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.
Run the following cell to download the CIFAR-10 dataset for python.
在该项目中,你将会对来自 CIFAR-10 数据集 中的图像进行分类。数据集中图片的内容包括飞机(airplane)、狗(dogs)、猫(cats)及其他物体。你需要处理这些图像,接着对所有的样本训练一个卷积神经网络。
具体而言,在项目中你要对图像进行正规化处理(normalization),同时还要对图像的标签进行 one-hot 编码。接着你将会应用到你所学的技能来搭建一个具有卷积层、最大池化(Max Pooling)层、Dropout 层及全连接(fully connected)层的神经网络。最后,你会训练你的神经网络,会得到你神经网络在样本图像上的预测结果。
运行如下代码下载 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)
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:
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.
为防止在运行过程中内存不足的问题,该数据集已经事先被分成了5批(batch),名为data_batch_1
、data_batch_2
等。每一批中都含有 图像 及对应的 标签,都是如下类别中的一种:
理解数据集也是对数据进行预测的一部分。修改如下代码中的 batch_id
和 sample_id
,看看输出的图像是什么样子。其中,batch_id
代表着批次数(1-5),sample_id
代表着在该批内图像及标签的编号。
你可以尝试回答如下问题:
对这些问题的回答,会有助于更好地处理数据,并能更好地进行预测。
In [2]:
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
import helper
import numpy as np
# Explore the dataset
batch_id = 2
sample_id = 1
helper.display_stats(cifar10_dataset_folder_path, batch_id, sample_id)
In [3]:
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
"""
return x/255.0
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_normalize(normalize)
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:
Look into LabelBinarizer in the preprocessing module of sklearn.
【CodeReview170905】 170905-19:34发现函数one_hot_encode()实现错了,本来应该是0-9,也就是range(1,10),而我直接写成了[1,2,3,4,5,6,7,8,9,10],导致错误,进一步地导致网络发散。
In [4]:
from sklearn import preprocessing
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
lb = preprocessing.LabelBinarizer()
labels = list(range(0, 10))
lb.fit(labels)
one_hot = lb.transform(x)
return one_hot
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_one_hot_encode(one_hot_encode)
In [5]:
"""
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)
In [6]:
"""
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'))
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.
Note: If you're finding it hard to dedicate enough time for this course each 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 classes from the TensorFlow Layers or TensorFlow Layers (contrib) packages to build each layer, except the layers you build in the "Convolutional and Max Pooling Layer" section. TF Layers is similar to Keras's and TFLearn's abstraction to layers, so it's easy to pickup.
However, if you would like to get the most out of this course, try to solve all the problems without using anything from the TF Layers packages. You can still use classes from other packages that happen to have the same name as ones you find in TF Layers! For example, instead of using the TF Layers version of the
conv2d
class, tf.layers.conv2d, you would want to use the TF Neural Network version ofconv2d
, tf.nn.conv2d.
Let's begin!
The neural network needs to read the image data, one-hot encoded labels, and dropout keep probability. Implement the following functions
neural_net_image_input
image_shape
with batch size set to None
.name
parameter in the TF Placeholder.neural_net_label_input
n_classes
with batch size set to None
.name
parameter in the TF Placeholder.neural_net_keep_prob_input
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.
为搭建神经网络,你需要将搭建每一层的过程封装到一个函数中。大部分的代码你在函数外已经见过。为能够更透彻地测试你的代码,我们要求你把每一层都封装到一个函数中。这能够帮助我们给予你更好的回复,同时还能让我们使用 unittests 在你提交报告前检测出你项目中的小问题。
注意: 如果你时间紧迫,那么在该部分我们为你提供了一个便捷方法。在接下来的一些问题中,你可以使用来自 TensorFlow Layers 或 TensorFlow Layers (contrib) 包中的函数来搭建各层,不过不可以用他们搭建卷积-最大池化层。TF Layers 和 Keras 及 TFLean 中对层的抽象比较相似,所以你应该很容易上手。
>
However, if you would like to get the most out of this course, try to solve all the problems without using anything from the TF Layers packages. You can still use classes from other packages that happen to have the same name as ones you find in TF Layers! For example, instead of using the TF Layers version of the conv2d
class, tf.layers.conv2d, you would want to use the TF Neural Network version of conv2d
, tf.nn.conv2d.
