4
Epoch 34, CIFAR-10 Batch 1:  Batch Loss - 1.3719440698623657; Batch Accuracy - 0.47
Valid Loss - 1.6130034923553467; Valid Accuracy - 0.4
Epoch 35, CIFAR-10 Batch 1:  Batch Loss - 1.2871017456054688; Batch Accuracy - 0.6
Valid Loss - 1.5665053129196167; Valid Accuracy - 0.42
Epoch 36, CIFAR-10 Batch 1:  Batch Loss - 1.3113770484924316; Batch Accuracy - 0.53
Valid Loss - 1.594038963317871; Valid Accuracy - 0.41
Epoch 37, CIFAR-10 Batch 1:  Batch Loss - 1.2598185539245605; Batch Accuracy - 0.62
Valid Loss - 1.6090431213378906; Valid Accuracy - 0.4
Epoch 38, CIFAR-10 Batch 1:  Batch Loss - 1.2030283212661743; Batch Accuracy - 0.55
Valid Loss - 1.5719841718673706; Valid Accuracy - 0.41
Epoch 39, CIFAR-10 Batch 1:  Batch Loss - 1.1501761674880981; Batch Accuracy - 0.7
Valid Loss - 1.552891731262207; Valid Accuracy - 0.42
Epoch 40, CIFAR-10 Batch 1:  Batch Loss - 1.1897273063659668; Batch Accuracy - 0.62
Valid Loss - 1.5872225761413574; Valid Accuracy - 0.41
Epoch 41, CIFAR-10 Batch 1:  Batch Loss - 1.153681755065918; Batch Accuracy - 0.7
Valid Loss - 1.544177770614624; Valid Accuracy - 0.43
Epoch 42, CIFAR-10 Batch 1:  Batch Loss - 1.1354330778121948; Batch Accuracy - 0.68
Valid Loss - 1.5179798603057861; Valid Accuracy - 0.43
Epoch 43, CIFAR-10 Batch 1:  Batch Loss - 1.1123679876327515; Batch Accuracy - 0.62
Valid Loss - 1.5304431915283203; Valid Accuracy - 0.43
Epoch 44, CIFAR-10 Batch 1:  Batch Loss - 1.0699050426483154; Batch Accuracy - 0.7
Valid Loss - 1.5273427963256836; Valid Accuracy - 0.43
Epoch 45, CIFAR-10 Batch 1:  Batch Loss - 1.062975525856018; Batch Accuracy - 0.78
Valid Loss - 1.529001235961914; Valid Accuracy - 0.43
Epoch 46, CIFAR-10 Batch 1:  Batch Loss - 1.0005519390106201; Batch Accuracy - 0.73
Valid Loss - 1.5129600763320923; Valid Accuracy - 0.44
Epoch 47, CIFAR-10 Batch 1:  Batch Loss - 0.9820792078971863; Batch Accuracy - 0.73
Valid Loss - 1.5182850360870361; Valid Accuracy - 0.44
Epoch 48, CIFAR-10 Batch 1:  Batch Loss - 0.9062871932983398; Batch Accuracy - 0.83
Valid Loss - 1.4960882663726807; Valid Accuracy - 0.45
Epoch 49, CIFAR-10 Batch 1:  Batch Loss - 0.9625035524368286; Batch Accuracy - 0.75
Valid Loss - 1.521624207496643; Valid Accuracy - 0.45
Epoch 50, CIFAR-10 Batch 1:  Batch Loss - 0.8705520629882812; Batch Accuracy - 0.8
Valid Loss - 1.5014318227767944; Valid Accuracy - 0.45
Epoch 51, CIFAR-10 Batch 1:  Batch Loss - 0.847429633140564; Batch Accuracy - 0.8
Valid Loss - 1.4718585014343262; Valid Accuracy - 0.46
Epoch 52, CIFAR-10 Batch 1:  Batch Loss - 0.8212205767631531; Batch Accuracy - 0.8
Valid Loss - 1.4440211057662964; Valid Accuracy - 0.46
Epoch 53, CIFAR-10 Batch 1:  Batch Loss - 0.7967441082000732; Batch Accuracy - 0.83
Valid Loss - 1.4943900108337402; Valid Accuracy - 0.45
Epoch 54, CIFAR-10 Batch 1:  Batch Loss - 0.7718554735183716; Batch Accuracy - 0.85
Valid Loss - 1.469313621520996; Valid Accuracy - 0.46
Epoch 55, CIFAR-10 Batch 1:  Batch Loss - 0.8154870271682739; Batch Accuracy - 0.85
Valid Loss - 1.5112221240997314; Valid Accuracy - 0.44
Epoch 56, CIFAR-10 Batch 1:  Batch Loss - 0.7779514193534851; Batch Accuracy - 0.85
Valid Loss - 1.5109577178955078; Valid Accuracy - 0.45
Epoch 57, CIFAR-10 Batch 1:  Batch Loss - 0.7062383890151978; Batch Accuracy - 0.85
Valid Loss - 1.4359220266342163; Valid Accuracy - 0.48
Epoch 58, CIFAR-10 Batch 1:  Batch Loss - 0.6549920439720154; Batch Accuracy - 0.85
Valid Loss - 1.4361329078674316; Valid Accuracy - 0.48
Epoch 59, CIFAR-10 Batch 1:  Batch Loss - 0.6519718766212463; Batch Accuracy - 0.88
Valid Loss - 1.4542245864868164; Valid Accuracy - 0.47
Epoch 60, CIFAR-10 Batch 1:  Batch Loss - 0.6798316240310669; Batch Accuracy - 0.85
Valid Loss - 1.4519952535629272; Valid Accuracy - 0.47
Epoch 61, CIFAR-10 Batch 1:  Batch Loss - 0.6629111766815186; Batch Accuracy - 0.85
Valid Loss - 1.4440886974334717; Valid Accuracy - 0.48
Epoch 62, CIFAR-10 Batch 1:  Batch Loss - 0.5994390249252319; Batch Accuracy - 0.88
Valid Loss - 1.4241082668304443; Valid Accuracy - 0.49
Epoch 63, CIFAR-10 Batch 1:  Batch Loss - 0.5839798450469971; Batch Accuracy - 0.85
Valid Loss - 1.4139524698257446; Valid Accuracy - 0.49
Epoch 64, CIFAR-10 Batch 1:  Batch Loss - 0.5931031703948975; Batch Accuracy - 0.8
Valid Loss - 1.4648581743240356; Valid Accuracy - 0.48
Epoch 65, CIFAR-10 Batch 1:  Batch Loss - 0.5114767551422119; Batch Accuracy - 0.93
Valid Loss - 1.408081293106079; Valid Accuracy - 0.49
Epoch 66, CIFAR-10 Batch 1:  Batch Loss - 0.5036602020263672; Batch Accuracy - 0.88
Valid Loss - 1.3748445510864258; Valid Accuracy - 0.5
Epoch 67, CIFAR-10 Batch 1:  Batch Loss - 0.5032857060432434; Batch Accuracy - 0.9
Valid Loss - 1.4134432077407837; Valid Accuracy - 0.49
Epoch 68, CIFAR-10 Batch 1:  Batch Loss - 0.4637836217880249; Batch Accuracy - 0.9
Valid Loss - 1.383981466293335; Valid Accuracy - 0.5
Epoch 69, CIFAR-10 Batch 1:  Batch Loss - 0.45570072531700134; Batch Accuracy - 0.9
Valid Loss - 1.38397216796875; Valid Accuracy - 0.5
Epoch 70, CIFAR-10 Batch 1:  Batch Loss - 0.4740965962409973; Batch Accuracy - 0.92
Valid Loss - 1.3774892091751099; Valid Accuracy - 0.5
Epoch 71, CIFAR-10 Batch 1:  Batch Loss - 0.4537332057952881; Batch Accuracy - 0.95
Valid Loss - 1.430383324623108; Valid Accuracy - 0.5
Epoch 72, CIFAR-10 Batch 1:  Batch Loss - 0.42172926664352417; Batch Accuracy - 0.92
Valid Loss - 1.3672714233398438; Valid Accuracy - 0.51
Epoch 73, CIFAR-10 Batch 1:  Batch Loss - 0.4041602909564972; Batch Accuracy - 0.95
Valid Loss - 1.3942815065383911; Valid Accuracy - 0.51
Epoch 74, CIFAR-10 Batch 1:  Batch Loss - 0.41348937153816223; Batch Accuracy - 0.92
Valid Loss - 1.3900405168533325; Valid Accuracy - 0.51
Epoch 75, CIFAR-10 Batch 1:  Batch Loss - 0.4082373082637787; Batch Accuracy - 0.88
Valid Loss - 1.4052402973175049; Valid Accuracy - 0.5
Epoch 76, CIFAR-10 Batch 1:  Batch Loss - 0.36298850178718567; Batch Accuracy - 0.95
Valid Loss - 1.4231584072113037; Valid Accuracy - 0.49
Epoch 77, CIFAR-10 Batch 1:  Batch Loss - 0.34987446665763855; Batch Accuracy - 0.93
Valid Loss - 1.4031424522399902; Valid Accuracy - 0.51
Epoch 78, CIFAR-10 Batch 1:  Batch Loss - 0.3524335026741028; Batch Accuracy - 0.92
Valid Loss - 1.3515254259109497; Valid Accuracy - 0.52
Epoch 79, CIFAR-10 Batch 1:  Batch Loss - 0.35520103573799133; Batch Accuracy - 0.92
Valid Loss - 1.3714359998703003; Valid Accuracy - 0.52
Epoch 80, CIFAR-10 Batch 1:  Batch Loss - 0.32429397106170654; Batch Accuracy - 0.98
Valid Loss - 1.3610509634017944; Valid Accuracy - 0.52
Epoch 81, CIFAR-10 Batch 1:  Batch Loss - 0.2875862717628479; Batch Accuracy - 0.95
Valid Loss - 1.367314100265503; Valid Accuracy - 0.53
Epoch 82, CIFAR-10 Batch 1:  Batch Loss - 0.27254149317741394; Batch Accuracy - 0.98
Valid Loss - 1.3720929622650146; Valid Accuracy - 0.52
Epoch 83, CIFAR-10 Batch 1:  Batch Loss - 0.27915629744529724; Batch Accuracy - 0.95
Valid Loss - 1.357853889465332; Valid Accuracy - 0.53
Epoch 84, CIFAR-10 Batch 1:  Batch Loss - 0.27135318517684937; Batch Accuracy - 0.98
Valid Loss - 1.3615716695785522; Valid Accuracy - 0.53
Epoch 85, CIFAR-10 Batch 1:  Batch Loss - 0.28655481338500977; Batch Accuracy - 0.98
Valid Loss - 1.3523821830749512; Valid Accuracy - 0.53
Epoch 86, CIFAR-10 Batch 1:  Batch Loss - 0.2741066813468933; Batch Accuracy - 0.98
Valid Loss - 1.3756533861160278; Valid Accuracy - 0.52
Epoch 87, CIFAR-10 Batch 1:  Batch Loss - 0.25518643856048584; Batch Accuracy - 0.98
Valid Loss - 1.3589999675750732; Valid Accuracy - 0.53
Epoch 88, CIFAR-10 Batch 1:  Batch Loss - 0.26818913221359253; Batch Accuracy - 0.95
Valid Loss - 1.3555885553359985; Valid Accuracy - 0.52
Epoch 89, CIFAR-10 Batch 1:  Batch Loss - 0.24127790331840515; Batch Accuracy - 0.98
Valid Loss - 1.3964769840240479; Valid Accuracy - 0.52
Epoch 90, CIFAR-10 Batch 1:  Batch Loss - 0.2213188260793686; Batch Accuracy - 0.98
Valid Loss - 1.3652842044830322; Valid Accuracy - 0.53






    



---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-176-af9d5ffa77aa> in <module>()
     12         batch_i = 1
     13         for batch_features, batch_labels in helper.load_preprocess_training_batch(batch_i, batch_size):
---> 14             train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels)
     15         print('Epoch {:>2}, CIFAR-10 Batch {}:  '.format(epoch + 1, batch_i), end='')
     16         print_stats(sess, batch_features, batch_labels, cost, accuracy)

<ipython-input-174-2f4efad22a64> in train_neural_network(session, optimizer, keep_probability, feature_batch, label_batch)
     12     session.run(optimizer, feed_dict={x : feature_batch, 
     13                                       y: label_batch,
---> 14                                       keep_prob: keep_probability})
     15 
     16 

/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    765     try:
    766       result = self._run(None, fetches, feed_dict, options_ptr,
--> 767                          run_metadata_ptr)
    768       if run_metadata:
    769         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
    963     if final_fetches or final_targets:
    964       results = self._do_run(handle, final_targets, final_fetches,
--> 965                              feed_dict_string, options, run_metadata)
    966     else:
    967       results = []

/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1013     if handle is None:
   1014       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1015                            target_list, options, run_metadata)
   1016     else:
   1017       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1020   def _do_call(self, fn, *args):
   1021     try:
-> 1022       return fn(*args)
   1023     except errors.OpError as e:
   1024       message = compat.as_text(e.message)

/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1002         return tf_session.TF_Run(session, options,
   1003                                  feed_dict, fetch_list, target_list,
-> 1004                                  status, run_metadata)
   1005 
   1006     def _prun_fn(session, handle, feed_dict, fetch_list):

KeyboardInterrupt:

Fully Train the Model

Now that you got a good accuracy with a single CIFAR-10 batch, try it with all five batches.



In [177]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
save_model_path = './image_classification'

print('Training...')
with tf.Session() as sess:
    # Initializing the variables
    sess.run(tf.global_variables_initializer())
    
    # Training cycle
    for epoch in range(epochs):
        # Loop over all batches
        n_batches = 5
        for batch_i in range(1, n_batches + 1):
            for batch_features, batch_labels in helper.load_preprocess_training_batch(batch_i, batch_size):
                train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels)
            print('Epoch {:>2}, CIFAR-10 Batch {}:  '.format(epoch + 1, batch_i), end='')
            print_stats(sess, batch_features, batch_labels, cost, accuracy)
            
    # Save Model
    saver = tf.train.Saver()
    save_path = saver.save(sess, save_model_path)









    



Training...
Epoch  1, CIFAR-10 Batch 1:  Batch Loss - 2.2723727226257324; Batch Accuracy - 0.2
Valid Loss - 2.3043293952941895; Valid Accuracy - 0.1
Epoch  1, CIFAR-10 Batch 2:  Batch Loss - 2.305101156234741; Batch Accuracy - 0.12
Valid Loss - 2.3022682666778564; Valid Accuracy - 0.11
Epoch  1, CIFAR-10 Batch 3:  Batch Loss - 2.2989532947540283; Batch Accuracy - 0.05
Valid Loss - 2.3051981925964355; Valid Accuracy - 0.097
Epoch  1, CIFAR-10 Batch 4:  Batch Loss - 2.279672622680664; Batch Accuracy - 0.15
Valid Loss - 2.3071537017822266; Valid Accuracy - 0.11
Epoch  1, CIFAR-10 Batch 5:  Batch Loss - 2.3033008575439453; Batch Accuracy - 0.1
Valid Loss - 2.2558422088623047; Valid Accuracy - 0.14
Epoch  2, CIFAR-10 Batch 1:  Batch Loss - 2.2031338214874268; Batch Accuracy - 0.18
Valid Loss - 2.1684865951538086; Valid Accuracy - 0.19
Epoch  2, CIFAR-10 Batch 2:  Batch Loss - 2.1282711029052734; Batch Accuracy - 0.12
Valid Loss - 2.181185722351074; Valid Accuracy - 0.17
Epoch  2, CIFAR-10 Batch 3:  Batch Loss - 2.081914186477661; Batch Accuracy - 0.075
Valid Loss - 2.083425521850586; Valid Accuracy - 0.2
Epoch  2, CIFAR-10 Batch 4:  Batch Loss - 1.974081039428711; Batch Accuracy - 0.18
Valid Loss - 1.971022605895996; Valid Accuracy - 0.27
Epoch  2, CIFAR-10 Batch 5:  Batch Loss - 2.052668571472168; Batch Accuracy - 0.18
Valid Loss - 1.9630753993988037; Valid Accuracy - 0.28
Epoch  3, CIFAR-10 Batch 1:  Batch Loss - 2.052014112472534; Batch Accuracy - 0.25
Valid Loss - 1.9032204151153564; Valid Accuracy - 0.29
Epoch  3, CIFAR-10 Batch 2:  Batch Loss - 1.8005895614624023; Batch Accuracy - 0.38
Valid Loss - 1.8712955713272095; Valid Accuracy - 0.3
Epoch  3, CIFAR-10 Batch 3:  Batch Loss - 1.7447452545166016; Batch Accuracy - 0.3
Valid Loss - 1.8146655559539795; Valid Accuracy - 0.32
Epoch  3, CIFAR-10 Batch 4:  Batch Loss - 1.7820981740951538; Batch Accuracy - 0.38
Valid Loss - 1.7914495468139648; Valid Accuracy - 0.33
Epoch  3, CIFAR-10 Batch 5:  Batch Loss - 1.8700635433197021; Batch Accuracy - 0.33
Valid Loss - 1.7940495014190674; Valid Accuracy - 0.33
Epoch  4, CIFAR-10 Batch 1:  Batch Loss - 1.9348024129867554; Batch Accuracy - 0.38
Valid Loss - 1.7431700229644775; Valid Accuracy - 0.34
Epoch  4, CIFAR-10 Batch 2:  Batch Loss - 1.761573314666748; Batch Accuracy - 0.33
Valid Loss - 1.7650089263916016; Valid Accuracy - 0.34
Epoch  4, CIFAR-10 Batch 3:  Batch Loss - 1.6008763313293457; Batch Accuracy - 0.4
Valid Loss - 1.707787036895752; Valid Accuracy - 0.34
Epoch  4, CIFAR-10 Batch 4:  Batch Loss - 1.7103396654129028; Batch Accuracy - 0.38
Valid Loss - 1.6872977018356323; Valid Accuracy - 0.36
Epoch  4, CIFAR-10 Batch 5:  Batch Loss - 1.808842658996582; Batch Accuracy - 0.35
Valid Loss - 1.6919363737106323; Valid Accuracy - 0.35
Epoch  5, CIFAR-10 Batch 1:  Batch Loss - 1.7828236818313599; Batch Accuracy - 0.38
Valid Loss - 1.6625590324401855; Valid Accuracy - 0.37
Epoch  5, CIFAR-10 Batch 2:  Batch Loss - 1.6690740585327148; Batch Accuracy - 0.45
Valid Loss - 1.689131259918213; Valid Accuracy - 0.36
Epoch  5, CIFAR-10 Batch 3:  Batch Loss - 1.5746195316314697; Batch Accuracy - 0.3
Valid Loss - 1.697702407836914; Valid Accuracy - 0.35
Epoch  5, CIFAR-10 Batch 4:  Batch Loss - 1.6925604343414307; Batch Accuracy - 0.43
Valid Loss - 1.637685775756836; Valid Accuracy - 0.38
Epoch  5, CIFAR-10 Batch 5:  Batch Loss - 1.6955095529556274; Batch Accuracy - 0.3
Valid Loss - 1.666447639465332; Valid Accuracy - 0.36
Epoch  6, CIFAR-10 Batch 1:  Batch Loss - 1.7114026546478271; Batch Accuracy - 0.43
Valid Loss - 1.615731954574585; Valid Accuracy - 0.39
Epoch  6, CIFAR-10 Batch 2:  Batch Loss - 1.573190689086914; Batch Accuracy - 0.4
Valid Loss - 1.623391032218933; Valid Accuracy - 0.39
Epoch  6, CIFAR-10 Batch 3:  Batch Loss - 1.445300817489624; Batch Accuracy - 0.4
Valid Loss - 1.5988670587539673; Valid Accuracy - 0.4
Epoch  6, CIFAR-10 Batch 4:  Batch Loss - 1.6277425289154053; Batch Accuracy - 0.5
Valid Loss - 1.5927374362945557; Valid Accuracy - 0.4
Epoch  6, CIFAR-10 Batch 5:  Batch Loss - 1.618270993232727; Batch Accuracy - 0.35
Valid Loss - 1.6260325908660889; Valid Accuracy - 0.38
Epoch  7, CIFAR-10 Batch 1:  Batch Loss - 1.6849193572998047; Batch Accuracy - 0.35
Valid Loss - 1.5857294797897339; Valid Accuracy - 0.4
Epoch  7, CIFAR-10 Batch 2:  Batch Loss - 1.509460210800171; Batch Accuracy - 0.42
Valid Loss - 1.6337941884994507; Valid Accuracy - 0.38
Epoch  7, CIFAR-10 Batch 3:  Batch Loss - 1.439165472984314; Batch Accuracy - 0.43
Valid Loss - 1.5740405321121216; Valid Accuracy - 0.41
Epoch  7, CIFAR-10 Batch 4:  Batch Loss - 1.6159671545028687; Batch Accuracy - 0.47
Valid Loss - 1.5365132093429565; Valid Accuracy - 0.43
Epoch  7, CIFAR-10 Batch 5:  Batch Loss - 1.5761916637420654; Batch Accuracy - 0.4
Valid Loss - 1.5582404136657715; Valid Accuracy - 0.41
Epoch  8, CIFAR-10 Batch 1:  Batch Loss - 1.6252684593200684; Batch Accuracy - 0.38
Valid Loss - 1.5691161155700684; Valid Accuracy - 0.41
Epoch  8, CIFAR-10 Batch 2:  Batch Loss - 1.4475690126419067; Batch Accuracy - 0.5
Valid Loss - 1.5775501728057861; Valid Accuracy - 0.4
Epoch  8, CIFAR-10 Batch 3:  Batch Loss - 1.3716838359832764; Batch Accuracy - 0.45
Valid Loss - 1.5629557371139526; Valid Accuracy - 0.41
Epoch  8, CIFAR-10 Batch 4:  Batch Loss - 1.4940872192382812; Batch Accuracy - 0.5
Valid Loss - 1.496633529663086; Valid Accuracy - 0.44
Epoch  8, CIFAR-10 Batch 5:  Batch Loss - 1.527636170387268; Batch Accuracy - 0.48
Valid Loss - 1.5504143238067627; Valid Accuracy - 0.42
Epoch  9, CIFAR-10 Batch 1:  Batch Loss - 1.607211947441101; Batch Accuracy - 0.42
Valid Loss - 1.5036389827728271; Valid Accuracy - 0.44
Epoch  9, CIFAR-10 Batch 2:  Batch Loss - 1.4033920764923096; Batch Accuracy - 0.55
Valid Loss - 1.5204519033432007; Valid Accuracy - 0.43
Epoch  9, CIFAR-10 Batch 3:  Batch Loss - 1.3453335762023926; Batch Accuracy - 0.43
Valid Loss - 1.5116363763809204; Valid Accuracy - 0.43
Epoch  9, CIFAR-10 Batch 4:  Batch Loss - 1.4583673477172852; Batch Accuracy - 0.5
Valid Loss - 1.4729576110839844; Valid Accuracy - 0.45
Epoch  9, CIFAR-10 Batch 5:  Batch Loss - 1.513331413269043; Batch Accuracy - 0.45
Valid Loss - 1.5383411645889282; Valid Accuracy - 0.43
Epoch 10, CIFAR-10 Batch 1:  Batch Loss - 1.4695048332214355; Batch Accuracy - 0.42
Valid Loss - 1.473596453666687; Valid Accuracy - 0.45
Epoch 10, CIFAR-10 Batch 2:  Batch Loss - 1.35617196559906; Batch Accuracy - 0.5
Valid Loss - 1.4507240056991577; Valid Accuracy - 0.47
Epoch 10, CIFAR-10 Batch 3:  Batch Loss - 1.2602899074554443; Batch Accuracy - 0.53
Valid Loss - 1.4879876375198364; Valid Accuracy - 0.44
Epoch 10, CIFAR-10 Batch 4:  Batch Loss - 1.4171357154846191; Batch Accuracy - 0.52
Valid Loss - 1.4682329893112183; Valid Accuracy - 0.45
Epoch 10, CIFAR-10 Batch 5:  Batch Loss - 1.4426767826080322; Batch Accuracy - 0.43
Valid Loss - 1.513766884803772; Valid Accuracy - 0.44
Epoch 11, CIFAR-10 Batch 1:  Batch Loss - 1.4614993333816528; Batch Accuracy - 0.43
Valid Loss - 1.4426636695861816; Valid Accuracy - 0.47
Epoch 11, CIFAR-10 Batch 2:  Batch Loss - 1.3154497146606445; Batch Accuracy - 0.53
Valid Loss - 1.4836833477020264; Valid Accuracy - 0.45
Epoch 11, CIFAR-10 Batch 3:  Batch Loss - 1.3041999340057373; Batch Accuracy - 0.47
Valid Loss - 1.4484295845031738; Valid Accuracy - 0.47
Epoch 11, CIFAR-10 Batch 4:  Batch Loss - 1.356020450592041; Batch Accuracy - 0.55
Valid Loss - 1.4429343938827515; Valid Accuracy - 0.46
Epoch 11, CIFAR-10 Batch 5:  Batch Loss - 1.343109369277954; Batch Accuracy - 0.43
Valid Loss - 1.452834129333496; Valid Accuracy - 0.46
Epoch 12, CIFAR-10 Batch 1:  Batch Loss - 1.3676350116729736; Batch Accuracy - 0.55
Valid Loss - 1.4149537086486816; Valid Accuracy - 0.47
Epoch 12, CIFAR-10 Batch 2:  Batch Loss - 1.255184292793274; Batch Accuracy - 0.55
Valid Loss - 1.4142664670944214; Valid Accuracy - 0.48
Epoch 12, CIFAR-10 Batch 3:  Batch Loss - 1.1818392276763916; Batch Accuracy - 0.57
Valid Loss - 1.404096245765686; Valid Accuracy - 0.48
Epoch 12, CIFAR-10 Batch 4:  Batch Loss - 1.2799949645996094; Batch Accuracy - 0.5
Valid Loss - 1.4192851781845093; Valid Accuracy - 0.47
Epoch 12, CIFAR-10 Batch 5:  Batch Loss - 1.3359324932098389; Batch Accuracy - 0.53
Valid Loss - 1.4352306127548218; Valid Accuracy - 0.47
Epoch 13, CIFAR-10 Batch 1:  Batch Loss - 1.397037148475647; Batch Accuracy - 0.5
Valid Loss - 1.4312901496887207; Valid Accuracy - 0.47
Epoch 13, CIFAR-10 Batch 2:  Batch Loss - 1.2302954196929932; Batch Accuracy - 0.55
Valid Loss - 1.4146502017974854; Valid Accuracy - 0.48
Epoch 13, CIFAR-10 Batch 3:  Batch Loss - 1.1854532957077026; Batch Accuracy - 0.55
Valid Loss - 1.413888692855835; Valid Accuracy - 0.48
Epoch 13, CIFAR-10 Batch 4:  Batch Loss - 1.1485075950622559; Batch Accuracy - 0.6
Valid Loss - 1.3348439931869507; Valid Accuracy - 0.51
Epoch 13, CIFAR-10 Batch 5:  Batch Loss - 1.305050253868103; Batch Accuracy - 0.48
Valid Loss - 1.3983155488967896; Valid Accuracy - 0.49
Epoch 14, CIFAR-10 Batch 1:  Batch Loss - 1.252835750579834; Batch Accuracy - 0.45
Valid Loss - 1.3934342861175537; Valid Accuracy - 0.49
Epoch 14, CIFAR-10 Batch 2:  Batch Loss - 1.3436651229858398; Batch Accuracy - 0.57
Valid Loss - 1.5238326787948608; Valid Accuracy - 0.45
Epoch 14, CIFAR-10 Batch 3:  Batch Loss - 1.120964527130127; Batch Accuracy - 0.6
Valid Loss - 1.3655167818069458; Valid Accuracy - 0.51
Epoch 14, CIFAR-10 Batch 4:  Batch Loss - 1.1675137281417847; Batch Accuracy - 0.58
Valid Loss - 1.3780622482299805; Valid Accuracy - 0.5
Epoch 14, CIFAR-10 Batch 5:  Batch Loss - 1.230318307876587; Batch Accuracy - 0.58
Valid Loss - 1.3574937582015991; Valid Accuracy - 0.5
Epoch 15, CIFAR-10 Batch 1:  Batch Loss - 1.1806082725524902; Batch Accuracy - 0.55
Valid Loss - 1.343673825263977; Valid Accuracy - 0.51
Epoch 15, CIFAR-10 Batch 2:  Batch Loss - 1.1960275173187256; Batch Accuracy - 0.58
Valid Loss - 1.3668673038482666; Valid Accuracy - 0.5
Epoch 15, CIFAR-10 Batch 3:  Batch Loss - 1.1258208751678467; Batch Accuracy - 0.58
Valid Loss - 1.3886427879333496; Valid Accuracy - 0.49
Epoch 15, CIFAR-10 Batch 4:  Batch Loss - 1.025428056716919; Batch Accuracy - 0.62
Valid Loss - 1.3445574045181274; Valid Accuracy - 0.52
Epoch 15, CIFAR-10 Batch 5:  Batch Loss - 1.1319737434387207; Batch Accuracy - 0.58
Valid Loss - 1.3401596546173096; Valid Accuracy - 0.52
Epoch 16, CIFAR-10 Batch 1:  Batch Loss - 1.2090147733688354; Batch Accuracy - 0.6
Valid Loss - 1.4048854112625122; Valid Accuracy - 0.5
Epoch 16, CIFAR-10 Batch 2:  Batch Loss - 1.150794506072998; Batch Accuracy - 0.6
Valid Loss - 1.299938678741455; Valid Accuracy - 0.53
Epoch 16, CIFAR-10 Batch 3:  Batch Loss - 1.0039702653884888; Batch Accuracy - 0.68
Valid Loss - 1.3062870502471924; Valid Accuracy - 0.53
Epoch 16, CIFAR-10 Batch 4:  Batch Loss - 1.053022861480713; Batch Accuracy - 0.67
Valid Loss - 1.3555585145950317; Valid Accuracy - 0.51
Epoch 16, CIFAR-10 Batch 5:  Batch Loss - 1.1064540147781372; Batch Accuracy - 0.63
Valid Loss - 1.3117761611938477; Valid Accuracy - 0.52
Epoch 17, CIFAR-10 Batch 1:  Batch Loss - 1.2117559909820557; Batch Accuracy - 0.6
Valid Loss - 1.3447325229644775; Valid Accuracy - 0.52
Epoch 17, CIFAR-10 Batch 2:  Batch Loss - 1.1230595111846924; Batch Accuracy - 0.57
Valid Loss - 1.2896031141281128; Valid Accuracy - 0.53
Epoch 17, CIFAR-10 Batch 3:  Batch Loss - 0.9428025484085083; Batch Accuracy - 0.75
Valid Loss - 1.316176414489746; Valid Accuracy - 0.52
Epoch 17, CIFAR-10 Batch 4:  Batch Loss - 1.001985788345337; Batch Accuracy - 0.68
Valid Loss - 1.2775061130523682; Valid Accuracy - 0.54
Epoch 17, CIFAR-10 Batch 5:  Batch Loss - 1.1249772310256958; Batch Accuracy - 0.6
Valid Loss - 1.3041818141937256; Valid Accuracy - 0.53
Epoch 18, CIFAR-10 Batch 1:  Batch Loss - 1.1053974628448486; Batch Accuracy - 0.65
Valid Loss - 1.2778403759002686; Valid Accuracy - 0.53
Epoch 18, CIFAR-10 Batch 2:  Batch Loss - 1.1392759084701538; Batch Accuracy - 0.62
Valid Loss - 1.2973662614822388; Valid Accuracy - 0.53
Epoch 18, CIFAR-10 Batch 3:  Batch Loss - 0.9281553626060486; Batch Accuracy - 0.75
Valid Loss - 1.3020318746566772; Valid Accuracy - 0.53
Epoch 18, CIFAR-10 Batch 4:  Batch Loss - 0.999509871006012; Batch Accuracy - 0.6
Valid Loss - 1.3414195775985718; Valid Accuracy - 0.52
Epoch 18, CIFAR-10 Batch 5:  Batch Loss - 1.0560410022735596; Batch Accuracy - 0.63
Valid Loss - 1.2945457696914673; Valid Accuracy - 0.53
Epoch 19, CIFAR-10 Batch 1:  Batch Loss - 1.133270502090454; Batch Accuracy - 0.6
Valid Loss - 1.3324720859527588; Valid Accuracy - 0.51
Epoch 19, CIFAR-10 Batch 2:  Batch Loss - 1.1102385520935059; Batch Accuracy - 0.65
Valid Loss - 1.3055847883224487; Valid Accuracy - 0.53
Epoch 19, CIFAR-10 Batch 3:  Batch Loss - 0.8556857109069824; Batch Accuracy - 0.73
Valid Loss - 1.277645230293274; Valid Accuracy - 0.54
Epoch 19, CIFAR-10 Batch 4:  Batch Loss - 0.91932213306427; Batch Accuracy - 0.7
Valid Loss - 1.2588142156600952; Valid Accuracy - 0.55
Epoch 19, CIFAR-10 Batch 5:  Batch Loss - 1.0305390357971191; Batch Accuracy - 0.65
Valid Loss - 1.2821052074432373; Valid Accuracy - 0.54
Epoch 20, CIFAR-10 Batch 1:  Batch Loss - 1.0042299032211304; Batch Accuracy - 0.65
Valid Loss - 1.2700384855270386; Valid Accuracy - 0.55
Epoch 20, CIFAR-10 Batch 2:  Batch Loss - 1.0957536697387695; Batch Accuracy - 0.62
Valid Loss - 1.2299625873565674; Valid Accuracy - 0.56
Epoch 20, CIFAR-10 Batch 3:  Batch Loss - 0.784577488899231; Batch Accuracy - 0.78
Valid Loss - 1.229161262512207; Valid Accuracy - 0.56
Epoch 20, CIFAR-10 Batch 4:  Batch Loss - 0.9353729486465454; Batch Accuracy - 0.62
Valid Loss - 1.2753872871398926; Valid Accuracy - 0.54
Epoch 20, CIFAR-10 Batch 5:  Batch Loss - 0.9521349668502808; Batch Accuracy - 0.65
Valid Loss - 1.2415437698364258; Valid Accuracy - 0.55
Epoch 21, CIFAR-10 Batch 1:  Batch Loss - 1.0030525922775269; Batch Accuracy - 0.65
Valid Loss - 1.2523778676986694; Valid Accuracy - 0.55
Epoch 21, CIFAR-10 Batch 2:  Batch Loss - 0.9992501139640808; Batch Accuracy - 0.62
Valid Loss - 1.257611632347107; Valid Accuracy - 0.55
Epoch 21, CIFAR-10 Batch 3:  Batch Loss - 0.7602688670158386; Batch Accuracy - 0.75
Valid Loss - 1.233368158340454; Valid Accuracy - 0.56
Epoch 21, CIFAR-10 Batch 4:  Batch Loss - 0.8365222811698914; Batch Accuracy - 0.72
Valid Loss - 1.2373878955841064; Valid Accuracy - 0.55
Epoch 21, CIFAR-10 Batch 5:  Batch Loss - 0.9829421043395996; Batch Accuracy - 0.65
Valid Loss - 1.2873084545135498; Valid Accuracy - 0.54
Epoch 22, CIFAR-10 Batch 1:  Batch Loss - 0.9653307795524597; Batch Accuracy - 0.68
Valid Loss - 1.2189964056015015; Valid Accuracy - 0.57
Epoch 22, CIFAR-10 Batch 2:  Batch Loss - 1.0229771137237549; Batch Accuracy - 0.6
Valid Loss - 1.2382581233978271; Valid Accuracy - 0.55
Epoch 22, CIFAR-10 Batch 3:  Batch Loss - 0.7223606705665588; Batch Accuracy - 0.75
Valid Loss - 1.230700969696045; Valid Accuracy - 0.56
Epoch 22, CIFAR-10 Batch 4:  Batch Loss - 0.8303850889205933; Batch Accuracy - 0.73
Valid Loss - 1.2552592754364014; Valid Accuracy - 0.56
Epoch 22, CIFAR-10 Batch 5:  Batch Loss - 0.9588004350662231; Batch Accuracy - 0.65
Valid Loss - 1.2523235082626343; Valid Accuracy - 0.55
Epoch 23, CIFAR-10 Batch 1:  Batch Loss - 0.9317131042480469; Batch Accuracy - 0.73
Valid Loss - 1.2187937498092651; Valid Accuracy - 0.57
Epoch 23, CIFAR-10 Batch 2:  Batch Loss - 0.9586479067802429; Batch Accuracy - 0.62
Valid Loss - 1.1816105842590332; Valid Accuracy - 0.58
Epoch 23, CIFAR-10 Batch 3:  Batch Loss - 0.7194514870643616; Batch Accuracy - 0.8
Valid Loss - 1.2090020179748535; Valid Accuracy - 0.57
Epoch 23, CIFAR-10 Batch 4:  Batch Loss - 0.7458418607711792; Batch Accuracy - 0.73
Valid Loss - 1.1795239448547363; Valid Accuracy - 0.58
Epoch 23, CIFAR-10 Batch 5:  Batch Loss - 0.8644723296165466; Batch Accuracy - 0.73
Valid Loss - 1.1976737976074219; Valid Accuracy - 0.57
Epoch 24, CIFAR-10 Batch 1:  Batch Loss - 0.9445664286613464; Batch Accuracy - 0.65
Valid Loss - 1.208282470703125; Valid Accuracy - 0.58
Epoch 24, CIFAR-10 Batch 2:  Batch Loss - 1.0142842531204224; Batch Accuracy - 0.67
Valid Loss - 1.1853433847427368; Valid Accuracy - 0.57
Epoch 24, CIFAR-10 Batch 3:  Batch Loss - 0.6222772002220154; Batch Accuracy - 0.83
Valid Loss - 1.1963471174240112; Valid Accuracy - 0.57
Epoch 24, CIFAR-10 Batch 4:  Batch Loss - 0.8091155886650085; Batch Accuracy - 0.6
Valid Loss - 1.28365159034729; Valid Accuracy - 0.54
Epoch 24, CIFAR-10 Batch 5:  Batch Loss - 0.830058217048645; Batch Accuracy - 0.7
Valid Loss - 1.1794761419296265; Valid Accuracy - 0.57
Epoch 25, CIFAR-10 Batch 1:  Batch Loss - 0.923500657081604; Batch Accuracy - 0.65
Valid Loss - 1.2143726348876953; Valid Accuracy - 0.57
Epoch 25, CIFAR-10 Batch 2:  Batch Loss - 0.904486894607544; Batch Accuracy - 0.68
Valid Loss - 1.1398221254348755; Valid Accuracy - 0.59
Epoch 25, CIFAR-10 Batch 3:  Batch Loss - 0.6177511811256409; Batch Accuracy - 0.83
Valid Loss - 1.1983253955841064; Valid Accuracy - 0.57
Epoch 25, CIFAR-10 Batch 4:  Batch Loss - 0.7477977275848389; Batch Accuracy - 0.7
Valid Loss - 1.2140823602676392; Valid Accuracy - 0.56
Epoch 25, CIFAR-10 Batch 5:  Batch Loss - 0.8390359282493591; Batch Accuracy - 0.73
Valid Loss - 1.2007488012313843; Valid Accuracy - 0.57
Epoch 26, CIFAR-10 Batch 1:  Batch Loss - 0.8704408407211304; Batch Accuracy - 0.73
Valid Loss - 1.1726956367492676; Valid Accuracy - 0.59
Epoch 26, CIFAR-10 Batch 2:  Batch Loss - 0.8792539834976196; Batch Accuracy - 0.68
Valid Loss - 1.1448030471801758; Valid Accuracy - 0.6
Epoch 26, CIFAR-10 Batch 3:  Batch Loss - 0.6066028475761414; Batch Accuracy - 0.8
Valid Loss - 1.1671875715255737; Valid Accuracy - 0.59
Epoch 26, CIFAR-10 Batch 4:  Batch Loss - 0.6701741218566895; Batch Accuracy - 0.77
Valid Loss - 1.18375825881958; Valid Accuracy - 0.58
Epoch 26, CIFAR-10 Batch 5:  Batch Loss - 0.795254111289978; Batch Accuracy - 0.73
Valid Loss - 1.14915132522583; Valid Accuracy - 0.59
Epoch 27, CIFAR-10 Batch 1:  Batch Loss - 0.8499232530593872; Batch Accuracy - 0.7
Valid Loss - 1.1580514907836914; Valid Accuracy - 0.59
Epoch 27, CIFAR-10 Batch 2:  Batch Loss - 0.7910614013671875; Batch Accuracy - 0.65
Valid Loss - 1.1433898210525513; Valid Accuracy - 0.59
Epoch 27, CIFAR-10 Batch 3:  Batch Loss - 0.6013469696044922; Batch Accuracy - 0.85
Valid Loss - 1.1308660507202148; Valid Accuracy - 0.6
Epoch 27, CIFAR-10 Batch 4:  Batch Loss - 0.6563165187835693; Batch Accuracy - 0.78
Valid Loss - 1.1343731880187988; Valid Accuracy - 0.6
Epoch 27, CIFAR-10 Batch 5:  Batch Loss - 0.7723098397254944; Batch Accuracy - 0.7
Valid Loss - 1.1549073457717896; Valid Accuracy - 0.59
Epoch 28, CIFAR-10 Batch 1:  Batch Loss - 0.7739144563674927; Batch Accuracy - 0.75
Valid Loss - 1.148833990097046; Valid Accuracy - 0.59
Epoch 28, CIFAR-10 Batch 2:  Batch Loss - 0.8288774490356445; Batch Accuracy - 0.7
Valid Loss - 1.1126905679702759; Valid Accuracy - 0.6
Epoch 28, CIFAR-10 Batch 3:  Batch Loss - 0.5408920645713806; Batch Accuracy - 0.85
Valid Loss - 1.137253999710083; Valid Accuracy - 0.6
Epoch 28, CIFAR-10 Batch 4:  Batch Loss - 0.6417310833930969; Batch Accuracy - 0.8
Valid Loss - 1.2032891511917114; Valid Accuracy - 0.58
Epoch 28, CIFAR-10 Batch 5:  Batch Loss - 0.7802789807319641; Batch Accuracy - 0.78
Valid Loss - 1.1835834980010986; Valid Accuracy - 0.59
Epoch 29, CIFAR-10 Batch 1:  Batch Loss - 0.8309884071350098; Batch Accuracy - 0.73
Valid Loss - 1.190617322921753; Valid Accuracy - 0.59
Epoch 29, CIFAR-10 Batch 2:  Batch Loss - 0.813457727432251; Batch Accuracy - 0.7
Valid Loss - 1.1648753881454468; Valid Accuracy - 0.59
Epoch 29, CIFAR-10 Batch 3:  Batch Loss - 0.5133509635925293; Batch Accuracy - 0.83
Valid Loss - 1.1144871711730957; Valid Accuracy - 0.6
Epoch 29, CIFAR-10 Batch 4:  Batch Loss - 0.6494659185409546; Batch Accuracy - 0.75
Valid Loss - 1.1159510612487793; Valid Accuracy - 0.61
Epoch 29, CIFAR-10 Batch 5:  Batch Loss - 0.6990681886672974; Batch Accuracy - 0.83
Valid Loss - 1.1525250673294067; Valid Accuracy - 0.6
Epoch 30, CIFAR-10 Batch 1:  Batch Loss - 0.8280684351921082; Batch Accuracy - 0.73
Valid Loss - 1.1975926160812378; Valid Accuracy - 0.58
Epoch 30, CIFAR-10 Batch 2:  Batch Loss - 0.8274865746498108; Batch Accuracy - 0.73
Valid Loss - 1.1082189083099365; Valid Accuracy - 0.61
Epoch 30, CIFAR-10 Batch 3:  Batch Loss - 0.5206993818283081; Batch Accuracy - 0.88
Valid Loss - 1.1445999145507812; Valid Accuracy - 0.6
Epoch 30, CIFAR-10 Batch 4:  Batch Loss - 0.6201926469802856; Batch Accuracy - 0.88
Valid Loss - 1.1445637941360474; Valid Accuracy - 0.6
Epoch 30, CIFAR-10 Batch 5:  Batch Loss - 0.7309761047363281; Batch Accuracy - 0.75
Valid Loss - 1.1114994287490845; Valid Accuracy - 0.61
Epoch 31, CIFAR-10 Batch 1:  Batch Loss - 0.6964867115020752; Batch Accuracy - 0.8
Valid Loss - 1.1129405498504639; Valid Accuracy - 0.61
Epoch 31, CIFAR-10 Batch 2:  Batch Loss - 0.7493797540664673; Batch Accuracy - 0.75
Valid Loss - 1.1069116592407227; Valid Accuracy - 0.61
Epoch 31, CIFAR-10 Batch 3:  Batch Loss - 0.507482647895813; Batch Accuracy - 0.83
Valid Loss - 1.112038254737854; Valid Accuracy - 0.61
Epoch 31, CIFAR-10 Batch 4:  Batch Loss - 0.5951825976371765; Batch Accuracy - 0.78
Valid Loss - 1.1107457876205444; Valid Accuracy - 0.61
Epoch 31, CIFAR-10 Batch 5:  Batch Loss - 0.7297852039337158; Batch Accuracy - 0.75
Valid Loss - 1.130484700202942; Valid Accuracy - 0.6
Epoch 32, CIFAR-10 Batch 1:  Batch Loss - 0.7786177396774292; Batch Accuracy - 0.78
Valid Loss - 1.157470464706421; Valid Accuracy - 0.6
Epoch 32, CIFAR-10 Batch 2:  Batch Loss - 0.6146859526634216; Batch Accuracy - 0.78
Valid Loss - 1.0843979120254517; Valid Accuracy - 0.62
Epoch 32, CIFAR-10 Batch 3:  Batch Loss - 0.44445836544036865; Batch Accuracy - 0.88
Valid Loss - 1.090037226676941; Valid Accuracy - 0.62
Epoch 32, CIFAR-10 Batch 4:  Batch Loss - 0.5144125819206238; Batch Accuracy - 0.85
Valid Loss - 1.0932626724243164; Valid Accuracy - 0.61
Epoch 32, CIFAR-10 Batch 5:  Batch Loss - 0.705990195274353; Batch Accuracy - 0.77
Valid Loss - 1.0886058807373047; Valid Accuracy - 0.61
Epoch 33, CIFAR-10 Batch 1:  Batch Loss - 0.7086079120635986; Batch Accuracy - 0.75
Valid Loss - 1.1085760593414307; Valid Accuracy - 0.61
Epoch 33, CIFAR-10 Batch 2:  Batch Loss - 0.7216464281082153; Batch Accuracy - 0.8
Valid Loss - 1.1112589836120605; Valid Accuracy - 0.61
Epoch 33, CIFAR-10 Batch 3:  Batch Loss - 0.45635396242141724; Batch Accuracy - 0.8
Valid Loss - 1.11073637008667; Valid Accuracy - 0.61
Epoch 33, CIFAR-10 Batch 4:  Batch Loss - 0.506262481212616; Batch Accuracy - 0.88
Valid Loss - 1.0969607830047607; Valid Accuracy - 0.61
Epoch 33, CIFAR-10 Batch 5:  Batch Loss - 0.677598237991333; Batch Accuracy - 0.77
Valid Loss - 1.1038708686828613; Valid Accuracy - 0.61
Epoch 34, CIFAR-10 Batch 1:  Batch Loss - 0.7228043079376221; Batch Accuracy - 0.75
Valid Loss - 1.062051773071289; Valid Accuracy - 0.63
Epoch 34, CIFAR-10 Batch 2:  Batch Loss - 0.6608461141586304; Batch Accuracy - 0.8
Valid Loss - 1.0674643516540527; Valid Accuracy - 0.62
Epoch 34, CIFAR-10 Batch 3:  Batch Loss - 0.3892723023891449; Batch Accuracy - 0.85
Valid Loss - 1.0976563692092896; Valid Accuracy - 0.62