不过,如果你希望能够更多地实践,我们希望你能够在不使用 TF Layers 的情况下解决所有问题。你依然能使用来自其他包但和 layers 中重名的函数。例如,你可以使用 TF Neural Network 版本的 `conv_2d
让我们开始吧!
神经网络需要能够读取图像数据、经 one-hot 编码之后的标签及 dropout 中的保留概率。修改如下函数:
neural_net_image_input
函数:image_shape
设定形状,设定批大小(batch size)为 None
。Name
参数,命名该 TensorFlow placeholder 为 "x"。neural_net_label_input
函数: n_classes
设定形状,设定批大小(batch size)为 None
。Name
参数,命名该 TensorFlow placeholder 为 "y"。neural_net_keep_prob_input
函数:Name
参数,命名该 TensorFlow placeholder 为 "keep_prob"。我们会在项目最后使用这些名字,来载入你储存的模型。
注意:在 TensorFlow 中,对形状设定为 None
,能帮助设定一个动态的大小。
这里本来是想用tensorflow-gpu的,但是,gpu报错,原因是卷积网络和神经网络连接那两层节点太多,GPU内存不够。另外,data_validation的过程中,5000个实例没有做分割,一起加载,也导致了tensor过大。
In [7]:
import tensorflow as tf
# There are tensorflow-gpu settings, but gpu can not work becourse of the net is too big.
from keras.backend.tensorflow_backend import set_session
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.3
set_session(tf.Session(config=config))
def neural_net_image_input(image_shape):
"""
Return a Tensor for a batch of image input
: image_shape: Shape of the images
: return: Tensor for image input.
"""
# TODO: Implement Function
x = tf.placeholder(tf.float32, shape=(None, image_shape[0], image_shape[1], image_shape[2]), name='x')
return x
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
y = tf.placeholder(tf.float32, shape=(None, n_classes), name='y')
return y
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)
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:
conv_ksize
, conv_num_outputs
and the shape of x_tensor
.x_tensor
using weight and conv_strides
.pool_ksize
and pool_strides
.Note: You can't use TensorFlow Layers or TensorFlow Layers (contrib) for this layer, but you can still use TensorFlow's Neural Network package. You may still use the shortcut option for all the other layers.
Hint:
When unpacking values as an argument in Python, look into the unpacking operator.
卷积层在图像处理中取得了不小的成功。在这部分的代码中,你需要修改 conv2d_maxpool
函数来先后实现卷积及最大池化的功能。
conv_ksize
、conv_num_outputs
及 x_tensor
来创建权重(weight)及偏差(bias)变量。x_tensor
进行卷积,使用 conv_strides
及权重。pool_kszie
及 pool_strides
进行最大池化。注意: 你不可以使用来自 TensorFlow Layers 或 TensorFlow Layers (contrib) 包中的函数来实现这一层的功能。但是你可以使用 TensorFlow 的Neural Network包。
对于如上的快捷方法,你在其他层中可以尝试使用。
提示: 当你在 Python 中希望展开(unpacking)某个变量的值作为函数的参数,你可以参考 unpacking 运算符。
In [8]:
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_ksize: kernal size 2-D Tuple 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
"""
#input = tf.placeholder(tf.float32, (None, 32, 32, 3))
x_tensor_shape = x_tensor.get_shape().as_list()
print('x_tensor_shape:\t{0}'.format(x_tensor_shape))
print('conv_num_outputs:{0}'.format(conv_num_outputs))
print('conv_ksize:\t{0}'.format(conv_ksize))
print('conv_strides:\t{0}'.format(conv_strides))
print('pool_ksize:\t{0}'.format(pool_ksize))
print('pool_strides:\t{0}'.format(pool_strides))
filter_weights = tf.Variable(tf.truncated_normal((conv_ksize[0], conv_ksize[1], x_tensor_shape[3], conv_num_outputs), mean=0.0, stddev = 0.05)) # (height, width, input_depth, output_depth)
filter_bias = tf.Variable(tf.zeros(conv_num_outputs))
strides = [1, conv_strides[0], conv_strides[1], 1] # (batch, height, width, depth)
conv_layer = tf.nn.conv2d(x_tensor, filter_weights, strides=strides, padding='SAME')
conv_layer = tf.nn.bias_add(conv_layer, filter_bias)
# conv_layer = conv_layer + filter_bias
conv_layer = tf.nn.relu(conv_layer)
# Apply Max Pooling
conv_layer = tf.nn.max_pool(
conv_layer,
ksize=[1, pool_ksize[0], pool_ksize[1], 1],
strides=[1, pool_strides[0], pool_strides[1], 1],
padding='SAME')
return conv_layer
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_con_pool(conv2d_maxpool)
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). Shortcut option: you can use classes from the TensorFlow Layers or TensorFlow Layers (contrib) packages for this layer. For more of a challenge, only use other TensorFlow packages.