Epoch 34, CIFAR-10 Batch 4:  Batch Loss - 0.4647645652294159; Batch Accuracy - 0.93
Valid Loss - 1.0547146797180176; Valid Accuracy - 0.62
Epoch 34, CIFAR-10 Batch 5:  Batch Loss - 0.7167834043502808; Batch Accuracy - 0.75
Valid Loss - 1.1323381662368774; Valid Accuracy - 0.61
Epoch 35, CIFAR-10 Batch 1:  Batch Loss - 0.6275366544723511; Batch Accuracy - 0.77
Valid Loss - 1.094254493713379; Valid Accuracy - 0.62
Epoch 35, CIFAR-10 Batch 2:  Batch Loss - 0.5842564105987549; Batch Accuracy - 0.82
Valid Loss - 1.0801637172698975; Valid Accuracy - 0.62
Epoch 35, CIFAR-10 Batch 3:  Batch Loss - 0.3872767388820648; Batch Accuracy - 0.93
Valid Loss - 1.0898505449295044; Valid Accuracy - 0.62
Epoch 35, CIFAR-10 Batch 4:  Batch Loss - 0.4949887692928314; Batch Accuracy - 0.85
Valid Loss - 1.0976035594940186; Valid Accuracy - 0.62
Epoch 35, CIFAR-10 Batch 5:  Batch Loss - 0.6283483505249023; Batch Accuracy - 0.75
Valid Loss - 1.0723627805709839; Valid Accuracy - 0.62
Epoch 36, CIFAR-10 Batch 1:  Batch Loss - 0.6346721053123474; Batch Accuracy - 0.8
Valid Loss - 1.0879242420196533; Valid Accuracy - 0.62
Epoch 36, CIFAR-10 Batch 2:  Batch Loss - 0.629967987537384; Batch Accuracy - 0.78
Valid Loss - 1.044630765914917; Valid Accuracy - 0.63
Epoch 36, CIFAR-10 Batch 3:  Batch Loss - 0.352531373500824; Batch Accuracy - 0.93
Valid Loss - 1.093003511428833; Valid Accuracy - 0.63
Epoch 36, CIFAR-10 Batch 4:  Batch Loss - 0.4413672089576721; Batch Accuracy - 0.88
Valid Loss - 1.0934712886810303; Valid Accuracy - 0.62
Epoch 36, CIFAR-10 Batch 5:  Batch Loss - 0.6145602464675903; Batch Accuracy - 0.73
Valid Loss - 1.062735915184021; Valid Accuracy - 0.63
Epoch 37, CIFAR-10 Batch 1:  Batch Loss - 0.6181623935699463; Batch Accuracy - 0.8
Valid Loss - 1.0845427513122559; Valid Accuracy - 0.62
Epoch 37, CIFAR-10 Batch 2:  Batch Loss - 0.49551713466644287; Batch Accuracy - 0.9
Valid Loss - 1.0415164232254028; Valid Accuracy - 0.63
Epoch 37, CIFAR-10 Batch 3:  Batch Loss - 0.36060965061187744; Batch Accuracy - 0.9
Valid Loss - 1.0553255081176758; Valid Accuracy - 0.63
Epoch 37, CIFAR-10 Batch 4:  Batch Loss - 0.4193963408470154; Batch Accuracy - 0.88
Valid Loss - 1.0837281942367554; Valid Accuracy - 0.62
Epoch 37, CIFAR-10 Batch 5:  Batch Loss - 0.591499924659729; Batch Accuracy - 0.77
Valid Loss - 1.122653841972351; Valid Accuracy - 0.62
Epoch 38, CIFAR-10 Batch 1:  Batch Loss - 0.5595614314079285; Batch Accuracy - 0.8
Valid Loss - 1.07464599609375; Valid Accuracy - 0.63
Epoch 38, CIFAR-10 Batch 2:  Batch Loss - 0.5279249548912048; Batch Accuracy - 0.88
Valid Loss - 1.0376224517822266; Valid Accuracy - 0.63
Epoch 38, CIFAR-10 Batch 3:  Batch Loss - 0.3375243544578552; Batch Accuracy - 0.9
Valid Loss - 1.0794329643249512; Valid Accuracy - 0.63
Epoch 38, CIFAR-10 Batch 4:  Batch Loss - 0.4584786891937256; Batch Accuracy - 0.9
Valid Loss - 1.0798588991165161; Valid Accuracy - 0.63
Epoch 38, CIFAR-10 Batch 5:  Batch Loss - 0.5544862747192383; Batch Accuracy - 0.77
Valid Loss - 1.061307430267334; Valid Accuracy - 0.63
Epoch 39, CIFAR-10 Batch 1:  Batch Loss - 0.5874209403991699; Batch Accuracy - 0.77
Valid Loss - 1.0582189559936523; Valid Accuracy - 0.64
Epoch 39, CIFAR-10 Batch 2:  Batch Loss - 0.5056926608085632; Batch Accuracy - 0.82
Valid Loss - 1.031632900238037; Valid Accuracy - 0.63
Epoch 39, CIFAR-10 Batch 3:  Batch Loss - 0.3164880871772766; Batch Accuracy - 0.88
Valid Loss - 1.0729782581329346; Valid Accuracy - 0.63
Epoch 39, CIFAR-10 Batch 4:  Batch Loss - 0.3574135899543762; Batch Accuracy - 0.95
Valid Loss - 1.0335458517074585; Valid Accuracy - 0.64
Epoch 39, CIFAR-10 Batch 5:  Batch Loss - 0.5499814748764038; Batch Accuracy - 0.85
Valid Loss - 1.0464732646942139; Valid Accuracy - 0.63
Epoch 40, CIFAR-10 Batch 1:  Batch Loss - 0.47838908433914185; Batch Accuracy - 0.85
Valid Loss - 1.053324580192566; Valid Accuracy - 0.63
Epoch 40, CIFAR-10 Batch 2:  Batch Loss - 0.5079825520515442; Batch Accuracy - 0.82
Valid Loss - 1.030678153038025; Valid Accuracy - 0.64
Epoch 40, CIFAR-10 Batch 3:  Batch Loss - 0.3241026997566223; Batch Accuracy - 0.95
Valid Loss - 1.0609537363052368; Valid Accuracy - 0.64
Epoch 40, CIFAR-10 Batch 4:  Batch Loss - 0.3762497007846832; Batch Accuracy - 0.93
Valid Loss - 1.0479092597961426; Valid Accuracy - 0.64
Epoch 40, CIFAR-10 Batch 5:  Batch Loss - 0.5538079142570496; Batch Accuracy - 0.83
Valid Loss - 1.031711459159851; Valid Accuracy - 0.64
Epoch 41, CIFAR-10 Batch 1:  Batch Loss - 0.49245527386665344; Batch Accuracy - 0.8
Valid Loss - 1.0304518938064575; Valid Accuracy - 0.64
Epoch 41, CIFAR-10 Batch 2:  Batch Loss - 0.5015208721160889; Batch Accuracy - 0.85
Valid Loss - 1.0307633876800537; Valid Accuracy - 0.64
Epoch 41, CIFAR-10 Batch 3:  Batch Loss - 0.2846636474132538; Batch Accuracy - 0.95
Valid Loss - 1.0685983896255493; Valid Accuracy - 0.63
Epoch 41, CIFAR-10 Batch 4:  Batch Loss - 0.35774853825569153; Batch Accuracy - 0.9
Valid Loss - 1.0279494524002075; Valid Accuracy - 0.64
Epoch 41, CIFAR-10 Batch 5:  Batch Loss - 0.5617642998695374; Batch Accuracy - 0.8
Valid Loss - 1.0312532186508179; Valid Accuracy - 0.65
Epoch 42, CIFAR-10 Batch 1:  Batch Loss - 0.46775540709495544; Batch Accuracy - 0.83
Valid Loss - 1.0570776462554932; Valid Accuracy - 0.64
Epoch 42, CIFAR-10 Batch 2:  Batch Loss - 0.46834877133369446; Batch Accuracy - 0.82
Valid Loss - 1.0170146226882935; Valid Accuracy - 0.64
Epoch 42, CIFAR-10 Batch 3:  Batch Loss - 0.3223775029182434; Batch Accuracy - 0.93
Valid Loss - 1.0746489763259888; Valid Accuracy - 0.63
Epoch 42, CIFAR-10 Batch 4:  Batch Loss - 0.3265911936759949; Batch Accuracy - 0.93
Valid Loss - 1.0238040685653687; Valid Accuracy - 0.64
Epoch 42, CIFAR-10 Batch 5:  Batch Loss - 0.5027878284454346; Batch Accuracy - 0.83
Valid Loss - 1.0441325902938843; Valid Accuracy - 0.64
Epoch 43, CIFAR-10 Batch 1:  Batch Loss - 0.47397202253341675; Batch Accuracy - 0.82
Valid Loss - 1.0344228744506836; Valid Accuracy - 0.65
Epoch 43, CIFAR-10 Batch 2:  Batch Loss - 0.4680566191673279; Batch Accuracy - 0.85
Valid Loss - 1.0427440404891968; Valid Accuracy - 0.65
Epoch 43, CIFAR-10 Batch 3:  Batch Loss - 0.29360461235046387; Batch Accuracy - 0.93
Valid Loss - 1.0470881462097168; Valid Accuracy - 0.64
Epoch 43, CIFAR-10 Batch 4:  Batch Loss - 0.3384011685848236; Batch Accuracy - 0.93
Valid Loss - 1.0772345066070557; Valid Accuracy - 0.63
Epoch 43, CIFAR-10 Batch 5:  Batch Loss - 0.5348929166793823; Batch Accuracy - 0.8
Valid Loss - 1.0402858257293701; Valid Accuracy - 0.63
Epoch 44, CIFAR-10 Batch 1:  Batch Loss - 0.45605412125587463; Batch Accuracy - 0.82
Valid Loss - 1.0483981370925903; Valid Accuracy - 0.64
Epoch 44, CIFAR-10 Batch 2:  Batch Loss - 0.41100239753723145; Batch Accuracy - 0.9
Valid Loss - 0.9981440305709839; Valid Accuracy - 0.65
Epoch 44, CIFAR-10 Batch 3:  Batch Loss - 0.2771855294704437; Batch Accuracy - 0.95
Valid Loss - 1.071661353111267; Valid Accuracy - 0.63
Epoch 44, CIFAR-10 Batch 4:  Batch Loss - 0.3063732087612152; Batch Accuracy - 0.93
Valid Loss - 1.0182877779006958; Valid Accuracy - 0.65
Epoch 44, CIFAR-10 Batch 5:  Batch Loss - 0.5000120997428894; Batch Accuracy - 0.77
Valid Loss - 1.0642424821853638; Valid Accuracy - 0.64
Epoch 45, CIFAR-10 Batch 1:  Batch Loss - 0.4015866816043854; Batch Accuracy - 0.88
Valid Loss - 1.0261183977127075; Valid Accuracy - 0.65
Epoch 45, CIFAR-10 Batch 2:  Batch Loss - 0.41674673557281494; Batch Accuracy - 0.9
Valid Loss - 1.0064327716827393; Valid Accuracy - 0.65
Epoch 45, CIFAR-10 Batch 3:  Batch Loss - 0.2171948105096817; Batch Accuracy - 0.93
Valid Loss - 1.057092547416687; Valid Accuracy - 0.65
Epoch 45, CIFAR-10 Batch 4:  Batch Loss - 0.32607561349868774; Batch Accuracy - 0.93
Valid Loss - 1.0213791131973267; Valid Accuracy - 0.64
Epoch 45, CIFAR-10 Batch 5:  Batch Loss - 0.4635092616081238; Batch Accuracy - 0.9
Valid Loss - 1.068498134613037; Valid Accuracy - 0.63
Epoch 46, CIFAR-10 Batch 1:  Batch Loss - 0.44478052854537964; Batch Accuracy - 0.85
Valid Loss - 1.0548535585403442; Valid Accuracy - 0.65
Epoch 46, CIFAR-10 Batch 2:  Batch Loss - 0.41330504417419434; Batch Accuracy - 0.85
Valid Loss - 1.0218168497085571; Valid Accuracy - 0.65
Epoch 46, CIFAR-10 Batch 3:  Batch Loss - 0.2784571349620819; Batch Accuracy - 0.93
Valid Loss - 1.051741600036621; Valid Accuracy - 0.64
Epoch 46, CIFAR-10 Batch 4:  Batch Loss - 0.2823028564453125; Batch Accuracy - 0.95
Valid Loss - 1.0128897428512573; Valid Accuracy - 0.65
Epoch 46, CIFAR-10 Batch 5:  Batch Loss - 0.4520094096660614; Batch Accuracy - 0.88
Valid Loss - 0.9822708964347839; Valid Accuracy - 0.66
Epoch 47, CIFAR-10 Batch 1:  Batch Loss - 0.4130711555480957; Batch Accuracy - 0.85
Valid Loss - 1.0692511796951294; Valid Accuracy - 0.65
Epoch 47, CIFAR-10 Batch 2:  Batch Loss - 0.4045213460922241; Batch Accuracy - 0.95
Valid Loss - 1.0139358043670654; Valid Accuracy - 0.65
Epoch 47, CIFAR-10 Batch 3:  Batch Loss - 0.2752794027328491; Batch Accuracy - 0.93
Valid Loss - 1.0448968410491943; Valid Accuracy - 0.64
Epoch 47, CIFAR-10 Batch 4:  Batch Loss - 0.24867787957191467; Batch Accuracy - 0.97
Valid Loss - 0.9815210700035095; Valid Accuracy - 0.66
Epoch 47, CIFAR-10 Batch 5:  Batch Loss - 0.46584904193878174; Batch Accuracy - 0.9
Valid Loss - 1.0177175998687744; Valid Accuracy - 0.65
Epoch 48, CIFAR-10 Batch 1:  Batch Loss - 0.38236644864082336; Batch Accuracy - 0.9
Valid Loss - 1.0154893398284912; Valid Accuracy - 0.66
Epoch 48, CIFAR-10 Batch 2:  Batch Loss - 0.29813092947006226; Batch Accuracy - 0.97
Valid Loss - 0.9984560608863831; Valid Accuracy - 0.66
Epoch 48, CIFAR-10 Batch 3:  Batch Loss - 0.20674031972885132; Batch Accuracy - 0.97
Valid Loss - 1.0230956077575684; Valid Accuracy - 0.65
Epoch 48, CIFAR-10 Batch 4:  Batch Loss - 0.2801567614078522; Batch Accuracy - 0.92
Valid Loss - 1.0146949291229248; Valid Accuracy - 0.65
Epoch 48, CIFAR-10 Batch 5:  Batch Loss - 0.4108029901981354; Batch Accuracy - 0.9
Valid Loss - 0.9868462681770325; Valid Accuracy - 0.66
Epoch 49, CIFAR-10 Batch 1:  Batch Loss - 0.40979713201522827; Batch Accuracy - 0.88
Valid Loss - 1.0505448579788208; Valid Accuracy - 0.65
Epoch 49, CIFAR-10 Batch 2:  Batch Loss - 0.3155510425567627; Batch Accuracy - 0.97
Valid Loss - 0.9719576239585876; Valid Accuracy - 0.66
Epoch 49, CIFAR-10 Batch 3:  Batch Loss - 0.29223793745040894; Batch Accuracy - 0.95
Valid Loss - 1.0552887916564941; Valid Accuracy - 0.64
Epoch 49, CIFAR-10 Batch 4:  Batch Loss - 0.2292112112045288; Batch Accuracy - 0.97
Valid Loss - 0.995171844959259; Valid Accuracy - 0.66
Epoch 49, CIFAR-10 Batch 5:  Batch Loss - 0.3821052014827728; Batch Accuracy - 0.85
Valid Loss - 1.0398344993591309; Valid Accuracy - 0.64
Epoch 50, CIFAR-10 Batch 1:  Batch Loss - 0.38924291729927063; Batch Accuracy - 0.85
Valid Loss - 0.9853225946426392; Valid Accuracy - 0.66
Epoch 50, CIFAR-10 Batch 2:  Batch Loss - 0.3070986866950989; Batch Accuracy - 0.97
Valid Loss - 0.9814861416816711; Valid Accuracy - 0.66
Epoch 50, CIFAR-10 Batch 3:  Batch Loss - 0.25553613901138306; Batch Accuracy - 0.95
Valid Loss - 1.03226900100708; Valid Accuracy - 0.65
Epoch 50, CIFAR-10 Batch 4:  Batch Loss - 0.23998232185840607; Batch Accuracy - 1.0
Valid Loss - 1.0175819396972656; Valid Accuracy - 0.65
Epoch 50, CIFAR-10 Batch 5:  Batch Loss - 0.4108496308326721; Batch Accuracy - 0.85
Valid Loss - 1.0297255516052246; Valid Accuracy - 0.65
Epoch 51, CIFAR-10 Batch 1:  Batch Loss - 0.3740553855895996; Batch Accuracy - 0.88
Valid Loss - 1.0070693492889404; Valid Accuracy - 0.66
Epoch 51, CIFAR-10 Batch 2:  Batch Loss - 0.27427035570144653; Batch Accuracy - 0.95
Valid Loss - 0.965173602104187; Valid Accuracy - 0.67
Epoch 51, CIFAR-10 Batch 3:  Batch Loss - 0.2400347739458084; Batch Accuracy - 0.93
Valid Loss - 1.008657455444336; Valid Accuracy - 0.65
Epoch 51, CIFAR-10 Batch 4:  Batch Loss - 0.21677523851394653; Batch Accuracy - 0.97
Valid Loss - 1.0139151811599731; Valid Accuracy - 0.66
Epoch 51, CIFAR-10 Batch 5:  Batch Loss - 0.3409087061882019; Batch Accuracy - 0.93
Valid Loss - 1.0188965797424316; Valid Accuracy - 0.66
Epoch 52, CIFAR-10 Batch 1:  Batch Loss - 0.40669187903404236; Batch Accuracy - 0.9
Valid Loss - 1.0184565782546997; Valid Accuracy - 0.66
Epoch 52, CIFAR-10 Batch 2:  Batch Loss - 0.3307846188545227; Batch Accuracy - 0.93
Valid Loss - 0.9791102409362793; Valid Accuracy - 0.66
Epoch 52, CIFAR-10 Batch 3:  Batch Loss - 0.2180948555469513; Batch Accuracy - 0.97
Valid Loss - 1.0058752298355103; Valid Accuracy - 0.66
Epoch 52, CIFAR-10 Batch 4:  Batch Loss - 0.20768341422080994; Batch Accuracy - 0.93
Valid Loss - 0.9843555688858032; Valid Accuracy - 0.67
Epoch 52, CIFAR-10 Batch 5:  Batch Loss - 0.3392140865325928; Batch Accuracy - 0.9
Valid Loss - 1.0118074417114258; Valid Accuracy - 0.66
Epoch 53, CIFAR-10 Batch 1:  Batch Loss - 0.5228209495544434; Batch Accuracy - 0.82
Valid Loss - 1.1078782081604004; Valid Accuracy - 0.65
Epoch 53, CIFAR-10 Batch 2:  Batch Loss - 0.2938135862350464; Batch Accuracy - 0.97
Valid Loss - 0.9837851524353027; Valid Accuracy - 0.66
Epoch 53, CIFAR-10 Batch 3:  Batch Loss - 0.17373889684677124; Batch Accuracy - 0.93
Valid Loss - 1.0118470191955566; Valid Accuracy - 0.66
Epoch 53, CIFAR-10 Batch 4:  Batch Loss - 0.19602052867412567; Batch Accuracy - 0.95
Valid Loss - 0.9953722953796387; Valid Accuracy - 0.67
Epoch 53, CIFAR-10 Batch 5:  Batch Loss - 0.32117223739624023; Batch Accuracy - 0.9
Valid Loss - 1.0061709880828857; Valid Accuracy - 0.66
Epoch 54, CIFAR-10 Batch 1:  Batch Loss - 0.3471677303314209; Batch Accuracy - 0.9
Valid Loss - 1.044668436050415; Valid Accuracy - 0.66
Epoch 54, CIFAR-10 Batch 2:  Batch Loss - 0.2763333320617676; Batch Accuracy - 0.98
Valid Loss - 1.027083396911621; Valid Accuracy - 0.65
Epoch 54, CIFAR-10 Batch 3:  Batch Loss - 0.21868211030960083; Batch Accuracy - 0.95
Valid Loss - 0.989341139793396; Valid Accuracy - 0.66
Epoch 54, CIFAR-10 Batch 4:  Batch Loss - 0.17869412899017334; Batch Accuracy - 0.97
Valid Loss - 0.9850198030471802; Valid Accuracy - 0.67
Epoch 54, CIFAR-10 Batch 5:  Batch Loss - 0.35039135813713074; Batch Accuracy - 0.9
Valid Loss - 0.9891927242279053; Valid Accuracy - 0.67
Epoch 55, CIFAR-10 Batch 1:  Batch Loss - 0.28709909319877625; Batch Accuracy - 0.9
Valid Loss - 1.0106284618377686; Valid Accuracy - 0.67
Epoch 55, CIFAR-10 Batch 2:  Batch Loss - 0.2867651581764221; Batch Accuracy - 0.93
Valid Loss - 0.9709138870239258; Valid Accuracy - 0.67
Epoch 55, CIFAR-10 Batch 3:  Batch Loss - 0.19543661177158356; Batch Accuracy - 0.97
Valid Loss - 1.028359055519104; Valid Accuracy - 0.66
Epoch 55, CIFAR-10 Batch 4:  Batch Loss - 0.20223075151443481; Batch Accuracy - 0.97
Valid Loss - 0.9868248701095581; Valid Accuracy - 0.67
Epoch 55, CIFAR-10 Batch 5:  Batch Loss - 0.3163195252418518; Batch Accuracy - 0.95
Valid Loss - 0.9699716567993164; Valid Accuracy - 0.67
Epoch 56, CIFAR-10 Batch 1:  Batch Loss - 0.26851579546928406; Batch Accuracy - 0.93
Valid Loss - 1.0056467056274414; Valid Accuracy - 0.66
Epoch 56, CIFAR-10 Batch 2:  Batch Loss - 0.28319838643074036; Batch Accuracy - 0.97
Valid Loss - 0.9568603038787842; Valid Accuracy - 0.68
Epoch 56, CIFAR-10 Batch 3:  Batch Loss - 0.159992054104805; Batch Accuracy - 0.97
Valid Loss - 1.0009801387786865; Valid Accuracy - 0.66
Epoch 56, CIFAR-10 Batch 4:  Batch Loss - 0.17928946018218994; Batch Accuracy - 0.97
Valid Loss - 0.99077308177948; Valid Accuracy - 0.67
Epoch 56, CIFAR-10 Batch 5:  Batch Loss - 0.30733522772789; Batch Accuracy - 0.9
Valid Loss - 1.0048019886016846; Valid Accuracy - 0.67
Epoch 57, CIFAR-10 Batch 1:  Batch Loss - 0.22777990996837616; Batch Accuracy - 0.95
Valid Loss - 0.9775484204292297; Valid Accuracy - 0.68
Epoch 57, CIFAR-10 Batch 2:  Batch Loss - 0.2783927023410797; Batch Accuracy - 0.97
Valid Loss - 0.9885130524635315; Valid Accuracy - 0.67
Epoch 57, CIFAR-10 Batch 3:  Batch Loss - 0.18529830873012543; Batch Accuracy - 0.93
Valid Loss - 1.0015708208084106; Valid Accuracy - 0.66
Epoch 57, CIFAR-10 Batch 4:  Batch Loss - 0.18396586179733276; Batch Accuracy - 0.95
Valid Loss - 0.9840569496154785; Valid Accuracy - 0.67
Epoch 57, CIFAR-10 Batch 5:  Batch Loss - 0.28637176752090454; Batch Accuracy - 0.95
Valid Loss - 0.9813052415847778; Valid Accuracy - 0.67
Epoch 58, CIFAR-10 Batch 1:  Batch Loss - 0.30448082089424133; Batch Accuracy - 0.9
Valid Loss - 0.9822003841400146; Valid Accuracy - 0.68
Epoch 58, CIFAR-10 Batch 2:  Batch Loss - 0.23874437808990479; Batch Accuracy - 1.0
Valid Loss - 0.9468148350715637; Valid Accuracy - 0.68
Epoch 58, CIFAR-10 Batch 3:  Batch Loss - 0.16335393488407135; Batch Accuracy - 0.95
Valid Loss - 0.9923856258392334; Valid Accuracy - 0.66
Epoch 58, CIFAR-10 Batch 4:  Batch Loss - 0.19476990401744843; Batch Accuracy - 0.95
Valid Loss - 1.0114624500274658; Valid Accuracy - 0.67
Epoch 58, CIFAR-10 Batch 5:  Batch Loss - 0.3433336317539215; Batch Accuracy - 0.88
Valid Loss - 1.0018925666809082; Valid Accuracy - 0.67
Epoch 59, CIFAR-10 Batch 1:  Batch Loss - 0.22396335005760193; Batch Accuracy - 0.97
Valid Loss - 0.9927114844322205; Valid Accuracy - 0.67
Epoch 59, CIFAR-10 Batch 2:  Batch Loss - 0.26770439743995667; Batch Accuracy - 0.95
Valid Loss - 0.9893336892127991; Valid Accuracy - 0.67
Epoch 59, CIFAR-10 Batch 3:  Batch Loss - 0.1845427006483078; Batch Accuracy - 0.95
Valid Loss - 1.0539512634277344; Valid Accuracy - 0.65
Epoch 59, CIFAR-10 Batch 4:  Batch Loss - 0.1374792605638504; Batch Accuracy - 0.97
Valid Loss - 0.9852505326271057; Valid Accuracy - 0.67
Epoch 59, CIFAR-10 Batch 5:  Batch Loss - 0.262988418340683; Batch Accuracy - 0.93
Valid Loss - 0.9859070777893066; Valid Accuracy - 0.67
Epoch 60, CIFAR-10 Batch 1:  Batch Loss - 0.2664121091365814; Batch Accuracy - 0.9
Valid Loss - 1.0236176252365112; Valid Accuracy - 0.66
Epoch 60, CIFAR-10 Batch 2:  Batch Loss - 0.21052458882331848; Batch Accuracy - 0.97
Valid Loss - 1.0037769079208374; Valid Accuracy - 0.67
Epoch 60, CIFAR-10 Batch 3:  Batch Loss - 0.1472627818584442; Batch Accuracy - 0.97
Valid Loss - 0.9692195653915405; Valid Accuracy - 0.67
Epoch 60, CIFAR-10 Batch 4:  Batch Loss - 0.13236767053604126; Batch Accuracy - 0.97
Valid Loss - 1.023038625717163; Valid Accuracy - 0.67
Epoch 60, CIFAR-10 Batch 5:  Batch Loss - 0.22534877061843872; Batch Accuracy - 0.93
Valid Loss - 0.9714552760124207; Valid Accuracy - 0.68
Epoch 61, CIFAR-10 Batch 1:  Batch Loss - 0.21821200847625732; Batch Accuracy - 0.93
Valid Loss - 0.9892972111701965; Valid Accuracy - 0.67
Epoch 61, CIFAR-10 Batch 2:  Batch Loss - 0.21328866481781006; Batch Accuracy - 1.0
Valid Loss - 0.9438877105712891; Valid Accuracy - 0.68
Epoch 61, CIFAR-10 Batch 3:  Batch Loss - 0.14353235065937042; Batch Accuracy - 1.0
Valid Loss - 0.9732037782669067; Valid Accuracy - 0.68
Epoch 61, CIFAR-10 Batch 4:  Batch Loss - 0.11466585844755173; Batch Accuracy - 1.0
Valid Loss - 0.9490002989768982; Valid Accuracy - 0.69
Epoch 61, CIFAR-10 Batch 5:  Batch Loss - 0.261374831199646; Batch Accuracy - 0.9
Valid Loss - 0.97706538438797; Valid Accuracy - 0.68
Epoch 62, CIFAR-10 Batch 1:  Batch Loss - 0.15421606600284576; Batch Accuracy - 0.95
Valid Loss - 0.9832043051719666; Valid Accuracy - 0.68
Epoch 62, CIFAR-10 Batch 2:  Batch Loss - 0.19770844280719757; Batch Accuracy - 0.97
Valid Loss - 0.9625471234321594; Valid Accuracy - 0.67
Epoch 62, CIFAR-10 Batch 3:  Batch Loss - 0.13685928285121918; Batch Accuracy - 0.97
Valid Loss - 0.9812723994255066; Valid Accuracy - 0.68
Epoch 62, CIFAR-10 Batch 4:  Batch Loss - 0.13125140964984894; Batch Accuracy - 1.0
Valid Loss - 0.997316837310791; Valid Accuracy - 0.67
Epoch 62, CIFAR-10 Batch 5:  Batch Loss - 0.2568438947200775; Batch Accuracy - 0.95
Valid Loss - 0.9753046631813049; Valid Accuracy - 0.68
Epoch 63, CIFAR-10 Batch 1:  Batch Loss - 0.18678471446037292; Batch Accuracy - 0.95
Valid Loss - 0.9729107022285461; Valid Accuracy - 0.69
Epoch 63, CIFAR-10 Batch 2:  Batch Loss - 0.1788540929555893; Batch Accuracy - 1.0
Valid Loss - 0.9430641531944275; Valid Accuracy - 0.68
Epoch 63, CIFAR-10 Batch 3:  Batch Loss - 0.1402471661567688; Batch Accuracy - 0.97
Valid Loss - 0.9867455363273621; Valid Accuracy - 0.67
Epoch 63, CIFAR-10 Batch 4:  Batch Loss - 0.13058078289031982; Batch Accuracy - 1.0
Valid Loss - 0.9624257683753967; Valid Accuracy - 0.68
Epoch 63, CIFAR-10 Batch 5:  Batch Loss - 0.2255140244960785; Batch Accuracy - 0.98
Valid Loss - 0.9980331659317017; Valid Accuracy - 0.67
Epoch 64, CIFAR-10 Batch 1:  Batch Loss - 0.21847018599510193; Batch Accuracy - 0.93
Valid Loss - 1.0079330205917358; Valid Accuracy - 0.67
Epoch 64, CIFAR-10 Batch 2:  Batch Loss - 0.22333481907844543; Batch Accuracy - 1.0
Valid Loss - 0.967897355556488; Valid Accuracy - 0.68
Epoch 64, CIFAR-10 Batch 3:  Batch Loss - 0.20141902565956116; Batch Accuracy - 0.95
Valid Loss - 0.9942701458930969; Valid Accuracy - 0.67
Epoch 64, CIFAR-10 Batch 4:  Batch Loss - 0.12472278624773026; Batch Accuracy - 1.0
Valid Loss - 0.9748681783676147; Valid Accuracy - 0.68
Epoch 64, CIFAR-10 Batch 5:  Batch Loss - 0.18818697333335876; Batch Accuracy - 0.97
Valid Loss - 0.9798141121864319; Valid Accuracy - 0.68
Epoch 65, CIFAR-10 Batch 1:  Batch Loss - 0.19744381308555603; Batch Accuracy - 0.97
Valid Loss - 1.0151522159576416; Valid Accuracy - 0.67
Epoch 65, CIFAR-10 Batch 2:  Batch Loss - 0.1821734607219696; Batch Accuracy - 1.0
Valid Loss - 0.9845629334449768; Valid Accuracy - 0.67
Epoch 65, CIFAR-10 Batch 3:  Batch Loss - 0.1247393935918808; Batch Accuracy - 1.0
Valid Loss - 0.9940402507781982; Valid Accuracy - 0.68
Epoch 65, CIFAR-10 Batch 4:  Batch Loss - 0.09055023640394211; Batch Accuracy - 1.0
Valid Loss - 0.9548396468162537; Valid Accuracy - 0.69
Epoch 65, CIFAR-10 Batch 5:  Batch Loss - 0.20690393447875977; Batch Accuracy - 0.95
Valid Loss - 0.9951369762420654; Valid Accuracy - 0.67
Epoch 66, CIFAR-10 Batch 1:  Batch Loss - 0.17875248193740845; Batch Accuracy - 0.97
Valid Loss - 0.9665711522102356; Valid Accuracy - 0.69
Epoch 66, CIFAR-10 Batch 2:  Batch Loss - 0.16309478878974915; Batch Accuracy - 1.0
Valid Loss - 0.9774694442749023; Valid Accuracy - 0.67
Epoch 66, CIFAR-10 Batch 3:  Batch Loss - 0.14295481145381927; Batch Accuracy - 0.95
Valid Loss - 0.9969273209571838; Valid Accuracy - 0.67
Epoch 66, CIFAR-10 Batch 4:  Batch Loss - 0.09382614493370056; Batch Accuracy - 1.0
Valid Loss - 0.955365002155304; Valid Accuracy - 0.68
Epoch 66, CIFAR-10 Batch 5:  Batch Loss - 0.16372761130332947; Batch Accuracy - 0.98
Valid Loss - 0.9775947332382202; Valid Accuracy - 0.68
Epoch 67, CIFAR-10 Batch 1:  Batch Loss - 0.19434385001659393; Batch Accuracy - 0.95
Valid Loss - 0.9570138454437256; Valid Accuracy - 0.68
Epoch 67, CIFAR-10 Batch 2:  Batch Loss - 0.1326541304588318; Batch Accuracy - 1.0
Valid Loss - 0.9518624544143677; Valid Accuracy - 0.69
Epoch 67, CIFAR-10 Batch 3:  Batch Loss - 0.12086544185876846; Batch Accuracy - 0.97
Valid Loss - 0.9780265092849731; Valid Accuracy - 0.68
Epoch 67, CIFAR-10 Batch 4:  Batch Loss - 0.0926358625292778; Batch Accuracy - 0.97
Valid Loss - 0.9828794002532959; Valid Accuracy - 0.68
Epoch 67, CIFAR-10 Batch 5:  Batch Loss - 0.15648165345191956; Batch Accuracy - 0.97
Valid Loss - 0.9569412469863892; Valid Accuracy - 0.68
Epoch 68, CIFAR-10 Batch 1:  Batch Loss - 0.2266175001859665; Batch Accuracy - 0.93
Valid Loss - 0.9667098522186279; Valid Accuracy - 0.69
Epoch 68, CIFAR-10 Batch 2:  Batch Loss - 0.1573106348514557; Batch Accuracy - 1.0
Valid Loss - 0.988622784614563; Valid Accuracy - 0.68
Epoch 68, CIFAR-10 Batch 3:  Batch Loss - 0.1369374841451645; Batch Accuracy - 0.97
Valid Loss - 1.0350267887115479; Valid Accuracy - 0.66
Epoch 68, CIFAR-10 Batch 4:  Batch Loss - 0.10839974880218506; Batch Accuracy - 0.97
Valid Loss - 0.9774798154830933; Valid Accuracy - 0.68
Epoch 68, CIFAR-10 Batch 5:  Batch Loss - 0.15925367176532745; Batch Accuracy - 1.0
Valid Loss - 0.9610165953636169; Valid Accuracy - 0.68
Epoch 69, CIFAR-10 Batch 1:  Batch Loss - 0.19282908737659454; Batch Accuracy - 0.95
Valid Loss - 0.9853623509407043; Valid Accuracy - 0.68
Epoch 69, CIFAR-10 Batch 2:  Batch Loss - 0.1578824818134308; Batch Accuracy - 1.0
Valid Loss - 0.9665249586105347; Valid Accuracy - 0.68
Epoch 69, CIFAR-10 Batch 3:  Batch Loss - 0.12534137070178986; Batch Accuracy - 0.97
Valid Loss - 1.005069613456726; Valid Accuracy - 0.67
Epoch 69, CIFAR-10 Batch 4:  Batch Loss - 0.09303372353315353; Batch Accuracy - 1.0
Valid Loss - 0.9810324907302856; Valid Accuracy - 0.68
Epoch 69, CIFAR-10 Batch 5:  Batch Loss - 0.12873271107673645; Batch Accuracy - 1.0
Valid Loss - 0.96551513671875; Valid Accuracy - 0.68
Epoch 70, CIFAR-10 Batch 1:  Batch Loss - 0.15979447960853577; Batch Accuracy - 0.95
Valid Loss - 0.9511423707008362; Valid Accuracy - 0.69
Epoch 70, CIFAR-10 Batch 2:  Batch Loss - 0.14573736488819122; Batch Accuracy - 1.0
Valid Loss - 0.9496704339981079; Valid Accuracy - 0.69
Epoch 70, CIFAR-10 Batch 3:  Batch Loss - 0.12086955457925797; Batch Accuracy - 0.97
Valid Loss - 0.9648656845092773; Valid Accuracy - 0.69
Epoch 70, CIFAR-10 Batch 4:  Batch Loss - 0.11813265830278397; Batch Accuracy - 0.98
Valid Loss - 1.0016218423843384; Valid Accuracy - 0.67
Epoch 70, CIFAR-10 Batch 5:  Batch Loss - 0.14455893635749817; Batch Accuracy - 1.0
Valid Loss - 0.9588091373443604; Valid Accuracy - 0.69
Epoch 71, CIFAR-10 Batch 1:  Batch Loss - 0.16677112877368927; Batch Accuracy - 0.97
Valid Loss - 0.960628092288971; Valid Accuracy - 0.68
Epoch 71, CIFAR-10 Batch 2:  Batch Loss - 0.12070473283529282; Batch Accuracy - 1.0
Valid Loss - 0.9400944709777832; Valid Accuracy - 0.69
Epoch 71, CIFAR-10 Batch 3:  Batch Loss - 0.1272295117378235; Batch Accuracy - 0.97
Valid Loss - 0.9931598901748657; Valid Accuracy - 0.68
Epoch 71, CIFAR-10 Batch 4:  Batch Loss - 0.06544563919305801; Batch Accuracy - 1.0
Valid Loss - 0.9771376252174377; Valid Accuracy - 0.68
Epoch 71, CIFAR-10 Batch 5:  Batch Loss - 0.11985242366790771; Batch Accuracy - 1.0
Valid Loss - 0.9718534350395203; Valid Accuracy - 0.69
Epoch 72, CIFAR-10 Batch 1:  Batch Loss - 0.18248102068901062; Batch Accuracy - 0.95
Valid Loss - 0.9809768199920654; Valid Accuracy - 0.68
Epoch 72, CIFAR-10 Batch 2:  Batch Loss - 0.10203753411769867; Batch Accuracy - 1.0
Valid Loss - 0.9560431241989136; Valid Accuracy - 0.68
Epoch 72, CIFAR-10 Batch 3:  Batch Loss - 0.10025915503501892; Batch Accuracy - 1.0
Valid Loss - 0.9601495862007141; Valid Accuracy - 0.68
Epoch 72, CIFAR-10 Batch 4:  Batch Loss - 0.08382105827331543; Batch Accuracy - 0.97
Valid Loss - 0.9602436423301697; Valid Accuracy - 0.69
Epoch 72, CIFAR-10 Batch 5:  Batch Loss - 0.14356254041194916; Batch Accuracy - 0.97
Valid Loss - 0.9847731590270996; Valid Accuracy - 0.68
Epoch 73, CIFAR-10 Batch 1:  Batch Loss - 0.15371914207935333; Batch Accuracy - 0.97
Valid Loss - 0.9414937496185303; Valid Accuracy - 0.69
Epoch 73, CIFAR-10 Batch 2:  Batch Loss - 0.10867549479007721; Batch Accuracy - 1.0
Valid Loss - 0.9501427412033081; Valid Accuracy - 0.69
Epoch 73, CIFAR-10 Batch 3:  Batch Loss - 0.10352242738008499; Batch Accuracy - 1.0
Valid Loss - 0.9684047102928162; Valid Accuracy - 0.69
Epoch 73, CIFAR-10 Batch 4:  Batch Loss - 0.07045891880989075; Batch Accuracy - 1.0
Valid Loss - 0.9601556062698364; Valid Accuracy - 0.69
Epoch 73, CIFAR-10 Batch 5:  Batch Loss - 0.0947340577840805; Batch Accuracy - 1.0
Valid Loss - 0.9584618210792542; Valid Accuracy - 0.69
Epoch 74, CIFAR-10 Batch 1:  Batch Loss - 0.13130801916122437; Batch Accuracy - 0.97
Valid Loss - 0.9547703862190247; Valid Accuracy - 0.69
Epoch 74, CIFAR-10 Batch 2:  Batch Loss - 0.097440704703331; Batch Accuracy - 1.0
Valid Loss - 0.936616063117981; Valid Accuracy - 0.69
Epoch 74, CIFAR-10 Batch 3:  Batch Loss - 0.09792682528495789; Batch Accuracy - 1.0
Valid Loss - 0.9792290329933167; Valid Accuracy - 0.68
Epoch 74, CIFAR-10 Batch 4:  Batch Loss - 0.07678079605102539; Batch Accuracy - 1.0
Valid Loss - 1.014664888381958; Valid Accuracy - 0.68
Epoch 74, CIFAR-10 Batch 5:  Batch Loss - 0.09616705030202866; Batch Accuracy - 1.0
Valid Loss - 0.9710767269134521; Valid Accuracy - 0.69
Epoch 75, CIFAR-10 Batch 1:  Batch Loss - 0.13926836848258972; Batch Accuracy - 1.0
Valid Loss - 0.965365469455719; Valid Accuracy - 0.69
Epoch 75, CIFAR-10 Batch 2:  Batch Loss - 0.09968376159667969; Batch Accuracy - 1.0
Valid Loss - 0.9785661697387695; Valid Accuracy - 0.68
Epoch 75, CIFAR-10 Batch 3:  Batch Loss - 0.10552375763654709; Batch Accuracy - 1.0
Valid Loss - 1.0020089149475098; Valid Accuracy - 0.68
Epoch 75, CIFAR-10 Batch 4:  Batch Loss - 0.07938703894615173; Batch Accuracy - 1.0
Valid Loss - 0.9704069495201111; Valid Accuracy - 0.69
Epoch 75, CIFAR-10 Batch 5:  Batch Loss - 0.10431619733572006; Batch Accuracy - 1.0
Valid Loss - 1.0015406608581543; Valid Accuracy - 0.69
Epoch 76, CIFAR-10 Batch 1:  Batch Loss - 0.10310813039541245; Batch Accuracy - 1.0
Valid Loss - 0.9580720067024231; Valid Accuracy - 0.69
Epoch 76, CIFAR-10 Batch 2:  Batch Loss - 0.08135202527046204; Batch Accuracy - 1.0
Valid Loss - 0.96738600730896; Valid Accuracy - 0.69
Epoch 76, CIFAR-10 Batch 3:  Batch Loss - 0.09373021870851517; Batch Accuracy - 1.0
Valid Loss - 0.9609652161598206; Valid Accuracy - 0.69
Epoch 76, CIFAR-10 Batch 4:  Batch Loss - 0.05601099133491516; Batch Accuracy - 1.0
Valid Loss - 0.9916854500770569; Valid Accuracy - 0.69
Epoch 76, CIFAR-10 Batch 5:  Batch Loss - 0.11466346681118011; Batch Accuracy - 1.0
Valid Loss - 0.9598422050476074; Valid Accuracy - 0.68
Epoch 77, CIFAR-10 Batch 1:  Batch Loss - 0.11093735694885254; Batch Accuracy - 1.0
Valid Loss - 0.9658042192459106; Valid Accuracy - 0.69
Epoch 77, CIFAR-10 Batch 2:  Batch Loss - 0.08743026852607727; Batch Accuracy - 1.0
Valid Loss - 0.9402514100074768; Valid Accuracy - 0.69
Epoch 77, CIFAR-10 Batch 3:  Batch Loss - 0.10808221995830536; Batch Accuracy - 1.0
Valid Loss - 0.975553035736084; Valid Accuracy - 0.68
Epoch 77, CIFAR-10 Batch 4:  Batch Loss - 0.06318722665309906; Batch Accuracy - 1.0
Valid Loss - 0.976291298866272; Valid Accuracy - 0.69
Epoch 77, CIFAR-10 Batch 5:  Batch Loss - 0.1180131733417511; Batch Accuracy - 1.0
Valid Loss - 0.9537447690963745; Valid Accuracy - 0.7
Epoch 78, CIFAR-10 Batch 1:  Batch Loss - 0.12366975843906403; Batch Accuracy - 1.0
Valid Loss - 0.9502814412117004; Valid Accuracy - 0.7
Epoch 78, CIFAR-10 Batch 2:  Batch Loss - 0.10924382507801056; Batch Accuracy - 1.0
Valid Loss - 1.004364013671875; Valid Accuracy - 0.69
Epoch 78, CIFAR-10 Batch 3:  Batch Loss - 0.11808517575263977; Batch Accuracy - 0.98
Valid Loss - 1.015861988067627; Valid Accuracy - 0.68
Epoch 78, CIFAR-10 Batch 4:  Batch Loss - 0.05626899003982544; Batch Accuracy - 1.0
Valid Loss - 1.0048795938491821; Valid Accuracy - 0.69
Epoch 78, CIFAR-10 Batch 5:  Batch Loss - 0.09211842715740204; Batch Accuracy - 1.0
Valid Loss - 0.9562089443206787; Valid Accuracy - 0.69
Epoch 79, CIFAR-10 Batch 1:  Batch Loss - 0.1080327108502388; Batch Accuracy - 0.97
Valid Loss - 0.9503222107887268; Valid Accuracy - 0.7
Epoch 79, CIFAR-10 Batch 2:  Batch Loss - 0.08647727966308594; Batch Accuracy - 1.0
Valid Loss - 0.9496187567710876; Valid Accuracy - 0.7
Epoch 79, CIFAR-10 Batch 3:  Batch Loss - 0.09017830342054367; Batch Accuracy - 1.0
Valid Loss - 0.9719979166984558; Valid Accuracy - 0.69
Epoch 79, CIFAR-10 Batch 4:  Batch Loss - 0.05841955915093422; Batch Accuracy - 1.0
Valid Loss - 0.9881083369255066; Valid Accuracy - 0.69
Epoch 79, CIFAR-10 Batch 5:  Batch Loss - 0.1263830065727234; Batch Accuracy - 0.97
Valid Loss - 0.996024489402771; Valid Accuracy - 0.68
Epoch 80, CIFAR-10 Batch 1:  Batch Loss - 0.0948183462023735; Batch Accuracy - 1.0
Valid Loss - 0.9533902406692505; Valid Accuracy - 0.69
Epoch 80, CIFAR-10 Batch 2:  Batch Loss - 0.07636605203151703; Batch Accuracy - 1.0
Valid Loss - 0.9349836707115173; Valid Accuracy - 0.69
Epoch 80, CIFAR-10 Batch 3:  Batch Loss - 0.08127731829881668; Batch Accuracy - 1.0
Valid Loss - 0.9718371629714966; Valid Accuracy - 0.69
Epoch 80, CIFAR-10 Batch 4:  Batch Loss - 0.06314647942781448; Batch Accuracy - 1.0
Valid Loss - 1.0187932252883911; Valid Accuracy - 0.67
Epoch 80, CIFAR-10 Batch 5:  Batch Loss - 0.10014897584915161; Batch Accuracy - 1.0
Valid Loss - 0.9801344871520996; Valid Accuracy - 0.69
Epoch 81, CIFAR-10 Batch 1:  Batch Loss - 0.09028550237417221; Batch Accuracy - 1.0
Valid Loss - 0.9682390689849854; Valid Accuracy - 0.7
Epoch 81, CIFAR-10 Batch 2:  Batch Loss - 0.06965629756450653; Batch Accuracy - 1.0
Valid Loss - 0.928860068321228; Valid Accuracy - 0.7
Epoch 81, CIFAR-10 Batch 3:  Batch Loss - 0.07673852145671844; Batch Accuracy - 1.0
Valid Loss - 0.9653229117393494; Valid Accuracy - 0.69
Epoch 81, CIFAR-10 Batch 4:  Batch Loss - 0.05940782278776169; Batch Accuracy - 1.0
Valid Loss - 0.9618067741394043; Valid Accuracy - 0.69
Epoch 81, CIFAR-10 Batch 5:  Batch Loss - 0.10097521543502808; Batch Accuracy - 0.98
Valid Loss - 0.9790291786193848; Valid Accuracy - 0.69
Epoch 82, CIFAR-10 Batch 1:  Batch Loss - 0.10041303187608719; Batch Accuracy - 1.0
Valid Loss - 0.9455741047859192; Valid Accuracy - 0.7
Epoch 82, CIFAR-10 Batch 2:  Batch Loss - 0.07133738696575165; Batch Accuracy - 1.0
Valid Loss - 0.9482634663581848; Valid Accuracy - 0.69
Epoch 82, CIFAR-10 Batch 3:  Batch Loss - 0.09759952872991562; Batch Accuracy - 0.97
Valid Loss - 0.976341724395752; Valid Accuracy - 0.69
Epoch 82, CIFAR-10 Batch 4:  Batch Loss - 0.04972247779369354; Batch Accuracy - 1.0
Valid Loss - 0.9462218880653381; Valid Accuracy - 0.7
Epoch 82, CIFAR-10 Batch 5:  Batch Loss - 0.10315457731485367; Batch Accuracy - 0.97
Valid Loss - 0.9934984445571899; Valid Accuracy - 0.69
Epoch 83, CIFAR-10 Batch 1:  Batch Loss - 0.10871216654777527; Batch Accuracy - 0.97
Valid Loss - 0.9702040553092957; Valid Accuracy - 0.69
Epoch 83, CIFAR-10 Batch 2:  Batch Loss - 0.0600859597325325; Batch Accuracy - 1.0
Valid Loss - 0.9641990065574646; Valid Accuracy - 0.69
Epoch 83, CIFAR-10 Batch 3:  Batch Loss - 0.09576483070850372; Batch Accuracy - 1.0
Valid Loss - 1.037814974784851; Valid Accuracy - 0.68
Epoch 83, CIFAR-10 Batch 4:  Batch Loss - 0.04333813488483429; Batch Accuracy - 1.0
Valid Loss - 0.9495420455932617; Valid Accuracy - 0.69
Epoch 83, CIFAR-10 Batch 5:  Batch Loss - 0.0726538673043251; Batch Accuracy - 1.0
Valid Loss - 0.936789870262146; Valid Accuracy - 0.7
Epoch 84, CIFAR-10 Batch 1:  Batch Loss - 0.10216152667999268; Batch Accuracy - 1.0
Valid Loss - 0.955559492111206; Valid Accuracy - 0.7
Epoch 84, CIFAR-10 Batch 2:  Batch Loss - 0.06553155183792114; Batch Accuracy - 1.0
Valid Loss - 0.9528524875640869; Valid Accuracy - 0.69
Epoch 84, CIFAR-10 Batch 3:  Batch Loss - 0.09972913563251495; Batch Accuracy - 1.0
Valid Loss - 1.0166575908660889; Valid Accuracy - 0.68
Epoch 84, CIFAR-10 Batch 4:  Batch Loss - 0.044932879507541656; Batch Accuracy - 1.0
Valid Loss - 0.9338526129722595; Valid Accuracy - 0.7
Epoch 84, CIFAR-10 Batch 5:  Batch Loss - 0.09841687232255936; Batch Accuracy - 0.98
Valid Loss - 0.9601709246635437; Valid Accuracy - 0.69
Epoch 85, CIFAR-10 Batch 1:  Batch Loss - 0.102249376475811; Batch Accuracy - 1.0
Valid Loss - 0.9713889360427856; Valid Accuracy - 0.7
Epoch 85, CIFAR-10 Batch 2:  Batch Loss - 0.08114679157733917; Batch Accuracy - 1.0
Valid Loss - 0.9669626355171204; Valid Accuracy - 0.69
Epoch 85, CIFAR-10 Batch 3:  Batch Loss - 0.08554328978061676; Batch Accuracy - 1.0
Valid Loss - 0.9722603559494019; Valid Accuracy - 0.69
Epoch 85, CIFAR-10 Batch 4:  Batch Loss - 0.040530331432819366; Batch Accuracy - 1.0
Valid Loss - 0.9428725242614746; Valid Accuracy - 0.7
Epoch 85, CIFAR-10 Batch 5:  Batch Loss - 0.07343915104866028; Batch Accuracy - 1.0
Valid Loss - 0.9585242867469788; Valid Accuracy - 0.69
Epoch 86, CIFAR-10 Batch 1:  Batch Loss - 0.0779305174946785; Batch Accuracy - 1.0
Valid Loss - 0.9549555778503418; Valid Accuracy - 0.69
Epoch 86, CIFAR-10 Batch 2:  Batch Loss - 0.05937620997428894; Batch Accuracy - 1.0
Valid Loss - 0.9745188355445862; Valid Accuracy - 0.69
Epoch 86, CIFAR-10 Batch 3:  Batch Loss - 0.07280866801738739; Batch Accuracy - 1.0
Valid Loss - 1.0156922340393066; Valid Accuracy - 0.67
Epoch 86, CIFAR-10 Batch 4:  Batch Loss - 0.0653979480266571; Batch Accuracy - 1.0
Valid Loss - 0.9697594046592712; Valid Accuracy - 0.69
Epoch 86, CIFAR-10 Batch 5:  Batch Loss - 0.08530857414007187; Batch Accuracy - 1.0
Valid Loss - 0.9604801535606384; Valid Accuracy - 0.7
Epoch 87, CIFAR-10 Batch 1:  Batch Loss - 0.08143138885498047; Batch Accuracy - 1.0
Valid Loss - 0.9558524489402771; Valid Accuracy - 0.7
Epoch 87, CIFAR-10 Batch 2:  Batch Loss - 0.0611388199031353; Batch Accuracy - 1.0
Valid Loss - 0.9586504697799683; Valid Accuracy - 0.69
Epoch 87, CIFAR-10 Batch 3:  Batch Loss - 0.06680193543434143; Batch Accuracy - 1.0
Valid Loss - 0.9775469899177551; Valid Accuracy - 0.69
Epoch 87, CIFAR-10 Batch 4:  Batch Loss - 0.036607302725315094; Batch Accuracy - 1.0
Valid Loss - 0.9332848191261292; Valid Accuracy - 0.7
Epoch 87, CIFAR-10 Batch 5:  Batch Loss - 0.08293552696704865; Batch Accuracy - 1.0
Valid Loss - 0.9345341324806213; Valid Accuracy - 0.7
Epoch 88, CIFAR-10 Batch 1:  Batch Loss - 0.11587401479482651; Batch Accuracy - 0.95
Valid Loss - 0.9629696607589722; Valid Accuracy - 0.7
Epoch 88, CIFAR-10 Batch 2:  Batch Loss - 0.08027948439121246; Batch Accuracy - 1.0
Valid Loss - 0.9633137583732605; Valid Accuracy - 0.68
Epoch 88, CIFAR-10 Batch 3:  Batch Loss - 0.07935518771409988; Batch Accuracy - 1.0
Valid Loss - 1.0466196537017822; Valid Accuracy - 0.68
Epoch 88, CIFAR-10 Batch 4:  Batch Loss - 0.0689360499382019; Batch Accuracy - 1.0
Valid Loss - 1.0071779489517212; Valid Accuracy - 0.68
Epoch 88, CIFAR-10 Batch 5:  Batch Loss - 0.07448862493038177; Batch Accuracy - 1.0
Valid Loss - 0.9642237424850464; Valid Accuracy - 0.69
Epoch 89, CIFAR-10 Batch 1:  Batch Loss - 0.08282779157161713; Batch Accuracy - 0.97
Valid Loss - 0.968787670135498; Valid Accuracy - 0.7
Epoch 89, CIFAR-10 Batch 2:  Batch Loss - 0.05264800041913986; Batch Accuracy - 1.0
Valid Loss - 0.9582907557487488; Valid Accuracy - 0.69
Epoch 89, CIFAR-10 Batch 3:  Batch Loss - 0.07080740481615067; Batch Accuracy - 1.0
Valid Loss - 1.0176135301589966; Valid Accuracy - 0.68
Epoch 89, CIFAR-10 Batch 4:  Batch Loss - 0.045870743691921234; Batch Accuracy - 1.0
Valid Loss - 0.9485076665878296; Valid Accuracy - 0.69
Epoch 89, CIFAR-10 Batch 5:  Batch Loss - 0.0700150653719902; Batch Accuracy - 1.0
Valid Loss - 0.9262399077415466; Valid Accuracy - 0.7
Epoch 90, CIFAR-10 Batch 1:  Batch Loss - 0.08141478896141052; Batch Accuracy - 1.0
Valid Loss - 0.9569897651672363; Valid Accuracy - 0.7
Epoch 90, CIFAR-10 Batch 2:  Batch Loss - 0.08882143348455429; Batch Accuracy - 1.0
Valid Loss - 0.966623842716217; Valid Accuracy - 0.69
Epoch 90, CIFAR-10 Batch 3:  Batch Loss - 0.05645199865102768; Batch Accuracy - 1.0
Valid Loss - 1.0096619129180908; Valid Accuracy - 0.69
Epoch 90, CIFAR-10 Batch 4:  Batch Loss - 0.03835827857255936; Batch Accuracy - 1.0
Valid Loss - 1.0064526796340942; Valid Accuracy - 0.69
Epoch 90, CIFAR-10 Batch 5:  Batch Loss - 0.054120831191539764; Batch Accuracy - 1.0
Valid Loss - 0.9285137057304382; Valid Accuracy - 0.7
Epoch 91, CIFAR-10 Batch 1:  Batch Loss - 0.0827435553073883; Batch Accuracy - 1.0
Valid Loss - 0.9518998265266418; Valid Accuracy - 0.7
Epoch 91, CIFAR-10 Batch 2:  Batch Loss - 0.06397660076618195; Batch Accuracy - 1.0
Valid Loss - 0.9652183055877686; Valid Accuracy - 0.69
Epoch 91, CIFAR-10 Batch 3:  Batch Loss - 0.058592505753040314; Batch Accuracy - 1.0
Valid Loss - 0.9519471526145935; Valid Accuracy - 0.7
Epoch 91, CIFAR-10 Batch 4:  Batch Loss - 0.02654731646180153; Batch Accuracy - 1.0
Valid Loss - 0.9524766802787781; Valid Accuracy - 0.7
Epoch 91, CIFAR-10 Batch 5:  Batch Loss - 0.06650715321302414; Batch Accuracy - 1.0
Valid Loss - 0.9496452212333679; Valid Accuracy - 0.7
Epoch 92, CIFAR-10 Batch 1:  Batch Loss - 0.05809450522065163; Batch Accuracy - 1.0
Valid Loss - 0.936029314994812; Valid Accuracy - 0.69
Epoch 92, CIFAR-10 Batch 2:  Batch Loss - 0.07206375151872635; Batch Accuracy - 1.0
Valid Loss - 0.963002622127533; Valid Accuracy - 0.69
Epoch 92, CIFAR-10 Batch 3:  Batch Loss - 0.06192469596862793; Batch Accuracy - 1.0
Valid Loss - 1.0046806335449219; Valid Accuracy - 0.69
Epoch 92, CIFAR-10 Batch 4:  Batch Loss - 0.027010872960090637; Batch Accuracy - 1.0
Valid Loss - 0.9453479647636414; Valid Accuracy - 0.7
Epoch 92, CIFAR-10 Batch 5:  Batch Loss - 0.050796281546354294; Batch Accuracy - 1.0
Valid Loss - 0.9941461682319641; Valid Accuracy - 0.69
Epoch 93, CIFAR-10 Batch 1:  Batch Loss - 0.06380735337734222; Batch Accuracy - 1.0
Valid Loss - 0.937359094619751; Valid Accuracy - 0.7
Epoch 93, CIFAR-10 Batch 2:  Batch Loss - 0.05137292295694351; Batch Accuracy - 1.0
Valid Loss - 0.9893215894699097; Valid Accuracy - 0.69
Epoch 93, CIFAR-10 Batch 3:  Batch Loss - 0.06042046844959259; Batch Accuracy - 1.0
Valid Loss - 1.0267611742019653; Valid Accuracy - 0.69
Epoch 93, CIFAR-10 Batch 4:  Batch Loss - 0.043065134435892105; Batch Accuracy - 1.0
Valid Loss - 0.9789744019508362; Valid Accuracy - 0.69
Epoch 93, CIFAR-10 Batch 5:  Batch Loss - 0.06446362286806107; Batch Accuracy - 1.0
Valid Loss - 0.9376420378684998; Valid Accuracy - 0.7
Epoch 94, CIFAR-10 Batch 1:  Batch Loss - 0.0587795153260231; Batch Accuracy - 1.0
Valid Loss - 0.9796512126922607; Valid Accuracy - 0.69
Epoch 94, CIFAR-10 Batch 2:  Batch Loss - 0.05449396371841431; Batch Accuracy - 1.0
Valid Loss - 0.9488588571548462; Valid Accuracy - 0.69
Epoch 94, CIFAR-10 Batch 3:  Batch Loss - 0.07070683687925339; Batch Accuracy - 1.0
Valid Loss - 1.0108073949813843; Valid Accuracy - 0.68
Epoch 94, CIFAR-10 Batch 4:  Batch Loss - 0.030076364055275917; Batch Accuracy - 1.0
Valid Loss - 0.9586090445518494; Valid Accuracy - 0.69
Epoch 94, CIFAR-10 Batch 5:  Batch Loss - 0.04881901293992996; Batch Accuracy - 1.0
Valid Loss - 0.957522988319397; Valid Accuracy - 0.69
Epoch 95, CIFAR-10 Batch 1:  Batch Loss - 0.05353923514485359; Batch Accuracy - 1.0
Valid Loss - 0.9554235935211182; Valid Accuracy - 0.7
Epoch 95, CIFAR-10 Batch 2:  Batch Loss - 0.051578108221292496; Batch Accuracy - 1.0
Valid Loss - 0.9472689032554626; Valid Accuracy - 0.69
Epoch 95, CIFAR-10 Batch 3:  Batch Loss - 0.053906749933958054; Batch Accuracy - 1.0
Valid Loss - 1.0331707000732422; Valid Accuracy - 0.68
Epoch 95, CIFAR-10 Batch 4:  Batch Loss - 0.029778940603137016; Batch Accuracy - 1.0
Valid Loss - 0.9645099639892578; Valid Accuracy - 0.7
Epoch 95, CIFAR-10 Batch 5:  Batch Loss - 0.06633441150188446; Batch Accuracy - 1.0
Valid Loss - 0.9994327425956726; Valid Accuracy - 0.69
Epoch 96, CIFAR-10 Batch 1:  Batch Loss - 0.06113174185156822; Batch Accuracy - 1.0
Valid Loss - 0.9641615152359009; Valid Accuracy - 0.7
Epoch 96, CIFAR-10 Batch 2:  Batch Loss - 0.057537518441677094; Batch Accuracy - 1.0
Valid Loss - 0.9657935500144958; Valid Accuracy - 0.7
Epoch 96, CIFAR-10 Batch 3:  Batch Loss - 0.051459915935993195; Batch Accuracy - 1.0
Valid Loss - 0.9896338582038879; Valid Accuracy - 0.69
Epoch 96, CIFAR-10 Batch 4:  Batch Loss - 0.050906527787446976; Batch Accuracy - 1.0
Valid Loss - 0.9618730545043945; Valid Accuracy - 0.7
Epoch 96, CIFAR-10 Batch 5:  Batch Loss - 0.0553601011633873; Batch Accuracy - 1.0
Valid Loss - 0.9997756481170654; Valid Accuracy - 0.69
Epoch 97, CIFAR-10 Batch 1:  Batch Loss - 0.07070614397525787; Batch Accuracy - 1.0
Valid Loss - 0.937451183795929; Valid Accuracy - 0.71
Epoch 97, CIFAR-10 Batch 2:  Batch Loss - 0.041074905544519424; Batch Accuracy - 1.0
Valid Loss - 0.9706225395202637; Valid Accuracy - 0.7
Epoch 97, CIFAR-10 Batch 3:  Batch Loss - 0.047828543931245804; Batch Accuracy - 1.0
Valid Loss - 1.0057183504104614; Valid Accuracy - 0.69
Epoch 97, CIFAR-10 Batch 4:  Batch Loss - 0.028737686574459076; Batch Accuracy - 1.0
Valid Loss - 0.9903028011322021; Valid Accuracy - 0.7
Epoch 97, CIFAR-10 Batch 5:  Batch Loss - 0.05529026687145233; Batch Accuracy - 1.0
Valid Loss - 0.985987663269043; Valid Accuracy - 0.69
Epoch 98, CIFAR-10 Batch 1:  Batch Loss - 0.03805781528353691; Batch Accuracy - 1.0
Valid Loss - 0.9952190518379211; Valid Accuracy - 0.7
Epoch 98, CIFAR-10 Batch 2:  Batch Loss - 0.046226367354393005; Batch Accuracy - 1.0
Valid Loss - 0.9708588123321533; Valid Accuracy - 0.7
Epoch 98, CIFAR-10 Batch 3:  Batch Loss - 0.06369081139564514; Batch Accuracy - 1.0
Valid Loss - 1.039755940437317; Valid Accuracy - 0.68
Epoch 98, CIFAR-10 Batch 4:  Batch Loss - 0.03792044147849083; Batch Accuracy - 1.0
Valid Loss - 0.9538759589195251; Valid Accuracy - 0.7
Epoch 98, CIFAR-10 Batch 5:  Batch Loss - 0.056567877531051636; Batch Accuracy - 1.0
Valid Loss - 0.9661979675292969; Valid Accuracy - 0.7
Epoch 99, CIFAR-10 Batch 1:  Batch Loss - 0.046165961772203445; Batch Accuracy - 1.0
Valid Loss - 0.9875158071517944; Valid Accuracy - 0.7
Epoch 99, CIFAR-10 Batch 2:  Batch Loss - 0.03683727979660034; Batch Accuracy - 1.0
Valid Loss - 0.9776890277862549; Valid Accuracy - 0.69
Epoch 99, CIFAR-10 Batch 3:  Batch Loss - 0.06156357377767563; Batch Accuracy - 1.0
Valid Loss - 1.0074942111968994; Valid Accuracy - 0.69
Epoch 99, CIFAR-10 Batch 4:  Batch Loss - 0.03422711789608002; Batch Accuracy - 1.0
Valid Loss - 0.966637909412384; Valid Accuracy - 0.7
Epoch 99, CIFAR-10 Batch 5:  Batch Loss - 0.03675073757767677; Batch Accuracy - 1.0
Valid Loss - 0.9697367548942566; Valid Accuracy - 0.7
Epoch 100, CIFAR-10 Batch 1:  Batch Loss - 0.06269488483667374; Batch Accuracy - 1.0
Valid Loss - 0.9925441741943359; Valid Accuracy - 0.69
Epoch 100, CIFAR-10 Batch 2:  Batch Loss - 0.042247481644153595; Batch Accuracy - 1.0
Valid Loss - 0.955565869808197; Valid Accuracy - 0.7
Epoch 100, CIFAR-10 Batch 3:  Batch Loss - 0.04249664396047592; Batch Accuracy - 1.0
Valid Loss - 1.0114182233810425; Valid Accuracy - 0.69
Epoch 100, CIFAR-10 Batch 4:  Batch Loss - 0.027066480368375778; Batch Accuracy - 1.0
Valid Loss - 0.9684174656867981; Valid Accuracy - 0.7
Epoch 100, CIFAR-10 Batch 5:  Batch Loss - 0.04642102122306824; Batch Accuracy - 1.0
Valid Loss - 0.9971750974655151; Valid Accuracy - 0.69
Epoch 101, CIFAR-10 Batch 1:  Batch Loss - 0.043784528970718384; Batch Accuracy - 1.0
Valid Loss - 0.9750679731369019; Valid Accuracy - 0.7
Epoch 101, CIFAR-10 Batch 2:  Batch Loss - 0.04511250928044319; Batch Accuracy - 0.98
Valid Loss - 0.9796983599662781; Valid Accuracy - 0.69
Epoch 101, CIFAR-10 Batch 3:  Batch Loss - 0.05141327157616615; Batch Accuracy - 1.0
Valid Loss - 1.0055903196334839; Valid Accuracy - 0.69
Epoch 101, CIFAR-10 Batch 4:  Batch Loss - 0.041925959289073944; Batch Accuracy - 1.0
Valid Loss - 0.9634367227554321; Valid Accuracy - 0.7
Epoch 101, CIFAR-10 Batch 5:  Batch Loss - 0.04678541421890259; Batch Accuracy - 1.0
Valid Loss - 0.980435848236084; Valid Accuracy - 0.7
Epoch 102, CIFAR-10 Batch 1:  Batch Loss - 0.061924517154693604; Batch Accuracy - 1.0
Valid Loss - 0.9633159637451172; Valid Accuracy - 0.7
Epoch 102, CIFAR-10 Batch 2:  Batch Loss - 0.04443395882844925; Batch Accuracy - 1.0
Valid Loss - 0.9874839782714844; Valid Accuracy - 0.69
Epoch 102, CIFAR-10 Batch 3:  Batch Loss - 0.06281663477420807; Batch Accuracy - 1.0
Valid Loss - 1.044234275817871; Valid Accuracy - 0.68
Epoch 102, CIFAR-10 Batch 4:  Batch Loss - 0.03111913427710533; Batch Accuracy - 1.0
Valid Loss - 0.9694995880126953; Valid Accuracy - 0.7
Epoch 102, CIFAR-10 Batch 5:  Batch Loss - 0.070913165807724; Batch Accuracy - 1.0
Valid Loss - 1.0373066663742065; Valid Accuracy - 0.69
Epoch 103, CIFAR-10 Batch 1:  Batch Loss - 0.04013390466570854; Batch Accuracy - 1.0
Valid Loss - 0.9759172201156616; Valid Accuracy - 0.7
Epoch 103, CIFAR-10 Batch 2:  Batch Loss - 0.03453864902257919; Batch Accuracy - 1.0
Valid Loss - 0.9748449325561523; Valid Accuracy - 0.7
Epoch 103, CIFAR-10 Batch 3:  Batch Loss - 0.05497785657644272; Batch Accuracy - 1.0
Valid Loss - 1.011191487312317; Valid Accuracy - 0.69
Epoch 103, CIFAR-10 Batch 4:  Batch Loss - 0.02636398747563362; Batch Accuracy - 1.0
Valid Loss - 0.9520025253295898; Valid Accuracy - 0.71
Epoch 103, CIFAR-10 Batch 5:  Batch Loss - 0.05633256211876869; Batch Accuracy - 1.0
Valid Loss - 0.9890169501304626; Valid Accuracy - 0.7
Epoch 104, CIFAR-10 Batch 1:  Batch Loss - 0.05471689626574516; Batch Accuracy - 1.0
Valid Loss - 0.9843495488166809; Valid Accuracy - 0.7
Epoch 104, CIFAR-10 Batch 2:  Batch Loss - 0.04289616644382477; Batch Accuracy - 1.0
Valid Loss - 0.9520853161811829; Valid Accuracy - 0.7
Epoch 104, CIFAR-10 Batch 3:  Batch Loss - 0.05501796305179596; Batch Accuracy - 1.0
Valid Loss - 1.0506047010421753; Valid Accuracy - 0.68
Epoch 104, CIFAR-10 Batch 4:  Batch Loss - 0.031081318855285645; Batch Accuracy - 1.0
Valid Loss - 0.9922791123390198; Valid Accuracy - 0.7
Epoch 104, CIFAR-10 Batch 5:  Batch Loss - 0.06335269659757614; Batch Accuracy - 1.0
Valid Loss - 0.9634580016136169; Valid Accuracy - 0.7
Epoch 105, CIFAR-10 Batch 1:  Batch Loss - 0.0543837770819664; Batch Accuracy - 1.0
Valid Loss - 0.9532101154327393; Valid Accuracy - 0.71
Epoch 105, CIFAR-10 Batch 2:  Batch Loss - 0.03020847588777542; Batch Accuracy - 1.0
Valid Loss - 0.9690320491790771; Valid Accuracy - 0.7
Epoch 105, CIFAR-10 Batch 3:  Batch Loss - 0.04298725724220276; Batch Accuracy - 1.0
Valid Loss - 0.9869096875190735; Valid Accuracy - 0.7
Epoch 105, CIFAR-10 Batch 4:  Batch Loss - 0.02543361485004425; Batch Accuracy - 1.0
Valid Loss - 0.9902847409248352; Valid Accuracy - 0.7
Epoch 105, CIFAR-10 Batch 5:  Batch Loss - 0.05165580287575722; Batch Accuracy - 1.0
Valid Loss - 0.9923339486122131; Valid Accuracy - 0.7
Epoch 106, CIFAR-10 Batch 1:  Batch Loss - 0.04887594282627106; Batch Accuracy - 1.0
Valid Loss - 0.9432525634765625; Valid Accuracy - 0.7
Epoch 106, CIFAR-10 Batch 2:  Batch Loss - 0.045054398477077484; Batch Accuracy - 1.0
Valid Loss - 0.9907044172286987; Valid Accuracy - 0.68
Epoch 106, CIFAR-10 Batch 3:  Batch Loss - 0.04956859350204468; Batch Accuracy - 1.0
Valid Loss - 1.0093737840652466; Valid Accuracy - 0.7
Epoch 106, CIFAR-10 Batch 4:  Batch Loss - 0.022932298481464386; Batch Accuracy - 1.0
Valid Loss - 0.943982720375061; Valid Accuracy - 0.71
Epoch 106, CIFAR-10 Batch 5:  Batch Loss - 0.04728955775499344; Batch Accuracy - 1.0
Valid Loss - 0.982029914855957; Valid Accuracy - 0.7
Epoch 107, CIFAR-10 Batch 1:  Batch Loss - 0.03695043921470642; Batch Accuracy - 1.0
Valid Loss - 0.9649855494499207; Valid Accuracy - 0.71
Epoch 107, CIFAR-10 Batch 2:  Batch Loss - 0.028283629566431046; Batch Accuracy - 1.0
Valid Loss - 0.9733235836029053; Valid Accuracy - 0.7
Epoch 107, CIFAR-10 Batch 3:  Batch Loss - 0.047065865248441696; Batch Accuracy - 1.0
Valid Loss - 1.0090734958648682; Valid Accuracy - 0.7
Epoch 107, CIFAR-10 Batch 4:  Batch Loss - 0.022617660462856293; Batch Accuracy - 1.0
Valid Loss - 0.9564685225486755; Valid Accuracy - 0.71
Epoch 107, CIFAR-10 Batch 5:  Batch Loss - 0.0408274307847023; Batch Accuracy - 1.0
Valid Loss - 0.9453364014625549; Valid Accuracy - 0.71
Epoch 108, CIFAR-10 Batch 1:  Batch Loss - 0.03120250627398491; Batch Accuracy - 1.0
Valid Loss - 0.9639608263969421; Valid Accuracy - 0.7
Epoch 108, CIFAR-10 Batch 2:  Batch Loss - 0.0460088886320591; Batch Accuracy - 1.0
Valid Loss - 0.9997717142105103; Valid Accuracy - 0.69
Epoch 108, CIFAR-10 Batch 3:  Batch Loss - 0.061308715492486954; Batch Accuracy - 0.98
Valid Loss - 1.0582698583602905; Valid Accuracy - 0.68
Epoch 108, CIFAR-10 Batch 4:  Batch Loss - 0.02088024467229843; Batch Accuracy - 1.0
Valid Loss - 0.9891531467437744; Valid Accuracy - 0.7
Epoch 108, CIFAR-10 Batch 5:  Batch Loss - 0.03395865857601166; Batch Accuracy - 1.0
Valid Loss - 0.9570371508598328; Valid Accuracy - 0.71
Epoch 109, CIFAR-10 Batch 1:  Batch Loss - 0.03988880664110184; Batch Accuracy - 1.0
Valid Loss - 0.9902081489562988; Valid Accuracy - 0.69
Epoch 109, CIFAR-10 Batch 2:  Batch Loss - 0.03843086212873459; Batch Accuracy - 1.0
Valid Loss - 0.9666503667831421; Valid Accuracy - 0.7
Epoch 109, CIFAR-10 Batch 3:  Batch Loss - 0.0637441948056221; Batch Accuracy - 1.0
Valid Loss - 1.0531851053237915; Valid Accuracy - 0.68
Epoch 109, CIFAR-10 Batch 4:  Batch Loss - 0.018709108233451843; Batch Accuracy - 1.0
Valid Loss - 0.9806304574012756; Valid Accuracy - 0.7
Epoch 109, CIFAR-10 Batch 5:  Batch Loss - 0.043207116425037384; Batch Accuracy - 1.0
Valid Loss - 0.9731099009513855; Valid Accuracy - 0.7
Epoch 110, CIFAR-10 Batch 1:  Batch Loss - 0.03574729338288307; Batch Accuracy - 1.0
Valid Loss - 0.9816240072250366; Valid Accuracy - 0.71
Epoch 110, CIFAR-10 Batch 2:  Batch Loss - 0.028427371755242348; Batch Accuracy - 1.0
Valid Loss - 0.9657400846481323; Valid Accuracy - 0.7
Epoch 110, CIFAR-10 Batch 3:  Batch Loss - 0.044821202754974365; Batch Accuracy - 1.0
Valid Loss - 1.049508810043335; Valid Accuracy - 0.69
Epoch 110, CIFAR-10 Batch 4:  Batch Loss - 0.01882300153374672; Batch Accuracy - 1.0
Valid Loss - 0.998696506023407; Valid Accuracy - 0.7
Epoch 110, CIFAR-10 Batch 5:  Batch Loss - 0.02982308715581894; Batch Accuracy - 1.0
Valid Loss - 0.9756597280502319; Valid Accuracy - 0.7
Epoch 111, CIFAR-10 Batch 1:  Batch Loss - 0.03100164420902729; Batch Accuracy - 1.0
Valid Loss - 0.9880117774009705; Valid Accuracy - 0.71
Epoch 111, CIFAR-10 Batch 2:  Batch Loss - 0.028906267136335373; Batch Accuracy - 1.0
Valid Loss - 1.0049500465393066; Valid Accuracy - 0.69
Epoch 111, CIFAR-10 Batch 3:  Batch Loss - 0.05407017469406128; Batch Accuracy - 1.0
Valid Loss - 1.0897855758666992; Valid Accuracy - 0.68
Epoch 111, CIFAR-10 Batch 4:  Batch Loss - 0.022072836756706238; Batch Accuracy - 1.0
Valid Loss - 0.966381311416626; Valid Accuracy - 0.7
Epoch 111, CIFAR-10 Batch 5:  Batch Loss - 0.05565012991428375; Batch Accuracy - 1.0
Valid Loss - 0.9956366419792175; Valid Accuracy - 0.7
Epoch 112, CIFAR-10 Batch 1:  Batch Loss - 0.038820937275886536; Batch Accuracy - 1.0
Valid Loss - 0.9558413028717041; Valid Accuracy - 0.71
Epoch 112, CIFAR-10 Batch 2:  Batch Loss - 0.02937791496515274; Batch Accuracy - 1.0
Valid Loss - 1.0190924406051636; Valid Accuracy - 0.69
Epoch 112, CIFAR-10 Batch 3:  Batch Loss - 0.04056971147656441; Batch Accuracy - 1.0
Valid Loss - 1.022922396659851; Valid Accuracy - 0.69
Epoch 112, CIFAR-10 Batch 4:  Batch Loss - 0.02502858079969883; Batch Accuracy - 1.0
Valid Loss - 0.9529351592063904; Valid Accuracy - 0.71
Epoch 112, CIFAR-10 Batch 5:  Batch Loss - 0.031132224947214127; Batch Accuracy - 1.0
Valid Loss - 0.9723904728889465; Valid Accuracy - 0.71
Epoch 113, CIFAR-10 Batch 1:  Batch Loss - 0.04037148132920265; Batch Accuracy - 1.0
Valid Loss - 0.9774940013885498; Valid Accuracy - 0.71
Epoch 113, CIFAR-10 Batch 2:  Batch Loss - 0.027718430384993553; Batch Accuracy - 1.0
Valid Loss - 0.9977661371231079; Valid Accuracy - 0.69
Epoch 113, CIFAR-10 Batch 3:  Batch Loss - 0.04697299003601074; Batch Accuracy - 1.0
Valid Loss - 1.0863560438156128; Valid Accuracy - 0.68
Epoch 113, CIFAR-10 Batch 4:  Batch Loss - 0.013579959981143475; Batch Accuracy - 1.0
Valid Loss - 0.9977768063545227; Valid Accuracy - 0.7
Epoch 113, CIFAR-10 Batch 5:  Batch Loss - 0.03666180372238159; Batch Accuracy - 1.0
Valid Loss - 0.9678287506103516; Valid Accuracy - 0.71
Epoch 114, CIFAR-10 Batch 1:  Batch Loss - 0.0337342843413353; Batch Accuracy - 1.0
Valid Loss - 0.9811983704566956; Valid Accuracy - 0.71
Epoch 114, CIFAR-10 Batch 2:  Batch Loss - 0.028856739401817322; Batch Accuracy - 1.0
Valid Loss - 0.9737914800643921; Valid Accuracy - 0.7
Epoch 114, CIFAR-10 Batch 3:  Batch Loss - 0.058736272156238556; Batch Accuracy - 1.0
Valid Loss - 1.0419533252716064; Valid Accuracy - 0.69
Epoch 114, CIFAR-10 Batch 4:  Batch Loss - 0.018004732206463814; Batch Accuracy - 1.0
Valid Loss - 0.9649045467376709; Valid Accuracy - 0.7
Epoch 114, CIFAR-10 Batch 5:  Batch Loss - 0.03970561549067497; Batch Accuracy - 1.0
Valid Loss - 0.9916924834251404; Valid Accuracy - 0.7
Epoch 115, CIFAR-10 Batch 1:  Batch Loss - 0.03261265903711319; Batch Accuracy - 1.0
Valid Loss - 0.9609971046447754; Valid Accuracy - 0.71
Epoch 115, CIFAR-10 Batch 2:  Batch Loss - 0.03225555643439293; Batch Accuracy - 1.0
Valid Loss - 0.9688307046890259; Valid Accuracy - 0.7
Epoch 115, CIFAR-10 Batch 3:  Batch Loss - 0.04827302321791649; Batch Accuracy - 1.0
Valid Loss - 1.0886080265045166; Valid Accuracy - 0.68
Epoch 115, CIFAR-10 Batch 4:  Batch Loss - 0.023822838440537453; Batch Accuracy - 1.0
Valid Loss - 0.9539541602134705; Valid Accuracy - 0.71
Epoch 115, CIFAR-10 Batch 5:  Batch Loss - 0.04181670770049095; Batch Accuracy - 1.0
Valid Loss - 0.9335624575614929; Valid Accuracy - 0.71
Epoch 116, CIFAR-10 Batch 1:  Batch Loss - 0.026788977906107903; Batch Accuracy - 1.0
Valid Loss - 0.9716957807540894; Valid Accuracy - 0.71
Epoch 116, CIFAR-10 Batch 2:  Batch Loss - 0.022349819540977478; Batch Accuracy - 1.0
Valid Loss - 0.9549075961112976; Valid Accuracy - 0.71
Epoch 116, CIFAR-10 Batch 3:  Batch Loss - 0.0409756563603878; Batch Accuracy - 1.0
Valid Loss - 1.0692987442016602; Valid Accuracy - 0.69
Epoch 116, CIFAR-10 Batch 4:  Batch Loss - 0.01693001389503479; Batch Accuracy - 1.0
Valid Loss - 0.9692562818527222; Valid Accuracy - 0.71
Epoch 116, CIFAR-10 Batch 5:  Batch Loss - 0.03137613460421562; Batch Accuracy - 1.0
Valid Loss - 1.0027960538864136; Valid Accuracy - 0.71
Epoch 117, CIFAR-10 Batch 1:  Batch Loss - 0.04525446146726608; Batch Accuracy - 1.0
Valid Loss - 0.9735361337661743; Valid Accuracy - 0.7
Epoch 117, CIFAR-10 Batch 2:  Batch Loss - 0.019508901983499527; Batch Accuracy - 1.0
Valid Loss - 0.9540477395057678; Valid Accuracy - 0.71
Epoch 117, CIFAR-10 Batch 3:  Batch Loss - 0.025467686355113983; Batch Accuracy - 1.0
Valid Loss - 1.0249557495117188; Valid Accuracy - 0.7
Epoch 117, CIFAR-10 Batch 4:  Batch Loss - 0.01961350440979004; Batch Accuracy - 1.0
Valid Loss - 0.9548788070678711; Valid Accuracy - 0.71
Epoch 117, CIFAR-10 Batch 5:  Batch Loss - 0.041278887540102005; Batch Accuracy - 1.0
Valid Loss - 0.9741761088371277; Valid Accuracy - 0.71
Epoch 118, CIFAR-10 Batch 1:  Batch Loss - 0.04072049260139465; Batch Accuracy - 1.0
Valid Loss - 0.9852427840232849; Valid Accuracy - 0.71
Epoch 118, CIFAR-10 Batch 2:  Batch Loss - 0.030537765473127365; Batch Accuracy - 1.0
Valid Loss - 0.9650405645370483; Valid Accuracy - 0.7
Epoch 118, CIFAR-10 Batch 3:  Batch Loss - 0.04054154083132744; Batch Accuracy - 1.0
Valid Loss - 1.0530149936676025; Valid Accuracy - 0.69
Epoch 118, CIFAR-10 Batch 4:  Batch Loss - 0.01953798718750477; Batch Accuracy - 1.0
Valid Loss - 0.9684281349182129; Valid Accuracy - 0.71
Epoch 118, CIFAR-10 Batch 5:  Batch Loss - 0.03166739642620087; Batch Accuracy - 1.0
Valid Loss - 1.0055341720581055; Valid Accuracy - 0.7
Epoch 119, CIFAR-10 Batch 1:  Batch Loss - 0.04712427034974098; Batch Accuracy - 1.0
Valid Loss - 1.0242860317230225; Valid Accuracy - 0.7
Epoch 119, CIFAR-10 Batch 2:  Batch Loss - 0.030437789857387543; Batch Accuracy - 1.0
Valid Loss - 0.9701983332633972; Valid Accuracy - 0.7
Epoch 119, CIFAR-10 Batch 3:  Batch Loss - 0.03515903651714325; Batch Accuracy - 1.0
Valid Loss - 1.0108610391616821; Valid Accuracy - 0.7
Epoch 119, CIFAR-10 Batch 4:  Batch Loss - 0.023011622950434685; Batch Accuracy - 1.0
Valid Loss - 0.973654568195343; Valid Accuracy - 0.71
Epoch 119, CIFAR-10 Batch 5:  Batch Loss - 0.03530479967594147; Batch Accuracy - 1.0
Valid Loss - 0.9703085422515869; Valid Accuracy - 0.71
Epoch 120, CIFAR-10 Batch 1:  Batch Loss - 0.023404162377119064; Batch Accuracy - 1.0
Valid Loss - 0.9623640775680542; Valid Accuracy - 0.71
Epoch 120, CIFAR-10 Batch 2:  Batch Loss - 0.034427836537361145; Batch Accuracy - 1.0
Valid Loss - 0.9310862421989441; Valid Accuracy - 0.7
Epoch 120, CIFAR-10 Batch 3:  Batch Loss - 0.03120749443769455; Batch Accuracy - 1.0
Valid Loss - 1.02034592628479; Valid Accuracy - 0.69
Epoch 120, CIFAR-10 Batch 4:  Batch Loss - 0.025324495509266853; Batch Accuracy - 1.0
Valid Loss - 1.0236140489578247; Valid Accuracy - 0.7
Epoch 120, CIFAR-10 Batch 5:  Batch Loss - 0.03593304753303528; Batch Accuracy - 1.0
Valid Loss - 0.9752492904663086; Valid Accuracy - 0.7
Epoch 121, CIFAR-10 Batch 1:  Batch Loss - 0.03036305494606495; Batch Accuracy - 1.0
Valid Loss - 0.9638098478317261; Valid Accuracy - 0.71
Epoch 121, CIFAR-10 Batch 2:  Batch Loss - 0.029713224619627; Batch Accuracy - 1.0
Valid Loss - 0.9741768836975098; Valid Accuracy - 0.71
Epoch 121, CIFAR-10 Batch 3:  Batch Loss - 0.033680640161037445; Batch Accuracy - 1.0
Valid Loss - 0.9761250019073486; Valid Accuracy - 0.71
Epoch 121, CIFAR-10 Batch 4:  Batch Loss - 0.021975617855787277; Batch Accuracy - 1.0
Valid Loss - 0.9647356867790222; Valid Accuracy - 0.71
Epoch 121, CIFAR-10 Batch 5:  Batch Loss - 0.037797730416059494; Batch Accuracy - 1.0
Valid Loss - 0.9512481689453125; Valid Accuracy - 0.71
Epoch 122, CIFAR-10 Batch 1:  Batch Loss - 0.022151954472064972; Batch Accuracy - 1.0
Valid Loss - 0.9606556296348572; Valid Accuracy - 0.71
Epoch 122, CIFAR-10 Batch 2:  Batch Loss - 0.03519047796726227; Batch Accuracy - 1.0
Valid Loss - 0.9793791770935059; Valid Accuracy - 0.7
Epoch 122, CIFAR-10 Batch 3:  Batch Loss - 0.037567831575870514; Batch Accuracy - 1.0
Valid Loss - 1.0485972166061401; Valid Accuracy - 0.69
Epoch 122, CIFAR-10 Batch 4:  Batch Loss - 0.018769729882478714; Batch Accuracy - 1.0
Valid Loss - 0.9918715953826904; Valid Accuracy - 0.7
Epoch 122, CIFAR-10 Batch 5:  Batch Loss - 0.03488975763320923; Batch Accuracy - 1.0
Valid Loss - 1.0134276151657104; Valid Accuracy - 0.7
Epoch 123, CIFAR-10 Batch 1:  Batch Loss - 0.030404996126890182; Batch Accuracy - 1.0
Valid Loss - 0.9689691662788391; Valid Accuracy - 0.71
Epoch 123, CIFAR-10 Batch 2:  Batch Loss - 0.02905512973666191; Batch Accuracy - 1.0
Valid Loss - 0.9728439450263977; Valid Accuracy - 0.71
Epoch 123, CIFAR-10 Batch 3:  Batch Loss - 0.029800206422805786; Batch Accuracy - 1.0
Valid Loss - 0.9819839596748352; Valid Accuracy - 0.7
Epoch 123, CIFAR-10 Batch 4:  Batch Loss - 0.013736034743487835; Batch Accuracy - 1.0
Valid Loss - 0.9741885662078857; Valid Accuracy - 0.71
Epoch 123, CIFAR-10 Batch 5:  Batch Loss - 0.03646089881658554; Batch Accuracy - 1.0
Valid Loss - 0.972337007522583; Valid Accuracy - 0.71
Epoch 124, CIFAR-10 Batch 1:  Batch Loss - 0.021206842735409737; Batch Accuracy - 1.0
Valid Loss - 0.9710336923599243; Valid Accuracy - 0.72
Epoch 124, CIFAR-10 Batch 2:  Batch Loss - 0.02477366104722023; Batch Accuracy - 1.0
Valid Loss - 0.9847780466079712; Valid Accuracy - 0.7
Epoch 124, CIFAR-10 Batch 3:  Batch Loss - 0.01964316889643669; Batch Accuracy - 1.0
Valid Loss - 1.0244669914245605; Valid Accuracy - 0.7
Epoch 124, CIFAR-10 Batch 4:  Batch Loss - 0.007775796111673117; Batch Accuracy - 1.0
Valid Loss - 0.9550131559371948; Valid Accuracy - 0.71
Epoch 124, CIFAR-10 Batch 5:  Batch Loss - 0.03098706156015396; Batch Accuracy - 1.0
Valid Loss - 1.0211904048919678; Valid Accuracy - 0.7
Epoch 125, CIFAR-10 Batch 1:  Batch Loss - 0.03286482393741608; Batch Accuracy - 1.0
Valid Loss - 1.0142580270767212; Valid Accuracy - 0.7
Epoch 125, CIFAR-10 Batch 2:  Batch Loss - 0.026456953957676888; Batch Accuracy - 1.0
Valid Loss - 0.978873610496521; Valid Accuracy - 0.7
Epoch 125, CIFAR-10 Batch 3:  Batch Loss - 0.030422456562519073; Batch Accuracy - 1.0
Valid Loss - 1.0500396490097046; Valid Accuracy - 0.69
Epoch 125, CIFAR-10 Batch 4:  Batch Loss - 0.010718959383666515; Batch Accuracy - 1.0
Valid Loss - 0.9725472927093506; Valid Accuracy - 0.71
Epoch 125, CIFAR-10 Batch 5:  Batch Loss - 0.040249429643154144; Batch Accuracy - 1.0
Valid Loss - 1.0205169916152954; Valid Accuracy - 0.7
Epoch 126, CIFAR-10 Batch 1:  Batch Loss - 0.02397998794913292; Batch Accuracy - 1.0
Valid Loss - 0.9891464710235596; Valid Accuracy - 0.71
Epoch 126, CIFAR-10 Batch 2:  Batch Loss - 0.01976965367794037; Batch Accuracy - 1.0
Valid Loss - 0.9920006394386292; Valid Accuracy - 0.7
Epoch 126, CIFAR-10 Batch 3:  Batch Loss - 0.029917340725660324; Batch Accuracy - 1.0
Valid Loss - 1.0187718868255615; Valid Accuracy - 0.7
Epoch 126, CIFAR-10 Batch 4:  Batch Loss - 0.010987107641994953; Batch Accuracy - 1.0
Valid Loss - 0.9908425807952881; Valid Accuracy - 0.7
Epoch 126, CIFAR-10 Batch 5:  Batch Loss - 0.033521514385938644; Batch Accuracy - 1.0
Valid Loss - 0.9735974669456482; Valid Accuracy - 0.71
Epoch 127, CIFAR-10 Batch 1:  Batch Loss - 0.0310714989900589; Batch Accuracy - 1.0
Valid Loss - 1.006678819656372; Valid Accuracy - 0.71
Epoch 127, CIFAR-10 Batch 2:  Batch Loss - 0.03527260571718216; Batch Accuracy - 1.0
Valid Loss - 0.9875386953353882; Valid Accuracy - 0.69
Epoch 127, CIFAR-10 Batch 3:  Batch Loss - 0.029426399618387222; Batch Accuracy - 1.0
Valid Loss - 1.0350250005722046; Valid Accuracy - 0.7
Epoch 127, CIFAR-10 Batch 4:  Batch Loss - 0.008854798972606659; Batch Accuracy - 1.0
Valid Loss - 1.0029443502426147; Valid Accuracy - 0.71
Epoch 127, CIFAR-10 Batch 5:  Batch Loss - 0.03479229658842087; Batch Accuracy - 1.0
Valid Loss - 1.0204236507415771; Valid Accuracy - 0.7
Epoch 128, CIFAR-10 Batch 1:  Batch Loss - 0.016795597970485687; Batch Accuracy - 1.0
Valid Loss - 1.0183148384094238; Valid Accuracy - 0.7
Epoch 128, CIFAR-10 Batch 2:  Batch Loss - 0.026456590741872787; Batch Accuracy - 1.0
Valid Loss - 1.007889986038208; Valid Accuracy - 0.69
Epoch 128, CIFAR-10 Batch 3:  Batch Loss - 0.028361793607473373; Batch Accuracy - 1.0
Valid Loss - 1.0052671432495117; Valid Accuracy - 0.7
Epoch 128, CIFAR-10 Batch 4:  Batch Loss - 0.00959761068224907; Batch Accuracy - 1.0
Valid Loss - 0.9829617738723755; Valid Accuracy - 0.7
Epoch 128, CIFAR-10 Batch 5:  Batch Loss - 0.04658108949661255; Batch Accuracy - 1.0
Valid Loss - 0.9982012510299683; Valid Accuracy - 0.7
Epoch 129, CIFAR-10 Batch 1:  Batch Loss - 0.01604597084224224; Batch Accuracy - 1.0
Valid Loss - 0.9972573518753052; Valid Accuracy - 0.7
Epoch 129, CIFAR-10 Batch 2:  Batch Loss - 0.024240601807832718; Batch Accuracy - 1.0
Valid Loss - 1.0183340311050415; Valid Accuracy - 0.69
Epoch 129, CIFAR-10 Batch 3:  Batch Loss - 0.019047189503908157; Batch Accuracy - 1.0
Valid Loss - 1.0238088369369507; Valid Accuracy - 0.7
Epoch 129, CIFAR-10 Batch 4:  Batch Loss - 0.009830540046095848; Batch Accuracy - 1.0
Valid Loss - 1.0052485466003418; Valid Accuracy - 0.71
Epoch 129, CIFAR-10 Batch 5:  Batch Loss - 0.02949388325214386; Batch Accuracy - 1.0
Valid Loss - 0.9942358136177063; Valid Accuracy - 0.71
Epoch 130, CIFAR-10 Batch 1:  Batch Loss - 0.023195896297693253; Batch Accuracy - 1.0
Valid Loss - 0.9950963258743286; Valid Accuracy - 0.7
Epoch 130, CIFAR-10 Batch 2:  Batch Loss - 0.02022217959165573; Batch Accuracy - 1.0
Valid Loss - 0.9941847324371338; Valid Accuracy - 0.7
Epoch 130, CIFAR-10 Batch 3:  Batch Loss - 0.02501470223069191; Batch Accuracy - 1.0
Valid Loss - 1.0135027170181274; Valid Accuracy - 0.69
Epoch 130, CIFAR-10 Batch 4:  Batch Loss - 0.009838464669883251; Batch Accuracy - 1.0
Valid Loss - 1.0111987590789795; Valid Accuracy - 0.7
Epoch 130, CIFAR-10 Batch 5:  Batch Loss - 0.02403687685728073; Batch Accuracy - 1.0
Valid Loss - 0.9937505125999451; Valid Accuracy - 0.71
Epoch 131, CIFAR-10 Batch 1:  Batch Loss - 0.018323780968785286; Batch Accuracy - 1.0
Valid Loss - 0.9947428703308105; Valid Accuracy - 0.71
Epoch 131, CIFAR-10 Batch 2:  Batch Loss - 0.029895124956965446; Batch Accuracy - 1.0
Valid Loss - 0.9903492331504822; Valid Accuracy - 0.7
Epoch 131, CIFAR-10 Batch 3:  Batch Loss - 0.02586071565747261; Batch Accuracy - 1.0
Valid Loss - 1.0408811569213867; Valid Accuracy - 0.69
Epoch 131, CIFAR-10 Batch 4:  Batch Loss - 0.012646938674151897; Batch Accuracy - 1.0
Valid Loss - 0.9977312088012695; Valid Accuracy - 0.71
Epoch 131, CIFAR-10 Batch 5:  Batch Loss - 0.024244356900453568; Batch Accuracy - 1.0
Valid Loss - 0.9881631135940552; Valid Accuracy - 0.71
Epoch 132, CIFAR-10 Batch 1:  Batch Loss - 0.016546504572033882; Batch Accuracy - 1.0
Valid Loss - 0.9947157502174377; Valid Accuracy - 0.71
Epoch 132, CIFAR-10 Batch 2:  Batch Loss - 0.024029256775975227; Batch Accuracy - 1.0
Valid Loss - 0.977726936340332; Valid Accuracy - 0.7
Epoch 132, CIFAR-10 Batch 3:  Batch Loss - 0.019427862018346786; Batch Accuracy - 1.0
Valid Loss - 1.050367832183838; Valid Accuracy - 0.7
Epoch 132, CIFAR-10 Batch 4:  Batch Loss - 0.01726171188056469; Batch Accuracy - 1.0
Valid Loss - 1.013121247291565; Valid Accuracy - 0.7
Epoch 132, CIFAR-10 Batch 5:  Batch Loss - 0.024393510073423386; Batch Accuracy - 1.0
Valid Loss - 1.013452172279358; Valid Accuracy - 0.7
Epoch 133, CIFAR-10 Batch 1:  Batch Loss - 0.015541662462055683; Batch Accuracy - 1.0
Valid Loss - 0.9914776682853699; Valid Accuracy - 0.71
Epoch 133, CIFAR-10 Batch 2:  Batch Loss - 0.03361847996711731; Batch Accuracy - 1.0
Valid Loss - 1.0179550647735596; Valid Accuracy - 0.7
Epoch 133, CIFAR-10 Batch 3:  Batch Loss - 0.030200514942407608; Batch Accuracy - 1.0
Valid Loss - 1.102837085723877; Valid Accuracy - 0.68
Epoch 133, CIFAR-10 Batch 4:  Batch Loss - 0.02125835232436657; Batch Accuracy - 1.0
Valid Loss - 1.0269731283187866; Valid Accuracy - 0.7
Epoch 133, CIFAR-10 Batch 5:  Batch Loss - 0.018769539892673492; Batch Accuracy - 1.0
Valid Loss - 1.0065741539001465; Valid Accuracy - 0.7
Epoch 134, CIFAR-10 Batch 1:  Batch Loss - 0.014046252705156803; Batch Accuracy - 1.0
Valid Loss - 1.0102005004882812; Valid Accuracy - 0.71
Epoch 134, CIFAR-10 Batch 2:  Batch Loss - 0.02185293659567833; Batch Accuracy - 1.0
Valid Loss - 1.003927230834961; Valid Accuracy - 0.7
Epoch 134, CIFAR-10 Batch 3:  Batch Loss - 0.02671791985630989; Batch Accuracy - 1.0
Valid Loss - 1.0325734615325928; Valid Accuracy - 0.7
Epoch 134, CIFAR-10 Batch 4:  Batch Loss - 0.011312724091112614; Batch Accuracy - 1.0
Valid Loss - 1.0133144855499268; Valid Accuracy - 0.71
Epoch 134, CIFAR-10 Batch 5:  Batch Loss - 0.027615249156951904; Batch Accuracy - 1.0
Valid Loss - 1.0215495824813843; Valid Accuracy - 0.7
Epoch 135, CIFAR-10 Batch 1:  Batch Loss - 0.0139676034450531; Batch Accuracy - 1.0
Valid Loss - 1.020076870918274; Valid Accuracy - 0.71
Epoch 135, CIFAR-10 Batch 2:  Batch Loss - 0.01594601199030876; Batch Accuracy - 1.0
Valid Loss - 1.0060232877731323; Valid Accuracy - 0.7
Epoch 135, CIFAR-10 Batch 3:  Batch Loss - 0.02015867829322815; Batch Accuracy - 1.0
Valid Loss - 1.0921427011489868; Valid Accuracy - 0.69
Epoch 135, CIFAR-10 Batch 4:  Batch Loss - 0.01017659343779087; Batch Accuracy - 1.0
Valid Loss - 0.9927114844322205; Valid Accuracy - 0.71
Epoch 135, CIFAR-10 Batch 5:  Batch Loss - 0.024080293253064156; Batch Accuracy - 1.0
Valid Loss - 1.019608736038208; Valid Accuracy - 0.7
Epoch 136, CIFAR-10 Batch 1:  Batch Loss - 0.02031649649143219; Batch Accuracy - 1.0
Valid Loss - 0.9602998495101929; Valid Accuracy - 0.71
Epoch 136, CIFAR-10 Batch 2:  Batch Loss - 0.018617434427142143; Batch Accuracy - 1.0
Valid Loss - 0.9977823495864868; Valid Accuracy - 0.7
Epoch 136, CIFAR-10 Batch 3:  Batch Loss - 0.01502247154712677; Batch Accuracy - 1.0
Valid Loss - 1.0503708124160767; Valid Accuracy - 0.7
Epoch 136, CIFAR-10 Batch 4:  Batch Loss - 0.011120414361357689; Batch Accuracy - 1.0
Valid Loss - 0.9868096113204956; Valid Accuracy - 0.7
Epoch 136, CIFAR-10 Batch 5:  Batch Loss - 0.025371119379997253; Batch Accuracy - 1.0
Valid Loss - 1.022610068321228; Valid Accuracy - 0.7
Epoch 137, CIFAR-10 Batch 1:  Batch Loss - 0.022837411612272263; Batch Accuracy - 1.0
Valid Loss - 1.005043387413025; Valid Accuracy - 0.7
Epoch 137, CIFAR-10 Batch 2:  Batch Loss - 0.02075939252972603; Batch Accuracy - 1.0
Valid Loss - 0.9709460735321045; Valid Accuracy - 0.7
Epoch 137, CIFAR-10 Batch 3:  Batch Loss - 0.016767673194408417; Batch Accuracy - 1.0
Valid Loss - 1.0481584072113037; Valid Accuracy - 0.69
Epoch 137, CIFAR-10 Batch 4:  Batch Loss - 0.00933302566409111; Batch Accuracy - 1.0
Valid Loss - 1.0137033462524414; Valid Accuracy - 0.7
Epoch 137, CIFAR-10 Batch 5:  Batch Loss - 0.020880497992038727; Batch Accuracy - 1.0
Valid Loss - 0.9878359436988831; Valid Accuracy - 0.71
Epoch 138, CIFAR-10 Batch 1:  Batch Loss - 0.022549157962203026; Batch Accuracy - 1.0
Valid Loss - 0.980965793132782; Valid Accuracy - 0.71
Epoch 138, CIFAR-10 Batch 2:  Batch Loss - 0.029172129929065704; Batch Accuracy - 1.0
Valid Loss - 0.9905653595924377; Valid Accuracy - 0.7
Epoch 138, CIFAR-10 Batch 3:  Batch Loss - 0.01878373697400093; Batch Accuracy - 1.0
Valid Loss - 1.0255868434906006; Valid Accuracy - 0.69
Epoch 138, CIFAR-10 Batch 4:  Batch Loss - 0.01458769105374813; Batch Accuracy - 1.0
Valid Loss - 1.0058960914611816; Valid Accuracy - 0.71
Epoch 138, CIFAR-10 Batch 5:  Batch Loss - 0.034647054970264435; Batch Accuracy - 1.0
Valid Loss - 1.0305423736572266; Valid Accuracy - 0.7
Epoch 139, CIFAR-10 Batch 1:  Batch Loss - 0.01408989354968071; Batch Accuracy - 1.0
Valid Loss - 1.0042341947555542; Valid Accuracy - 0.71
Epoch 139, CIFAR-10 Batch 2:  Batch Loss - 0.021564051508903503; Batch Accuracy - 1.0
Valid Loss - 0.9996854066848755; Valid Accuracy - 0.7
Epoch 139, CIFAR-10 Batch 3:  Batch Loss - 0.024778254330158234; Batch Accuracy - 1.0
Valid Loss - 1.075394630432129; Valid Accuracy - 0.7
Epoch 139, CIFAR-10 Batch 4:  Batch Loss - 0.007838284596800804; Batch Accuracy - 1.0
Valid Loss - 0.9953057765960693; Valid Accuracy - 0.71
Epoch 139, CIFAR-10 Batch 5:  Batch Loss - 0.03449918329715729; Batch Accuracy - 1.0
Valid Loss - 1.0239880084991455; Valid Accuracy - 0.7
Epoch 140, CIFAR-10 Batch 1:  Batch Loss - 0.02065127342939377; Batch Accuracy - 1.0
Valid Loss - 1.028639793395996; Valid Accuracy - 0.71
Epoch 140, CIFAR-10 Batch 2:  Batch Loss - 0.018476158380508423; Batch Accuracy - 1.0
Valid Loss - 1.0066440105438232; Valid Accuracy - 0.7
Epoch 140, CIFAR-10 Batch 3:  Batch Loss - 0.030907107517123222; Batch Accuracy - 1.0
Valid Loss - 1.0624123811721802; Valid Accuracy - 0.69
Epoch 140, CIFAR-10 Batch 4:  Batch Loss - 0.011893589049577713; Batch Accuracy - 1.0
Valid Loss - 1.0317373275756836; Valid Accuracy - 0.7
Epoch 140, CIFAR-10 Batch 5:  Batch Loss - 0.03524404391646385; Batch Accuracy - 1.0
Valid Loss - 1.0063236951828003; Valid Accuracy - 0.7
Epoch 141, CIFAR-10 Batch 1:  Batch Loss - 0.011024915613234043; Batch Accuracy - 1.0
Valid Loss - 1.009486436843872; Valid Accuracy - 0.72
Epoch 141, CIFAR-10 Batch 2:  Batch Loss - 0.02685503289103508; Batch Accuracy - 1.0
Valid Loss - 1.020344614982605; Valid Accuracy - 0.7
Epoch 141, CIFAR-10 Batch 3:  Batch Loss - 0.018262241035699844; Batch Accuracy - 1.0
Valid Loss - 1.0427128076553345; Valid Accuracy - 0.7
Epoch 141, CIFAR-10 Batch 4:  Batch Loss - 0.05428439751267433; Batch Accuracy - 0.98
Valid Loss - 1.06203031539917; Valid Accuracy - 0.69
Epoch 141, CIFAR-10 Batch 5:  Batch Loss - 0.02524847909808159; Batch Accuracy - 1.0
Valid Loss - 1.0220673084259033; Valid Accuracy - 0.7
Epoch 142, CIFAR-10 Batch 1:  Batch Loss - 0.01491149328649044; Batch Accuracy - 1.0
Valid Loss - 1.017110824584961; Valid Accuracy - 0.71
Epoch 142, CIFAR-10 Batch 2:  Batch Loss - 0.01895179972052574; Batch Accuracy - 1.0
Valid Loss - 0.9835690855979919; Valid Accuracy - 0.71
Epoch 142, CIFAR-10 Batch 3:  Batch Loss - 0.01767623983323574; Batch Accuracy - 1.0
Valid Loss - 1.0886650085449219; Valid Accuracy - 0.7
Epoch 142, CIFAR-10 Batch 4:  Batch Loss - 0.009608610533177853; Batch Accuracy - 1.0
Valid Loss - 1.0311145782470703; Valid Accuracy - 0.7
Epoch 142, CIFAR-10 Batch 5:  Batch Loss - 0.022590940818190575; Batch Accuracy - 1.0
Valid Loss - 1.0287195444107056; Valid Accuracy - 0.71
Epoch 143, CIFAR-10 Batch 1:  Batch Loss - 0.020021483302116394; Batch Accuracy - 1.0
Valid Loss - 1.0194437503814697; Valid Accuracy - 0.71
Epoch 143, CIFAR-10 Batch 2:  Batch Loss - 0.018814418464899063; Batch Accuracy - 1.0
Valid Loss - 0.9766502380371094; Valid Accuracy - 0.7
Epoch 143, CIFAR-10 Batch 3:  Batch Loss - 0.01693843863904476; Batch Accuracy - 1.0
Valid Loss - 1.0579389333724976; Valid Accuracy - 0.7
Epoch 143, CIFAR-10 Batch 4:  Batch Loss - 0.011299221776425838; Batch Accuracy - 1.0
Valid Loss - 1.0296452045440674; Valid Accuracy - 0.71
Epoch 143, CIFAR-10 Batch 5:  Batch Loss - 0.03315545991063118; Batch Accuracy - 1.0
Valid Loss - 0.9956412315368652; Valid Accuracy - 0.71
Epoch 144, CIFAR-10 Batch 1:  Batch Loss - 0.017712773755192757; Batch Accuracy - 1.0
Valid Loss - 1.0056263208389282; Valid Accuracy - 0.71
Epoch 144, CIFAR-10 Batch 2:  Batch Loss - 0.01485869474709034; Batch Accuracy - 1.0
Valid Loss - 1.014488697052002; Valid Accuracy - 0.7
Epoch 144, CIFAR-10 Batch 3:  Batch Loss - 0.018420075997710228; Batch Accuracy - 1.0
Valid Loss - 1.031869649887085; Valid Accuracy - 0.71
Epoch 144, CIFAR-10 Batch 4:  Batch Loss - 0.010061720386147499; Batch Accuracy - 1.0
Valid Loss - 1.0328614711761475; Valid Accuracy - 0.7
Epoch 144, CIFAR-10 Batch 5:  Batch Loss - 0.025915903970599174; Batch Accuracy - 1.0
Valid Loss - 1.0003516674041748; Valid Accuracy - 0.71
Epoch 145, CIFAR-10 Batch 1:  Batch Loss - 0.020173002034425735; Batch Accuracy - 1.0
Valid Loss - 0.9699192643165588; Valid Accuracy - 0.72
Epoch 145, CIFAR-10 Batch 2:  Batch Loss - 0.013668620027601719; Batch Accuracy - 1.0
Valid Loss - 0.9968786239624023; Valid Accuracy - 0.7
Epoch 145, CIFAR-10 Batch 3:  Batch Loss - 0.017260044813156128; Batch Accuracy - 1.0
Valid Loss - 1.0876739025115967; Valid Accuracy - 0.69
Epoch 145, CIFAR-10 Batch 4:  Batch Loss - 0.009227120317518711; Batch Accuracy - 1.0
Valid Loss - 1.0052076578140259; Valid Accuracy - 0.71
Epoch 145, CIFAR-10 Batch 5:  Batch Loss - 0.0311468206346035; Batch Accuracy - 1.0
Valid Loss - 0.9940890669822693; Valid Accuracy - 0.71
Epoch 146, CIFAR-10 Batch 1:  Batch Loss - 0.015409796498715878; Batch Accuracy - 1.0
Valid Loss - 1.0180891752243042; Valid Accuracy - 0.71
Epoch 146, CIFAR-10 Batch 2:  Batch Loss - 0.021133456379175186; Batch Accuracy - 1.0
Valid Loss - 1.0170174837112427; Valid Accuracy - 0.69
Epoch 146, CIFAR-10 Batch 3:  Batch Loss - 0.012938803061842918; Batch Accuracy - 1.0
Valid Loss - 1.0394266843795776; Valid Accuracy - 0.7
Epoch 146, CIFAR-10 Batch 4:  Batch Loss - 0.010957477614283562; Batch Accuracy - 1.0
Valid Loss - 1.038803219795227; Valid Accuracy - 0.71
Epoch 146, CIFAR-10 Batch 5:  Batch Loss - 0.01599658466875553; Batch Accuracy - 1.0
Valid Loss - 1.0023096799850464; Valid Accuracy - 0.7
Epoch 147, CIFAR-10 Batch 1:  Batch Loss - 0.012409154325723648; Batch Accuracy - 1.0
Valid Loss - 1.0318832397460938; Valid Accuracy - 0.7
Epoch 147, CIFAR-10 Batch 2:  Batch Loss - 0.018033023923635483; Batch Accuracy - 1.0
Valid Loss - 1.013204574584961; Valid Accuracy - 0.7
Epoch 147, CIFAR-10 Batch 3:  Batch Loss - 0.015981029719114304; Batch Accuracy - 1.0
Valid Loss - 1.0291589498519897; Valid Accuracy - 0.7
Epoch 147, CIFAR-10 Batch 4:  Batch Loss - 0.007858991622924805; Batch Accuracy - 1.0
Valid Loss - 1.0098044872283936; Valid Accuracy - 0.71
Epoch 147, CIFAR-10 Batch 5:  Batch Loss - 0.021501054987311363; Batch Accuracy - 1.0
Valid Loss - 1.0255053043365479; Valid Accuracy - 0.71
Epoch 148, CIFAR-10 Batch 1:  Batch Loss - 0.012393712066113949; Batch Accuracy - 1.0
Valid Loss - 1.006880283355713; Valid Accuracy - 0.71
Epoch 148, CIFAR-10 Batch 2:  Batch Loss - 0.024904638528823853; Batch Accuracy - 1.0
Valid Loss - 1.0275062322616577; Valid Accuracy - 0.69
Epoch 148, CIFAR-10 Batch 3:  Batch Loss - 0.015599489212036133; Batch Accuracy - 1.0
Valid Loss - 1.0843393802642822; Valid Accuracy - 0.7
Epoch 148, CIFAR-10 Batch 4:  Batch Loss - 0.013923637568950653; Batch Accuracy - 1.0
Valid Loss - 1.0139055252075195; Valid Accuracy - 0.71
Epoch 148, CIFAR-10 Batch 5:  Batch Loss - 0.0211979728192091; Batch Accuracy - 1.0
Valid Loss - 1.0283162593841553; Valid Accuracy - 0.7
Epoch 149, CIFAR-10 Batch 1:  Batch Loss - 0.01534472219645977; Batch Accuracy - 1.0
Valid Loss - 1.0010275840759277; Valid Accuracy - 0.71
Epoch 149, CIFAR-10 Batch 2:  Batch Loss - 0.019926192238926888; Batch Accuracy - 1.0
Valid Loss - 0.9984308481216431; Valid Accuracy - 0.71
Epoch 149, CIFAR-10 Batch 3:  Batch Loss - 0.015361151657998562; Batch Accuracy - 1.0
Valid Loss - 1.0291881561279297; Valid Accuracy - 0.7
Epoch 149, CIFAR-10 Batch 4:  Batch Loss - 0.00944798719137907; Batch Accuracy - 1.0
Valid Loss - 0.9995309114456177; Valid Accuracy - 0.71
Epoch 149, CIFAR-10 Batch 5:  Batch Loss - 0.020399682223796844; Batch Accuracy - 1.0
Valid Loss - 1.0121524333953857; Valid Accuracy - 0.71
Epoch 150, CIFAR-10 Batch 1:  Batch Loss - 0.012175919488072395; Batch Accuracy - 1.0
Valid Loss - 1.008194088935852; Valid Accuracy - 0.71
Epoch 150, CIFAR-10 Batch 2:  Batch Loss - 0.020111896097660065; Batch Accuracy - 1.0
Valid Loss - 0.9958882331848145; Valid Accuracy - 0.71
Epoch 150, CIFAR-10 Batch 3:  Batch Loss - 0.018248513340950012; Batch Accuracy - 1.0
Valid Loss - 1.0936555862426758; Valid Accuracy - 0.69
Epoch 150, CIFAR-10 Batch 4:  Batch Loss - 0.007701716385781765; Batch Accuracy - 1.0
Valid Loss - 1.0170762538909912; Valid Accuracy - 0.71
Epoch 150, CIFAR-10 Batch 5:  Batch Loss - 0.01982969045639038; Batch Accuracy - 1.0
Valid Loss - 1.0116350650787354; Valid Accuracy - 0.7
Epoch 151, CIFAR-10 Batch 1:  Batch Loss - 0.01632378064095974; Batch Accuracy - 1.0
Valid Loss - 0.9712739586830139; Valid Accuracy - 0.72
Epoch 151, CIFAR-10 Batch 2:  Batch Loss - 0.016399729996919632; Batch Accuracy - 1.0
Valid Loss - 0.9978713393211365; Valid Accuracy - 0.71
Epoch 151, CIFAR-10 Batch 3:  Batch Loss - 0.008435720577836037; Batch Accuracy - 1.0
Valid Loss - 1.029237985610962; Valid Accuracy - 0.7
Epoch 151, CIFAR-10 Batch 4:  Batch Loss - 0.010659885592758656; Batch Accuracy - 1.0
Valid Loss - 1.0266366004943848; Valid Accuracy - 0.71
Epoch 151, CIFAR-10 Batch 5:  Batch Loss - 0.01674947701394558; Batch Accuracy - 1.0
Valid Loss - 0.9998582005500793; Valid Accuracy - 0.71
Epoch 152, CIFAR-10 Batch 1:  Batch Loss - 0.013671902008354664; Batch Accuracy - 1.0
Valid Loss - 1.0343726873397827; Valid Accuracy - 0.71
Epoch 152, CIFAR-10 Batch 2:  Batch Loss - 0.01719510182738304; Batch Accuracy - 1.0
Valid Loss - 1.0153155326843262; Valid Accuracy - 0.7
Epoch 152, CIFAR-10 Batch 3:  Batch Loss - 0.010863367468118668; Batch Accuracy - 1.0
Valid Loss - 1.0557626485824585; Valid Accuracy - 0.7
Epoch 152, CIFAR-10 Batch 4:  Batch Loss - 0.008798607625067234; Batch Accuracy - 1.0
Valid Loss - 1.006692886352539; Valid Accuracy - 0.7
Epoch 152, CIFAR-10 Batch 5:  Batch Loss - 0.012982118874788284; Batch Accuracy - 1.0
Valid Loss - 0.9816714525222778; Valid Accuracy - 0.72
Epoch 153, CIFAR-10 Batch 1:  Batch Loss - 0.018509913235902786; Batch Accuracy - 1.0
Valid Loss - 1.0065563917160034; Valid Accuracy - 0.71
Epoch 153, CIFAR-10 Batch 2:  Batch Loss - 0.013290532864630222; Batch Accuracy - 1.0
Valid Loss - 1.0098613500595093; Valid Accuracy - 0.71
Epoch 153, CIFAR-10 Batch 3:  Batch Loss - 0.013341443613171577; Batch Accuracy - 1.0
Valid Loss - 1.0504322052001953; Valid Accuracy - 0.7
Epoch 153, CIFAR-10 Batch 4:  Batch Loss - 0.008822130039334297; Batch Accuracy - 1.0
Valid Loss - 1.0037013292312622; Valid Accuracy - 0.71
Epoch 153, CIFAR-10 Batch 5:  Batch Loss - 0.011451554484665394; Batch Accuracy - 1.0
Valid Loss - 0.9749906659126282; Valid Accuracy - 0.72
Epoch 154, CIFAR-10 Batch 1:  Batch Loss - 0.018854640424251556; Batch Accuracy - 1.0
Valid Loss - 0.996630847454071; Valid Accuracy - 0.71
Epoch 154, CIFAR-10 Batch 2:  Batch Loss - 0.017667921259999275; Batch Accuracy - 1.0
Valid Loss - 0.9955008625984192; Valid Accuracy - 0.7
Epoch 154, CIFAR-10 Batch 3:  Batch Loss - 0.010488048195838928; Batch Accuracy - 1.0
Valid Loss - 1.0703425407409668; Valid Accuracy - 0.69
Epoch 154, CIFAR-10 Batch 4:  Batch Loss - 0.010802410542964935; Batch Accuracy - 1.0
Valid Loss - 1.009451985359192; Valid Accuracy - 0.71
Epoch 154, CIFAR-10 Batch 5:  Batch Loss - 0.014140943996608257; Batch Accuracy - 1.0
Valid Loss - 0.9840999245643616; Valid Accuracy - 0.71
Epoch 155, CIFAR-10 Batch 1:  Batch Loss - 0.018607288599014282; Batch Accuracy - 1.0
Valid Loss - 0.9941855072975159; Valid Accuracy - 0.71
Epoch 155, CIFAR-10 Batch 2:  Batch Loss - 0.014828763902187347; Batch Accuracy - 1.0
Valid Loss - 0.9976804852485657; Valid Accuracy - 0.7
Epoch 155, CIFAR-10 Batch 3:  Batch Loss - 0.0144316041842103; Batch Accuracy - 1.0
Valid Loss - 1.0377202033996582; Valid Accuracy - 0.7
Epoch 155, CIFAR-10 Batch 4:  Batch Loss - 0.009698423556983471; Batch Accuracy - 1.0
Valid Loss - 1.0352873802185059; Valid Accuracy - 0.71
Epoch 155, CIFAR-10 Batch 5:  Batch Loss - 0.01866960898041725; Batch Accuracy - 1.0
Valid Loss - 1.0000395774841309; Valid Accuracy - 0.71
Epoch 156, CIFAR-10 Batch 1:  Batch Loss - 0.027299147099256516; Batch Accuracy - 1.0
Valid Loss - 1.0338748693466187; Valid Accuracy - 0.71
Epoch 156, CIFAR-10 Batch 2:  Batch Loss - 0.01134168915450573; Batch Accuracy - 1.0
Valid Loss - 1.0395116806030273; Valid Accuracy - 0.7
Epoch 156, CIFAR-10 Batch 3:  Batch Loss - 0.021896827965974808; Batch Accuracy - 1.0
Valid Loss - 1.1179301738739014; Valid Accuracy - 0.68
Epoch 156, CIFAR-10 Batch 4:  Batch Loss - 0.007627604529261589; Batch Accuracy - 1.0
Valid Loss - 1.0398612022399902; Valid Accuracy - 0.7
Epoch 156, CIFAR-10 Batch 5:  Batch Loss - 0.022473592311143875; Batch Accuracy - 1.0
Valid Loss - 1.0141804218292236; Valid Accuracy - 0.71
Epoch 157, CIFAR-10 Batch 1:  Batch Loss - 0.01264879759401083; Batch Accuracy - 1.0
Valid Loss - 1.0481963157653809; Valid Accuracy - 0.71
Epoch 157, CIFAR-10 Batch 2:  Batch Loss - 0.02276020310819149; Batch Accuracy - 1.0
Valid Loss - 1.0204631090164185; Valid Accuracy - 0.7
Epoch 157, CIFAR-10 Batch 3:  Batch Loss - 0.018155770376324654; Batch Accuracy - 1.0
Valid Loss - 1.0225995779037476; Valid Accuracy - 0.7
Epoch 157, CIFAR-10 Batch 4:  Batch Loss - 0.004301200620830059; Batch Accuracy - 1.0
Valid Loss - 1.0588041543960571; Valid Accuracy - 0.71
Epoch 157, CIFAR-10 Batch 5:  Batch Loss - 0.016833756119012833; Batch Accuracy - 1.0
Valid Loss - 1.01133131980896; Valid Accuracy - 0.71
Epoch 158, CIFAR-10 Batch 1:  Batch Loss - 0.011272625997662544; Batch Accuracy - 1.0
Valid Loss - 1.0122524499893188; Valid Accuracy - 0.71
Epoch 158, CIFAR-10 Batch 2:  Batch Loss - 0.01232429314404726; Batch Accuracy - 1.0
Valid Loss - 1.020362377166748; Valid Accuracy - 0.71
Epoch 158, CIFAR-10 Batch 3:  Batch Loss - 0.02170107141137123; Batch Accuracy - 1.0
Valid Loss - 1.0703524351119995; Valid Accuracy - 0.69
Epoch 158, CIFAR-10 Batch 4:  Batch Loss - 0.00659500528126955; Batch Accuracy - 1.0
Valid Loss - 1.034343957901001; Valid Accuracy - 0.71
Epoch 158, CIFAR-10 Batch 5:  Batch Loss - 0.014131705276668072; Batch Accuracy - 1.0
Valid Loss - 1.0233932733535767; Valid Accuracy - 0.71
Epoch 159, CIFAR-10 Batch 1:  Batch Loss - 0.00806756503880024; Batch Accuracy - 1.0
Valid Loss - 1.0270179510116577; Valid Accuracy - 0.71
Epoch 159, CIFAR-10 Batch 2:  Batch Loss - 0.02209092304110527; Batch Accuracy - 1.0
Valid Loss - 1.0085499286651611; Valid Accuracy - 0.71
Epoch 159, CIFAR-10 Batch 3:  Batch Loss - 0.015669938176870346; Batch Accuracy - 1.0
Valid Loss - 1.070515751838684; Valid Accuracy - 0.7
Epoch 159, CIFAR-10 Batch 4:  Batch Loss - 0.014543178491294384; Batch Accuracy - 1.0
Valid Loss - 1.058881163597107; Valid Accuracy - 0.7
Epoch 159, CIFAR-10 Batch 5:  Batch Loss - 0.01685023307800293; Batch Accuracy - 1.0
Valid Loss - 1.022861123085022; Valid Accuracy - 0.71
Epoch 160, CIFAR-10 Batch 1:  Batch Loss - 0.012558858841657639; Batch Accuracy - 1.0
Valid Loss - 1.019214391708374; Valid Accuracy - 0.71
Epoch 160, CIFAR-10 Batch 2:  Batch Loss - 0.010449673980474472; Batch Accuracy - 1.0
Valid Loss - 1.0081225633621216; Valid Accuracy - 0.71
Epoch 160, CIFAR-10 Batch 3:  Batch Loss - 0.012960363179445267; Batch Accuracy - 1.0
Valid Loss - 1.0688079595565796; Valid Accuracy - 0.7
Epoch 160, CIFAR-10 Batch 4:  Batch Loss - 0.010306483134627342; Batch Accuracy - 1.0
Valid Loss - 1.0697754621505737; Valid Accuracy - 0.7
Epoch 160, CIFAR-10 Batch 5:  Batch Loss - 0.01582738757133484; Batch Accuracy - 1.0
Valid Loss - 1.0215727090835571; Valid Accuracy - 0.71
Epoch 161, CIFAR-10 Batch 1:  Batch Loss - 0.013278558850288391; Batch Accuracy - 1.0
Valid Loss - 1.046567440032959; Valid Accuracy - 0.71
Epoch 161, CIFAR-10 Batch 2:  Batch Loss - 0.012131854891777039; Batch Accuracy - 1.0
Valid Loss - 1.0093328952789307; Valid Accuracy - 0.7
Epoch 161, CIFAR-10 Batch 3:  Batch Loss - 0.00940394215285778; Batch Accuracy - 1.0
Valid Loss - 1.0530736446380615; Valid Accuracy - 0.71
Epoch 161, CIFAR-10 Batch 4:  Batch Loss - 0.00580943189561367; Batch Accuracy - 1.0
Valid Loss - 1.0359340906143188; Valid Accuracy - 0.71
Epoch 161, CIFAR-10 Batch 5:  Batch Loss - 0.018077179789543152; Batch Accuracy - 1.0
Valid Loss - 1.0164636373519897; Valid Accuracy - 0.71
Epoch 162, CIFAR-10 Batch 1:  Batch Loss - 0.01125682145357132; Batch Accuracy - 1.0
Valid Loss - 1.0093053579330444; Valid Accuracy - 0.71
Epoch 162, CIFAR-10 Batch 2:  Batch Loss - 0.011656742542982101; Batch Accuracy - 1.0
Valid Loss - 1.0050508975982666; Valid Accuracy - 0.71
Epoch 162, CIFAR-10 Batch 3:  Batch Loss - 0.011501120403409004; Batch Accuracy - 1.0
Valid Loss - 1.0911251306533813; Valid Accuracy - 0.7
Epoch 162, CIFAR-10 Batch 4:  Batch Loss - 0.010388936847448349; Batch Accuracy - 1.0
Valid Loss - 1.0316112041473389; Valid Accuracy - 0.71
Epoch 162, CIFAR-10 Batch 5:  Batch Loss - 0.018568869680166245; Batch Accuracy - 1.0
Valid Loss - 1.0103596448898315; Valid Accuracy - 0.71
Epoch 163, CIFAR-10 Batch 1:  Batch Loss - 0.01650380529463291; Batch Accuracy - 1.0
Valid Loss - 1.0384691953659058; Valid Accuracy - 0.71
Epoch 163, CIFAR-10 Batch 2:  Batch Loss - 0.010864711366593838; Batch Accuracy - 1.0
Valid Loss - 0.9908519983291626; Valid Accuracy - 0.71
Epoch 163, CIFAR-10 Batch 3:  Batch Loss - 0.00895162858068943; Batch Accuracy - 1.0
Valid Loss - 1.0614087581634521; Valid Accuracy - 0.71
Epoch 163, CIFAR-10 Batch 4:  Batch Loss - 0.010028427466750145; Batch Accuracy - 1.0
Valid Loss - 1.0026546716690063; Valid Accuracy - 0.71
Epoch 163, CIFAR-10 Batch 5:  Batch Loss - 0.011716867797076702; Batch Accuracy - 1.0
Valid Loss - 0.9900276064872742; Valid Accuracy - 0.71
Epoch 164, CIFAR-10 Batch 1:  Batch Loss - 0.009008035995066166; Batch Accuracy - 1.0
Valid Loss - 1.0279853343963623; Valid Accuracy - 0.71
Epoch 164, CIFAR-10 Batch 2:  Batch Loss - 0.013940483331680298; Batch Accuracy - 1.0
Valid Loss - 0.9933977723121643; Valid Accuracy - 0.71
Epoch 164, CIFAR-10 Batch 3:  Batch Loss - 0.016416257247328758; Batch Accuracy - 1.0
Valid Loss - 1.047702670097351; Valid Accuracy - 0.7
Epoch 164, CIFAR-10 Batch 4:  Batch Loss - 0.009755540639162064; Batch Accuracy - 1.0
Valid Loss - 1.0642086267471313; Valid Accuracy - 0.7
Epoch 164, CIFAR-10 Batch 5:  Batch Loss - 0.01668325439095497; Batch Accuracy - 1.0
Valid Loss - 1.0090608596801758; Valid Accuracy - 0.7
Epoch 165, CIFAR-10 Batch 1:  Batch Loss - 0.013631630688905716; Batch Accuracy - 1.0
Valid Loss - 1.0221558809280396; Valid Accuracy - 0.71
Epoch 165, CIFAR-10 Batch 2:  Batch Loss - 0.008825073018670082; Batch Accuracy - 1.0
Valid Loss - 1.034433364868164; Valid Accuracy - 0.7
Epoch 165, CIFAR-10 Batch 3:  Batch Loss - 0.013739380985498428; Batch Accuracy - 1.0
Valid Loss - 1.1255673170089722; Valid Accuracy - 0.69
Epoch 165, CIFAR-10 Batch 4:  Batch Loss - 0.008503880351781845; Batch Accuracy - 1.0
Valid Loss - 1.0662533044815063; Valid Accuracy - 0.7
Epoch 165, CIFAR-10 Batch 5:  Batch Loss - 0.015694033354520798; Batch Accuracy - 1.0
Valid Loss - 1.0115506649017334; Valid Accuracy - 0.71
Epoch 166, CIFAR-10 Batch 1:  Batch Loss - 0.015310611575841904; Batch Accuracy - 1.0
Valid Loss - 1.0800215005874634; Valid Accuracy - 0.7
Epoch 166, CIFAR-10 Batch 2:  Batch Loss - 0.01103418879210949; Batch Accuracy - 1.0
Valid Loss - 1.0109713077545166; Valid Accuracy - 0.71
Epoch 166, CIFAR-10 Batch 3:  Batch Loss - 0.008446171879768372; Batch Accuracy - 1.0
Valid Loss - 1.075144648551941; Valid Accuracy - 0.7
Epoch 166, CIFAR-10 Batch 4:  Batch Loss - 0.008476505056023598; Batch Accuracy - 1.0
Valid Loss - 1.0415515899658203; Valid Accuracy - 0.7
Epoch 166, CIFAR-10 Batch 5:  Batch Loss - 0.0120841134339571; Batch Accuracy - 1.0
Valid Loss - 1.0253535509109497; Valid Accuracy - 0.71
Epoch 167, CIFAR-10 Batch 1:  Batch Loss - 0.013090124353766441; Batch Accuracy - 1.0
Valid Loss - 1.0563122034072876; Valid Accuracy - 0.71
Epoch 167, CIFAR-10 Batch 2:  Batch Loss - 0.011427173390984535; Batch Accuracy - 1.0
Valid Loss - 1.000767707824707; Valid Accuracy - 0.7
Epoch 167, CIFAR-10 Batch 3:  Batch Loss - 0.00811223778873682; Batch Accuracy - 1.0
Valid Loss - 1.1012612581253052; Valid Accuracy - 0.69
Epoch 167, CIFAR-10 Batch 4:  Batch Loss - 0.008829977363348007; Batch Accuracy - 1.0
Valid Loss - 1.0668561458587646; Valid Accuracy - 0.7
Epoch 167, CIFAR-10 Batch 5:  Batch Loss - 0.012899909168481827; Batch Accuracy - 1.0
Valid Loss - 1.034483790397644; Valid Accuracy - 0.71
Epoch 168, CIFAR-10 Batch 1:  Batch Loss - 0.012010247446596622; Batch Accuracy - 1.0
Valid Loss - 1.0626044273376465; Valid Accuracy - 0.7
Epoch 168, CIFAR-10 Batch 2:  Batch Loss - 0.012824559584259987; Batch Accuracy - 1.0
Valid Loss - 1.024768352508545; Valid Accuracy - 0.71
Epoch 168, CIFAR-10 Batch 3:  Batch Loss - 0.008286964148283005; Batch Accuracy - 1.0
Valid Loss - 1.0782259702682495; Valid Accuracy - 0.71
Epoch 168, CIFAR-10 Batch 4:  Batch Loss - 0.006089866627007723; Batch Accuracy - 1.0
Valid Loss - 1.0619992017745972; Valid Accuracy - 0.7
Epoch 168, CIFAR-10 Batch 5:  Batch Loss - 0.012761848047375679; Batch Accuracy - 1.0
Valid Loss - 1.0376797914505005; Valid Accuracy - 0.71
Epoch 169, CIFAR-10 Batch 1:  Batch Loss - 0.010596837848424911; Batch Accuracy - 1.0
Valid Loss - 1.0233144760131836; Valid Accuracy - 0.71
Epoch 169, CIFAR-10 Batch 2:  Batch Loss - 0.017043638974428177; Batch Accuracy - 1.0
Valid Loss - 1.054592251777649; Valid Accuracy - 0.7
Epoch 169, CIFAR-10 Batch 3:  Batch Loss - 0.00600011320784688; Batch Accuracy - 1.0
Valid Loss - 1.103306531906128; Valid Accuracy - 0.7
Epoch 169, CIFAR-10 Batch 4:  Batch Loss - 0.007809725124388933; Batch Accuracy - 1.0
Valid Loss - 1.0490974187850952; Valid Accuracy - 0.7
Epoch 169, CIFAR-10 Batch 5:  Batch Loss - 0.013597827404737473; Batch Accuracy - 1.0
Valid Loss - 1.0498979091644287; Valid Accuracy - 0.71
Epoch 170, CIFAR-10 Batch 1:  Batch Loss - 0.006062365602701902; Batch Accuracy - 1.0
Valid Loss - 1.054862141609192; Valid Accuracy - 0.71
Epoch 170, CIFAR-10 Batch 2:  Batch Loss - 0.011118963360786438; Batch Accuracy - 1.0
Valid Loss - 0.9755358695983887; Valid Accuracy - 0.71
Epoch 170, CIFAR-10 Batch 3:  Batch Loss - 0.007447967305779457; Batch Accuracy - 1.0
Valid Loss - 1.1113210916519165; Valid Accuracy - 0.7
Epoch 170, CIFAR-10 Batch 4:  Batch Loss - 0.010062028653919697; Batch Accuracy - 1.0
Valid Loss - 1.0403227806091309; Valid Accuracy - 0.7
Epoch 170, CIFAR-10 Batch 5:  Batch Loss - 0.025654766708612442; Batch Accuracy - 1.0
Valid Loss - 1.1174712181091309; Valid Accuracy - 0.69
Epoch 171, CIFAR-10 Batch 1:  Batch Loss - 0.009240483865141869; Batch Accuracy - 1.0
Valid Loss - 1.0920696258544922; Valid Accuracy - 0.71
Epoch 171, CIFAR-10 Batch 2:  Batch Loss - 0.015312263742089272; Batch Accuracy - 1.0
Valid Loss - 1.0336438417434692; Valid Accuracy - 0.7
Epoch 171, CIFAR-10 Batch 3:  Batch Loss - 0.005855516530573368; Batch Accuracy - 1.0
Valid Loss - 1.148463249206543; Valid Accuracy - 0.69
Epoch 171, CIFAR-10 Batch 4:  Batch Loss - 0.006789625622332096; Batch Accuracy - 1.0
Valid Loss - 1.0739521980285645; Valid Accuracy - 0.7
Epoch 171, CIFAR-10 Batch 5:  Batch Loss - 0.009408720768988132; Batch Accuracy - 1.0
Valid Loss - 1.04823899269104; Valid Accuracy - 0.71
Epoch 172, CIFAR-10 Batch 1:  Batch Loss - 0.006631872616708279; Batch Accuracy - 1.0
Valid Loss - 1.0428828001022339; Valid Accuracy - 0.71
Epoch 172, CIFAR-10 Batch 2:  Batch Loss - 0.010576236993074417; Batch Accuracy - 1.0
Valid Loss - 1.0313537120819092; Valid Accuracy - 0.71
Epoch 172, CIFAR-10 Batch 3:  Batch Loss - 0.012400072999298573; Batch Accuracy - 1.0
Valid Loss - 1.1230450868606567; Valid Accuracy - 0.7
Epoch 172, CIFAR-10 Batch 4:  Batch Loss - 0.01090552844107151; Batch Accuracy - 1.0
Valid Loss - 1.0794252157211304; Valid Accuracy - 0.7
Epoch 172, CIFAR-10 Batch 5:  Batch Loss - 0.01043257862329483; Batch Accuracy - 1.0
Valid Loss - 1.0410276651382446; Valid Accuracy - 0.71
Epoch 173, CIFAR-10 Batch 1:  Batch Loss - 0.012465104460716248; Batch Accuracy - 1.0
Valid Loss - 1.0585694313049316; Valid Accuracy - 0.71
Epoch 173, CIFAR-10 Batch 2:  Batch Loss - 0.010116131976246834; Batch Accuracy - 1.0
Valid Loss - 1.0215811729431152; Valid Accuracy - 0.71
Epoch 173, CIFAR-10 Batch 3:  Batch Loss - 0.009128272533416748; Batch Accuracy - 1.0
Valid Loss - 1.0774816274642944; Valid Accuracy - 0.7
Epoch 173, CIFAR-10 Batch 4:  Batch Loss - 0.0049972753040492535; Batch Accuracy - 1.0
Valid Loss - 1.0549402236938477; Valid Accuracy - 0.7
Epoch 173, CIFAR-10 Batch 5:  Batch Loss - 0.008142294362187386; Batch Accuracy - 1.0
Valid Loss - 1.0308597087860107; Valid Accuracy - 0.71
Epoch 174, CIFAR-10 Batch 1:  Batch Loss - 0.010386592708528042; Batch Accuracy - 1.0
Valid Loss - 1.088587760925293; Valid Accuracy - 0.71
Epoch 174, CIFAR-10 Batch 2:  Batch Loss - 0.012767652049660683; Batch Accuracy - 1.0
Valid Loss - 1.0440870523452759; Valid Accuracy - 0.7
Epoch 174, CIFAR-10 Batch 3:  Batch Loss - 0.010670093819499016; Batch Accuracy - 1.0
Valid Loss - 1.0645134449005127; Valid Accuracy - 0.7
Epoch 174, CIFAR-10 Batch 4:  Batch Loss - 0.00875027198344469; Batch Accuracy - 1.0
Valid Loss - 1.059291958808899; Valid Accuracy - 0.7
Epoch 174, CIFAR-10 Batch 5:  Batch Loss - 0.011458667926490307; Batch Accuracy - 1.0
Valid Loss - 1.0473277568817139; Valid Accuracy - 0.71
Epoch 175, CIFAR-10 Batch 1:  Batch Loss - 0.009425938129425049; Batch Accuracy - 1.0
Valid Loss - 1.0253260135650635; Valid Accuracy - 0.71
Epoch 175, CIFAR-10 Batch 2:  Batch Loss - 0.016484763473272324; Batch Accuracy - 1.0
Valid Loss - 1.0680129528045654; Valid Accuracy - 0.69
Epoch 175, CIFAR-10 Batch 3:  Batch Loss - 0.0069005428813397884; Batch Accuracy - 1.0
Valid Loss - 1.0396925210952759; Valid Accuracy - 0.7
Epoch 175, CIFAR-10 Batch 4:  Batch Loss - 0.008148892782628536; Batch Accuracy - 1.0
Valid Loss - 1.096358299255371; Valid Accuracy - 0.7
Epoch 175, CIFAR-10 Batch 5:  Batch Loss - 0.012808792293071747; Batch Accuracy - 1.0
Valid Loss - 1.0561994314193726; Valid Accuracy - 0.71
Epoch 176, CIFAR-10 Batch 1:  Batch Loss - 0.007116722408682108; Batch Accuracy - 1.0
Valid Loss - 1.103857398033142; Valid Accuracy - 0.7
Epoch 176, CIFAR-10 Batch 2:  Batch Loss - 0.01282564364373684; Batch Accuracy - 1.0
Valid Loss - 1.044858455657959; Valid Accuracy - 0.7
Epoch 176, CIFAR-10 Batch 3:  Batch Loss - 0.008453933522105217; Batch Accuracy - 1.0
Valid Loss - 1.111298680305481; Valid Accuracy - 0.7
Epoch 176, CIFAR-10 Batch 4:  Batch Loss - 0.0056306906044483185; Batch Accuracy - 1.0
Valid Loss - 1.0642740726470947; Valid Accuracy - 0.71
Epoch 176, CIFAR-10 Batch 5:  Batch Loss - 0.010097840800881386; Batch Accuracy - 1.0
Valid Loss - 1.018357753753662; Valid Accuracy - 0.72
Epoch 177, CIFAR-10 Batch 1:  Batch Loss - 0.006324348971247673; Batch Accuracy - 1.0
Valid Loss - 1.0465681552886963; Valid Accuracy - 0.72
Epoch 177, CIFAR-10 Batch 2:  Batch Loss - 0.014259971678256989; Batch Accuracy - 1.0
Valid Loss - 1.042520523071289; Valid Accuracy - 0.7
Epoch 177, CIFAR-10 Batch 3:  Batch Loss - 0.010754035785794258; Batch Accuracy - 1.0
Valid Loss - 1.0702579021453857; Valid Accuracy - 0.71
Epoch 177, CIFAR-10 Batch 4:  Batch Loss - 0.007098373491317034; Batch Accuracy - 1.0
Valid Loss - 1.0455724000930786; Valid Accuracy - 0.71
Epoch 177, CIFAR-10 Batch 5:  Batch Loss - 0.013884883373975754; Batch Accuracy - 1.0
Valid Loss - 1.0575388669967651; Valid Accuracy - 0.72
Epoch 178, CIFAR-10 Batch 1:  Batch Loss - 0.0059944880194962025; Batch Accuracy - 1.0
Valid Loss - 1.0959572792053223; Valid Accuracy - 0.71
Epoch 178, CIFAR-10 Batch 2:  Batch Loss - 0.011585338972508907; Batch Accuracy - 1.0
Valid Loss - 1.0616443157196045; Valid Accuracy - 0.71
Epoch 178, CIFAR-10 Batch 3:  Batch Loss - 0.007465333677828312; Batch Accuracy - 1.0
Valid Loss - 1.1041017770767212; Valid Accuracy - 0.7
Epoch 178, CIFAR-10 Batch 4:  Batch Loss - 0.0123953428119421; Batch Accuracy - 1.0
Valid Loss - 1.0964964628219604; Valid Accuracy - 0.7
Epoch 178, CIFAR-10 Batch 5:  Batch Loss - 0.009739627130329609; Batch Accuracy - 1.0
Valid Loss - 1.0260517597198486; Valid Accuracy - 0.72
Epoch 179, CIFAR-10 Batch 1:  Batch Loss - 0.009001675061881542; Batch Accuracy - 1.0
Valid Loss - 1.0466079711914062; Valid Accuracy - 0.71
Epoch 179, CIFAR-10 Batch 2:  Batch Loss - 0.006868695840239525; Batch Accuracy - 1.0
Valid Loss - 0.9961552023887634; Valid Accuracy - 0.71
Epoch 179, CIFAR-10 Batch 3:  Batch Loss - 0.008370748721063137; Batch Accuracy - 1.0
Valid Loss - 1.0743670463562012; Valid Accuracy - 0.71
Epoch 179, CIFAR-10 Batch 4:  Batch Loss - 0.0044969250448048115; Batch Accuracy - 1.0
Valid Loss - 1.0729213953018188; Valid Accuracy - 0.72
Epoch 179, CIFAR-10 Batch 5:  Batch Loss - 0.013652617111802101; Batch Accuracy - 1.0
Valid Loss - 1.041496992111206; Valid Accuracy - 0.71
Epoch 180, CIFAR-10 Batch 1:  Batch Loss - 0.008460469543933868; Batch Accuracy - 1.0
Valid Loss - 1.0463995933532715; Valid Accuracy - 0.71
Epoch 180, CIFAR-10 Batch 2:  Batch Loss - 0.012797688134014606; Batch Accuracy - 1.0
Valid Loss - 1.0046768188476562; Valid Accuracy - 0.71
Epoch 180, CIFAR-10 Batch 3:  Batch Loss - 0.007631281390786171; Batch Accuracy - 1.0
Valid Loss - 1.1079355478286743; Valid Accuracy - 0.71
Epoch 180, CIFAR-10 Batch 4:  Batch Loss - 0.006590978242456913; Batch Accuracy - 1.0
Valid Loss - 1.0682380199432373; Valid Accuracy - 0.71
Epoch 180, CIFAR-10 Batch 5:  Batch Loss - 0.01139402762055397; Batch Accuracy - 1.0
Valid Loss - 1.0687775611877441; Valid Accuracy - 0.71
Epoch 181, CIFAR-10 Batch 1:  Batch Loss - 0.006853194907307625; Batch Accuracy - 1.0
Valid Loss - 1.0802175998687744; Valid Accuracy - 0.7
Epoch 181, CIFAR-10 Batch 2:  Batch Loss - 0.010646692477166653; Batch Accuracy - 1.0
Valid Loss - 1.048021912574768; Valid Accuracy - 0.71
Epoch 181, CIFAR-10 Batch 3:  Batch Loss - 0.012682957574725151; Batch Accuracy - 1.0
Valid Loss - 1.14548659324646; Valid Accuracy - 0.69
Epoch 181, CIFAR-10 Batch 4:  Batch Loss - 0.0045296987518668175; Batch Accuracy - 1.0
Valid Loss - 1.09731924533844; Valid Accuracy - 0.7
Epoch 181, CIFAR-10 Batch 5:  Batch Loss - 0.010878553614020348; Batch Accuracy - 1.0
Valid Loss - 1.102774739265442; Valid Accuracy - 0.7
Epoch 182, CIFAR-10 Batch 1:  Batch Loss - 0.009766636416316032; Batch Accuracy - 1.0
Valid Loss - 1.0446045398712158; Valid Accuracy - 0.72
Epoch 182, CIFAR-10 Batch 2:  Batch Loss - 0.010732781141996384; Batch Accuracy - 1.0
Valid Loss - 1.0211395025253296; Valid Accuracy - 0.71
Epoch 182, CIFAR-10 Batch 3:  Batch Loss - 0.006475023925304413; Batch Accuracy - 1.0
Valid Loss - 1.1086161136627197; Valid Accuracy - 0.71
Epoch 182, CIFAR-10 Batch 4:  Batch Loss - 0.007205176167190075; Batch Accuracy - 1.0
Valid Loss - 1.080431580543518; Valid Accuracy - 0.71
Epoch 182, CIFAR-10 Batch 5:  Batch Loss - 0.00884331576526165; Batch Accuracy - 1.0
Valid Loss - 1.0462499856948853; Valid Accuracy - 0.72
Epoch 183, CIFAR-10 Batch 1:  Batch Loss - 0.012056000530719757; Batch Accuracy - 1.0
Valid Loss - 1.0937894582748413; Valid Accuracy - 0.71
Epoch 183, CIFAR-10 Batch 2:  Batch Loss - 0.013087114319205284; Batch Accuracy - 1.0
Valid Loss - 1.0615299940109253; Valid Accuracy - 0.7
Epoch 183, CIFAR-10 Batch 3:  Batch Loss - 0.006690296344459057; Batch Accuracy - 1.0
Valid Loss - 1.0616223812103271; Valid Accuracy - 0.71
Epoch 183, CIFAR-10 Batch 4:  Batch Loss - 0.00894418079406023; Batch Accuracy - 1.0
Valid Loss - 1.083925724029541; Valid Accuracy - 0.7
Epoch 183, CIFAR-10 Batch 5:  Batch Loss - 0.010073856450617313; Batch Accuracy - 1.0
Valid Loss - 1.019675612449646; Valid Accuracy - 0.72
Epoch 184, CIFAR-10 Batch 1:  Batch Loss - 0.007253836840391159; Batch Accuracy - 1.0
Valid Loss - 1.054503321647644; Valid Accuracy - 0.72
Epoch 184, CIFAR-10 Batch 2:  Batch Loss - 0.01076497696340084; Batch Accuracy - 1.0
Valid Loss - 1.0683711767196655; Valid Accuracy - 0.7
Epoch 184, CIFAR-10 Batch 3:  Batch Loss - 0.010094983503222466; Batch Accuracy - 1.0
Valid Loss - 1.0440711975097656; Valid Accuracy - 0.7
Epoch 184, CIFAR-10 Batch 4:  Batch Loss - 0.006814413238316774; Batch Accuracy - 1.0
Valid Loss - 1.0423004627227783; Valid Accuracy - 0.71
Epoch 184, CIFAR-10 Batch 5:  Batch Loss - 0.006347179412841797; Batch Accuracy - 1.0
Valid Loss - 1.0366790294647217; Valid Accuracy - 0.71
Epoch 185, CIFAR-10 Batch 1:  Batch Loss - 0.021238252520561218; Batch Accuracy - 1.0
Valid Loss - 1.0923645496368408; Valid Accuracy - 0.71
Epoch 185, CIFAR-10 Batch 2:  Batch Loss - 0.011083865538239479; Batch Accuracy - 1.0
Valid Loss - 1.0365185737609863; Valid Accuracy - 0.71
Epoch 185, CIFAR-10 Batch 3:  Batch Loss - 0.016823168843984604; Batch Accuracy - 1.0
Valid Loss - 1.1128337383270264; Valid Accuracy - 0.7
Epoch 185, CIFAR-10 Batch 4:  Batch Loss - 0.00992934312671423; Batch Accuracy - 1.0
Valid Loss - 1.0552139282226562; Valid Accuracy - 0.7
Epoch 185, CIFAR-10 Batch 5:  Batch Loss - 0.011776652187108994; Batch Accuracy - 1.0
Valid Loss - 1.0492429733276367; Valid Accuracy - 0.71
Epoch 186, CIFAR-10 Batch 1:  Batch Loss - 0.0041954913176596165; Batch Accuracy - 1.0
Valid Loss - 1.048121690750122; Valid Accuracy - 0.72
Epoch 186, CIFAR-10 Batch 2:  Batch Loss - 0.008904218673706055; Batch Accuracy - 1.0
Valid Loss - 1.0428507328033447; Valid Accuracy - 0.71
Epoch 186, CIFAR-10 Batch 3:  Batch Loss - 0.006515871733427048; Batch Accuracy - 1.0
Valid Loss - 1.1367847919464111; Valid Accuracy - 0.7
Epoch 186, CIFAR-10 Batch 4:  Batch Loss - 0.006895785219967365; Batch Accuracy - 1.0
Valid Loss - 1.082058072090149; Valid Accuracy - 0.71
Epoch 186, CIFAR-10 Batch 5:  Batch Loss - 0.0073838382959365845; Batch Accuracy - 1.0
Valid Loss - 1.0431398153305054; Valid Accuracy - 0.71
Epoch 187, CIFAR-10 Batch 1:  Batch Loss - 0.020910639315843582; Batch Accuracy - 1.0
Valid Loss - 1.0417706966400146; Valid Accuracy - 0.71
Epoch 187, CIFAR-10 Batch 2:  Batch Loss - 0.010778320953249931; Batch Accuracy - 1.0
Valid Loss - 1.0279545783996582; Valid Accuracy - 0.71
Epoch 187, CIFAR-10 Batch 3:  Batch Loss - 0.0061752693727612495; Batch Accuracy - 1.0
Valid Loss - 1.1313276290893555; Valid Accuracy - 0.7
Epoch 187, CIFAR-10 Batch 4:  Batch Loss - 0.007338311988860369; Batch Accuracy - 1.0
Valid Loss - 1.083719253540039; Valid Accuracy - 0.7
Epoch 187, CIFAR-10 Batch 5:  Batch Loss - 0.009161828085780144; Batch Accuracy - 1.0
Valid Loss - 1.067141056060791; Valid Accuracy - 0.71
Epoch 188, CIFAR-10 Batch 1:  Batch Loss - 0.011018464341759682; Batch Accuracy - 1.0
Valid Loss - 1.021971583366394; Valid Accuracy - 0.71
Epoch 188, CIFAR-10 Batch 2:  Batch Loss - 0.008537624031305313; Batch Accuracy - 1.0
Valid Loss - 1.0253874063491821; Valid Accuracy - 0.71
Epoch 188, CIFAR-10 Batch 3:  Batch Loss - 0.005325811915099621; Batch Accuracy - 1.0
Valid Loss - 1.073167324066162; Valid Accuracy - 0.71
Epoch 188, CIFAR-10 Batch 4:  Batch Loss - 0.005142000503838062; Batch Accuracy - 1.0
Valid Loss - 1.06898033618927; Valid Accuracy - 0.71
Epoch 188, CIFAR-10 Batch 5:  Batch Loss - 0.00922099594026804; Batch Accuracy - 1.0
Valid Loss - 1.0319794416427612; Valid Accuracy - 0.71
Epoch 189, CIFAR-10 Batch 1:  Batch Loss - 0.017393741756677628; Batch Accuracy - 1.0
Valid Loss - 1.0752997398376465; Valid Accuracy - 0.7
Epoch 189, CIFAR-10 Batch 2:  Batch Loss - 0.007664024829864502; Batch Accuracy - 1.0
Valid Loss - 1.0137628316879272; Valid Accuracy - 0.72
Epoch 189, CIFAR-10 Batch 3:  Batch Loss - 0.007643083110451698; Batch Accuracy - 1.0
Valid Loss - 1.132551670074463; Valid Accuracy - 0.7
Epoch 189, CIFAR-10 Batch 4:  Batch Loss - 0.00742862606421113; Batch Accuracy - 1.0
Valid Loss - 1.0513750314712524; Valid Accuracy - 0.71
Epoch 189, CIFAR-10 Batch 5:  Batch Loss - 0.013081328012049198; Batch Accuracy - 1.0
Valid Loss - 1.0262324810028076; Valid Accuracy - 0.72
Epoch 190, CIFAR-10 Batch 1:  Batch Loss - 0.0081998435780406; Batch Accuracy - 1.0
Valid Loss - 1.0640087127685547; Valid Accuracy - 0.71
Epoch 190, CIFAR-10 Batch 2:  Batch Loss - 0.010553374886512756; Batch Accuracy - 1.0
Valid Loss - 1.0708998441696167; Valid Accuracy - 0.71
Epoch 190, CIFAR-10 Batch 3:  Batch Loss - 0.006177439354360104; Batch Accuracy - 1.0
Valid Loss - 1.1332590579986572; Valid Accuracy - 0.7
Epoch 190, CIFAR-10 Batch 4:  Batch Loss - 0.00618343148380518; Batch Accuracy - 1.0
Valid Loss - 1.067771315574646; Valid Accuracy - 0.71
Epoch 190, CIFAR-10 Batch 5:  Batch Loss - 0.011677080765366554; Batch Accuracy - 1.0
Valid Loss - 1.0622690916061401; Valid Accuracy - 0.71
Epoch 191, CIFAR-10 Batch 1:  Batch Loss - 0.00914344284683466; Batch Accuracy - 1.0
Valid Loss - 1.074110507965088; Valid Accuracy - 0.71
Epoch 191, CIFAR-10 Batch 2:  Batch Loss - 0.008480299264192581; Batch Accuracy - 1.0
Valid Loss - 1.0555150508880615; Valid Accuracy - 0.71
Epoch 191, CIFAR-10 Batch 3:  Batch Loss - 0.00725935585796833; Batch Accuracy - 1.0
Valid Loss - 1.1400388479232788; Valid Accuracy - 0.7
Epoch 191, CIFAR-10 Batch 4:  Batch Loss - 0.0037529494147747755; Batch Accuracy - 1.0
Valid Loss - 1.0666791200637817; Valid Accuracy - 0.71
Epoch 191, CIFAR-10 Batch 5:  Batch Loss - 0.007721768692135811; Batch Accuracy - 1.0
Valid Loss - 1.0547881126403809; Valid Accuracy - 0.72
Epoch 192, CIFAR-10 Batch 1:  Batch Loss - 0.010816771537065506; Batch Accuracy - 1.0
Valid Loss - 1.0313142538070679; Valid Accuracy - 0.71
Epoch 192, CIFAR-10 Batch 2:  Batch Loss - 0.01224969606846571; Batch Accuracy - 1.0
Valid Loss - 1.0477625131607056; Valid Accuracy - 0.7
Epoch 192, CIFAR-10 Batch 3:  Batch Loss - 0.007521215360611677; Batch Accuracy - 1.0
Valid Loss - 1.1517596244812012; Valid Accuracy - 0.69
Epoch 192, CIFAR-10 Batch 4:  Batch Loss - 0.006534763611853123; Batch Accuracy - 1.0
Valid Loss - 1.0708179473876953; Valid Accuracy - 0.7
Epoch 192, CIFAR-10 Batch 5:  Batch Loss - 0.01090485230088234; Batch Accuracy - 1.0
Valid Loss - 1.0308605432510376; Valid Accuracy - 0.71
Epoch 193, CIFAR-10 Batch 1:  Batch Loss - 0.009324734099209309; Batch Accuracy - 1.0
Valid Loss - 1.0405739545822144; Valid Accuracy - 0.71
Epoch 193, CIFAR-10 Batch 2:  Batch Loss - 0.006572067737579346; Batch Accuracy - 1.0
Valid Loss - 1.0323100090026855; Valid Accuracy - 0.71
Epoch 193, CIFAR-10 Batch 3:  Batch Loss - 0.0069398595951497555; Batch Accuracy - 1.0
Valid Loss - 1.161576509475708; Valid Accuracy - 0.7
Epoch 193, CIFAR-10 Batch 4:  Batch Loss - 0.006961023900657892; Batch Accuracy - 1.0
Valid Loss - 1.0528932809829712; Valid Accuracy - 0.71
Epoch 193, CIFAR-10 Batch 5:  Batch Loss - 0.006924488581717014; Batch Accuracy - 1.0
Valid Loss - 1.0383304357528687; Valid Accuracy - 0.72
Epoch 194, CIFAR-10 Batch 1:  Batch Loss - 0.007945393212139606; Batch Accuracy - 1.0
Valid Loss - 1.0394121408462524; Valid Accuracy - 0.71
Epoch 194, CIFAR-10 Batch 2:  Batch Loss - 0.011324003338813782; Batch Accuracy - 1.0
Valid Loss - 1.007857084274292; Valid Accuracy - 0.71
Epoch 194, CIFAR-10 Batch 3:  Batch Loss - 0.007425153627991676; Batch Accuracy - 1.0
Valid Loss - 1.0412383079528809; Valid Accuracy - 0.71
Epoch 194, CIFAR-10 Batch 4:  Batch Loss - 0.007847364991903305; Batch Accuracy - 1.0
Valid Loss - 1.0641916990280151; Valid Accuracy - 0.71
Epoch 194, CIFAR-10 Batch 5:  Batch Loss - 0.0070320614613592625; Batch Accuracy - 1.0
Valid Loss - 1.0492199659347534; Valid Accuracy - 0.72
Epoch 195, CIFAR-10 Batch 1:  Batch Loss - 0.003833590541034937; Batch Accuracy - 1.0
Valid Loss - 1.0623449087142944; Valid Accuracy - 0.71
Epoch 195, CIFAR-10 Batch 2:  Batch Loss - 0.009871968068182468; Batch Accuracy - 1.0
Valid Loss - 1.0555341243743896; Valid Accuracy - 0.71
Epoch 195, CIFAR-10 Batch 3:  Batch Loss - 0.004693895578384399; Batch Accuracy - 1.0
Valid Loss - 1.0968663692474365; Valid Accuracy - 0.71
Epoch 195, CIFAR-10 Batch 4:  Batch Loss - 0.004464639816433191; Batch Accuracy - 1.0
Valid Loss - 1.057986855506897; Valid Accuracy - 0.71
Epoch 195, CIFAR-10 Batch 5:  Batch Loss - 0.011303415521979332; Batch Accuracy - 1.0
Valid Loss - 1.0358304977416992; Valid Accuracy - 0.72
Epoch 196, CIFAR-10 Batch 1:  Batch Loss - 0.0070688966661691666; Batch Accuracy - 1.0
Valid Loss - 1.0608999729156494; Valid Accuracy - 0.71
Epoch 196, CIFAR-10 Batch 2:  Batch Loss - 0.0075423382222652435; Batch Accuracy - 1.0
Valid Loss - 1.0720282793045044; Valid Accuracy - 0.72
Epoch 196, CIFAR-10 Batch 3:  Batch Loss - 0.005688098259270191; Batch Accuracy - 1.0
Valid Loss - 1.0658745765686035; Valid Accuracy - 0.71
Epoch 196, CIFAR-10 Batch 4:  Batch Loss - 0.0032377252355217934; Batch Accuracy - 1.0
Valid Loss - 1.0936930179595947; Valid Accuracy - 0.71
Epoch 196, CIFAR-10 Batch 5:  Batch Loss - 0.009574754163622856; Batch Accuracy - 1.0
Valid Loss - 1.0463041067123413; Valid Accuracy - 0.72
Epoch 197, CIFAR-10 Batch 1:  Batch Loss - 0.011868573725223541; Batch Accuracy - 1.0
Valid Loss - 1.0860955715179443; Valid Accuracy - 0.71
Epoch 197, CIFAR-10 Batch 2:  Batch Loss - 0.010951332747936249; Batch Accuracy - 1.0
Valid Loss - 1.0265169143676758; Valid Accuracy - 0.71
Epoch 197, CIFAR-10 Batch 3:  Batch Loss - 0.004053969867527485; Batch Accuracy - 1.0
Valid Loss - 1.1011804342269897; Valid Accuracy - 0.7
Epoch 197, CIFAR-10 Batch 4:  Batch Loss - 0.003870079293847084; Batch Accuracy - 1.0
Valid Loss - 1.0788615942001343; Valid Accuracy - 0.71
Epoch 197, CIFAR-10 Batch 5:  Batch Loss - 0.008427699096500874; Batch Accuracy - 1.0
Valid Loss - 1.0412105321884155; Valid Accuracy - 0.72
Epoch 198, CIFAR-10 Batch 1:  Batch Loss - 0.007498428225517273; Batch Accuracy - 1.0
Valid Loss - 1.0686366558074951; Valid Accuracy - 0.71
Epoch 198, CIFAR-10 Batch 2:  Batch Loss - 0.009758459404110909; Batch Accuracy - 1.0
Valid Loss - 1.0408220291137695; Valid Accuracy - 0.71
Epoch 198, CIFAR-10 Batch 3:  Batch Loss - 0.0032177497632801533; Batch Accuracy - 1.0
Valid Loss - 1.1096473932266235; Valid Accuracy - 0.7
Epoch 198, CIFAR-10 Batch 4:  Batch Loss - 0.00902233924716711; Batch Accuracy - 1.0
Valid Loss - 1.0623365640640259; Valid Accuracy - 0.71
Epoch 198, CIFAR-10 Batch 5:  Batch Loss - 0.005119191482663155; Batch Accuracy - 1.0
Valid Loss - 1.042742371559143; Valid Accuracy - 0.71
Epoch 199, CIFAR-10 Batch 1:  Batch Loss - 0.01577197015285492; Batch Accuracy - 1.0
Valid Loss - 1.1330512762069702; Valid Accuracy - 0.71
Epoch 199, CIFAR-10 Batch 2:  Batch Loss - 0.011466547846794128; Batch Accuracy - 1.0
Valid Loss - 1.098446249961853; Valid Accuracy - 0.71
Epoch 199, CIFAR-10 Batch 3:  Batch Loss - 0.00977942906320095; Batch Accuracy - 1.0
Valid Loss - 1.08241868019104; Valid Accuracy - 0.7
Epoch 199, CIFAR-10 Batch 4:  Batch Loss - 0.004114085342735052; Batch Accuracy - 1.0
Valid Loss - 1.1027339696884155; Valid Accuracy - 0.7
Epoch 199, CIFAR-10 Batch 5:  Batch Loss - 0.009443964809179306; Batch Accuracy - 1.0
Valid Loss - 1.0660300254821777; Valid Accuracy - 0.71
Epoch 200, CIFAR-10 Batch 1:  Batch Loss - 0.008073667995631695; Batch Accuracy - 1.0
Valid Loss - 1.0507562160491943; Valid Accuracy - 0.71
Epoch 200, CIFAR-10 Batch 2:  Batch Loss - 0.008822355419397354; Batch Accuracy - 1.0
Valid Loss - 1.058640956878662; Valid Accuracy - 0.71
Epoch 200, CIFAR-10 Batch 3:  Batch Loss - 0.004425106570124626; Batch Accuracy - 1.0
Valid Loss - 1.0978381633758545; Valid Accuracy - 0.7
Epoch 200, CIFAR-10 Batch 4:  Batch Loss - 0.004855664446949959; Batch Accuracy - 1.0
Valid Loss - 1.073520302772522; Valid Accuracy - 0.71
Epoch 200, CIFAR-10 Batch 5:  Batch Loss - 0.0066184187307953835; Batch Accuracy - 1.0
Valid Loss - 1.0531522035598755; Valid Accuracy - 0.72

Checkpoint

The model has been saved to disk.

Test Model

Test your model against the test dataset. This will be your final accuracy. You should have an accuracy greater than 50%. If you don't, keep tweaking the model architecture and parameters.



In [178]:

    
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import tensorflow as tf
import pickle
import helper
import random

# Set batch size if not already set
try:
    if batch_size:
        pass
except NameError:
    batch_size = 64

save_model_path = './image_classification'
n_samples = 4
top_n_predictions = 3

def test_model():
    """
    Test the saved model against the test dataset
    """

    test_features, test_labels = pickle.load(open('preprocess_training.p', mode='rb'))
    loaded_graph = tf.Graph()

    with tf.Session(graph=loaded_graph) as sess:
        # Load model
        loader = tf.train.import_meta_graph(save_model_path + '.meta')
        loader.restore(sess, save_model_path)

        # Get Tensors from loaded model
        loaded_x = loaded_graph.get_tensor_by_name('x:0')
        loaded_y = loaded_graph.get_tensor_by_name('y:0')
        loaded_keep_prob = loaded_graph.get_tensor_by_name('keep_prob:0')
        loaded_logits = loaded_graph.get_tensor_by_name('logits:0')
        loaded_acc = loaded_graph.get_tensor_by_name('accuracy:0')
        
        # Get accuracy in batches for memory limitations
        test_batch_acc_total = 0
        test_batch_count = 0
        
        for train_feature_batch, train_label_batch in helper.batch_features_labels(test_features, test_labels, batch_size):
            test_batch_acc_total += sess.run(
                loaded_acc,
                feed_dict={loaded_x: train_feature_batch, loaded_y: train_label_batch, loaded_keep_prob: 1.0})
            test_batch_count += 1

        print('Testing Accuracy: {}\n'.format(test_batch_acc_total/test_batch_count))

        # Print Random Samples
        random_test_features, random_test_labels = tuple(zip(*random.sample(list(zip(test_features, test_labels)), n_samples)))
        random_test_predictions = sess.run(
            tf.nn.top_k(tf.nn.softmax(loaded_logits), top_n_predictions),
            feed_dict={loaded_x: random_test_features, loaded_y: random_test_labels, loaded_keep_prob: 1.0})
        helper.display_image_predictions(random_test_features, random_test_labels, random_test_predictions)


test_model()









    



Testing Accuracy: 0.7130859375

Why 50-70% Accuracy?

You might be wondering why you can't get an accuracy any higher. First things first, 50% isn't bad for a simple CNN. Pure guessing would get you 10% accuracy. However, you might notice people are getting scores well above 70%. That's because we haven't taught you all there is to know about neural networks. We still need to cover a few more techniques.

Submitting This Project

When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_image_classification.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.