修改 flatten
函数,来将4维的输入张量 x_tensor
转换为一个二维的张量。输出的形状应当是 (Batch Size, Flattened Image Size)
。
快捷方法:你可以使用来自 TensorFlow Layers 或 TensorFlow Layers (contrib) 包中的函数来实现该功能。不过你也可以只使用 TensorFlow 包中的函数来挑战自己。
In [9]:
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
return tf.contrib.layers.flatten(x_tensor)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_flatten(flatten)
Implement the fully_conn
function to apply a fully connected layer to x_tensor
with the shape (Batch Size, num_outputs). Shortcut option: you can use classes from the TensorFlow Layers or TensorFlow Layers (contrib) packages for this layer. For more of a challenge, only use other TensorFlow packages.
修改 fully_conn
函数,来对形如 (batch Size, num_outputs)
的输入 x_tensor
应用一个全连接层。快捷方法:你可以使用来自 TensorFlow Layers 或 TensorFlow Layers (contrib) 包中的函数来实现该功能。不过你也可以只使用 TensorFlow 包中的函数来挑战自己。
In [10]:
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
return tf.contrib.layers.fully_connected(x_tensor, num_outputs)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_fully_conn(fully_conn)
Implement the output
function to apply a fully connected layer to x_tensor
with the shape (Batch Size, num_outputs). Shortcut option: you can use classes from the TensorFlow Layers or TensorFlow Layers (contrib) packages for this layer. For more of a challenge, only use other TensorFlow packages.
Note: Activation, softmax, or cross entropy should not be applied to this.
修改 output
函数,来对形如 (batch Size, num_outputs)
的输入 x_tensor
应用一个全连接层。快捷方法:你可以使用来自 TensorFlow Layers 或 TensorFlow Layers (contrib) 包中的函数来实现该功能。不过你也可以只使用 TensorFlow 包中的函数来挑战自己。
注意: 激活函数、softmax 或者交叉熵(corss entropy)不应被加入到该层。
In [11]:
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
return tf.contrib.layers.fully_connected(x_tensor, num_outputs, activation_fn=None)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_output(output)
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:
keep_prob
. 修改 conv_net
函数,使之能够生成一个卷积神经网络模型。该函数的输入为一批图像数据 x
,输出为 logits。在函数中,使用上方你修改的创建各种层的函数来创建该模型:
keep_prob
.
In [12]:
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:
# conv2d_maxpool(x_tensor, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides)
conv_num_outputs1 = 32
conv_ksize1 = (4, 4)
conv_strides1 = (1, 1)
pool_ksize1 = (2, 2)
pool_strides1 = (2, 2)
conv_layer1 = conv2d_maxpool(x, conv_num_outputs1, conv_ksize1, conv_strides1, pool_ksize1, pool_strides1)
conv_layer1 = tf.nn.dropout(conv_layer1, keep_prob)
conv_num_outputs2 = 64
conv_ksize2 = (4, 4)
conv_strides2 = (1, 1)
pool_ksize2 = (2, 2)
pool_strides2 = (2, 2)
conv_layer2 = conv2d_maxpool(x, conv_num_outputs2, conv_ksize2, conv_strides2, pool_ksize2, pool_strides2)
conv_layer2 = tf.nn.dropout(conv_layer2, keep_prob)
conv_num_outputs3 = 128
conv_ksize3 = (4, 4)
conv_strides3 = (1, 1)
pool_ksize3 = (2, 2)
pool_strides3 = (2, 2)
conv_layer3 = conv2d_maxpool(x, conv_num_outputs3, conv_ksize3, conv_strides3, pool_ksize3, pool_strides3)
conv_layer3 = tf.nn.dropout(conv_layer3, keep_prob)
# TODO: Apply a Flatten Layer
# Function Definition from Above:
# flatten(x_tensor)
conv_layer_flatten = flatten(conv_layer3)
print('conv_layer_flatten.shape:%s' %conv_layer_flatten.shape)
# TODO: Apply 1, 2, or 3 Fully Connected Layers
# Play around with different number of outputs
# Function Definition from Above:
# fully_conn(x_tensor, num_outputs)
fc_num_outputs1 = 1024
fc_layer1 = fully_conn(conv_layer_flatten, fc_num_outputs1)
fc_layer1 = tf.nn.dropout(fc_layer1, keep_prob)
fc_num_outputs2 = 512
fc_layer2 = fully_conn(fc_layer1, fc_num_outputs2)
fc_layer2 = tf.nn.dropout(fc_layer2, keep_prob)
# TODO: Apply an Output Layer
# Set this to the number of classes
# Function Definition from Above:
# output(x_tensor, num_outputs)
num_outputs = 10
nn_output = output(fc_layer2, num_outputs)
print('fc_num_outputs1:\t{0}'.format(fc_num_outputs1))
print('fc_num_outputs2:\t{0}'.format(fc_num_outputs2))
print('num_outputs:\t\t{0}'.format(num_outputs))
print('')
# TODO: return output
return nn_output
"""
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)
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 inputy
for labelskeep_prob
for keep probability for dropoutThis 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 [13]:
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={keep_prob: keep_probability, x: feature_batch, y: label_batch})
pass
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_train_nn(train_neural_network)
In [14]:
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
loss = session.run(cost, feed_dict={ x: feature_batch, y: label_batch, keep_prob: 1.0 })
valid_accuracy = session.run(accuracy, feed_dict={ x: valid_features[0:400], y: valid_labels[0:400], keep_prob: 1.0 })
print('Loss: %.6f' %loss, end=' ')
print('Validation Accuracy: %.6f' %valid_accuracy)
pass
Tune the following parameters:
epochs
to the number of iterations until the network stops learning or start overfittingbatch_size
to the highest number that your machine has memory for. Most people set them to common sizes of memory:keep_probability
to the probability of keeping a node using dropout
In [15]:
# TODO: Tune Parameters
epochs = 20
batch_size = 256
keep_probability = 0.5
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.
0902上午开始,因为这个activation_fn=None,导致神经网络发散。我用keras搭了一个一摸一样的网络,收拾收敛的,但是这个网络不收敛,估计是哪里实现错了,可以帮忙看一下为什么网络会发散吗?
【CodeReview170905】 170905-19:34发现函数one_hot_encode()实现错了,本来应该是0-9,也就是range(1,10),而我直接写成了[1,2,3,4,5,6,7,8,9,10],导致错误,进一步地导致网络发散。
In [16]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
print('Checking the Training on a Single Batch...')
with tf.Session() 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)
In [17]:
"""
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)
In [18]:
"""
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()
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. That's because there are many more techniques that can be applied to your model and we recemmond that once you are done with this project, you explore!
When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "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.
你也许会觉得奇怪,为什么你的准确率总是提高不上去。对于简单的 CNN 网络而言,50% 并非是很差的表现。纯粹的猜测只会得到 10% 的准确率(因为一共有 10 类)。这是因为还有许多许多能够应用到你模型的技巧。在你做完了该项目之后,你可以探索探索我们给你推荐的一些方法。
在提交项目前,请确保你在运行了所有的 cell 之后保存了项目。将项目储存为 "image_classification.ipynb" 并导出为一个 HTML 文件。你可以再菜单栏中选择 File -> Download as 进行导出。请将 "helper.py" 及 "problem_unittests.py" 文件也放在你的提交文件中。
In [ ]: