In [1]:

    

import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np

#Adding Seed so that random initialization is consistent
from numpy.random import seed
seed(1)
from tensorflow import set_random_seed
set_random_seed(2)


batch_size = 20

#Prepare input data
classes = ['clite','non_clite']
num_classes = len(classes)

# 20% of the data will automatically be used for validation
validation_size = 0.2
img_size = 128
num_channels = 3
train_path='training_data'

# We shall load all the training and validation images and labels into memory using openCV and use that during training
data = dataset.read_train_sets(train_path, img_size, classes, validation_size=validation_size)


print("Complete reading input data. Will Now print a snippet of it")
print("Number of files in Training-set:\t\t{}".format(len(data.train.labels)))
print("Number of files in Validation-set:\t{}".format(len(data.valid.labels)))



session = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, img_size,img_size,num_channels], name='x')

## labels
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)



##Network graph params
filter_size_conv1 = 3 
num_filters_conv1 = 32

filter_size_conv2 = 3
num_filters_conv2 = 32

filter_size_conv3 = 3
num_filters_conv3 = 64

filter_size_conv4 = 3
num_filters_conv4 = 64


fc_layer_size = 128

def create_weights(shape):
    return tf.Variable(tf.truncated_normal(shape, stddev=0.05))

def create_biases(size):
    return tf.Variable(tf.constant(0.05, shape=[size]))



def create_convolutional_layer(input,
               num_input_channels, 
               conv_filter_size,        
               num_filters):  
    
    ## We shall define the weights that will be trained using create_weights function.
    weights = create_weights(shape=[conv_filter_size, conv_filter_size, num_input_channels, num_filters])
    ## We create biases using the create_biases function. These are also trained.
    biases = create_biases(num_filters)

    ## Creating the convolutional layer
    layer = tf.nn.conv2d(input=input,
                     filter=weights,
                     strides=[1, 1, 1, 1],
                     padding='SAME')

    layer += biases

    ## We shall be using max-pooling.  
    layer = tf.nn.max_pool(value=layer,
                            ksize=[1, 2, 2, 1],
                            strides=[1, 2, 2, 1],
                            padding='SAME')
    ## Output of pooling is fed to Relu which is the activation function for us.
    layer = tf.nn.relu(layer)

    return layer

    

def create_flatten_layer(layer):
    #We know that the shape of the layer will be [batch_size img_size img_size num_channels] 
    # But let's get it from the previous layer.
    layer_shape = layer.get_shape()

    ## Number of features will be img_height * img_width* num_channels. But we shall calculate it in place of hard-coding it.
    num_features = layer_shape[1:4].num_elements()

    ## Now, we Flatten the layer so we shall have to reshape to num_features
    layer = tf.reshape(layer, [-1, num_features])

    return layer


def create_fc_layer(input,          
             num_inputs,    
             num_outputs,
             use_relu=True):
    
    #Let's define trainable weights and biases.
    weights = create_weights(shape=[num_inputs, num_outputs])
    biases = create_biases(num_outputs)

    # Fully connected layer takes input x and produces wx+b.Since, these are matrices, we use matmul function in Tensorflow
    layer = tf.matmul(input, weights) + biases
    if use_relu:
        layer = tf.nn.relu(layer)

    return layer


layer_conv1 = create_convolutional_layer(input=x,
               num_input_channels=num_channels,
               conv_filter_size=filter_size_conv1,
               num_filters=num_filters_conv1)
layer_conv2 = create_convolutional_layer(input=layer_conv1,
               num_input_channels=num_filters_conv1,
               conv_filter_size=filter_size_conv2,
               num_filters=num_filters_conv2)

layer_conv3= create_convolutional_layer(input=layer_conv2,
               num_input_channels=num_filters_conv2,
               conv_filter_size=filter_size_conv3,
               num_filters=num_filters_conv3)


layer_conv4= create_convolutional_layer(input=layer_conv3,
               num_input_channels=num_filters_conv3,
               conv_filter_size=filter_size_conv4,
               num_filters=num_filters_conv4)
          
layer_flat = create_flatten_layer(layer_conv4)

layer_fc1 = create_fc_layer(input=layer_flat,
                     num_inputs=layer_flat.get_shape()[1:4].num_elements(),
                     num_outputs=fc_layer_size,
                     use_relu=True)

layer_fc2 = create_fc_layer(input=layer_fc1,
                     num_inputs=fc_layer_size,
                     num_outputs=num_classes,
                     use_relu=False) 

y_pred = tf.nn.softmax(layer_fc2,name='y_pred')

y_pred_cls = tf.argmax(y_pred, dimension=1)
session.run(tf.global_variables_initializer())
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,
                                                    labels=y_true)
cost = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


session.run(tf.global_variables_initializer()) 


def show_progress(epoch, feed_dict_train, feed_dict_validate, val_loss):
    acc = session.run(accuracy, feed_dict=feed_dict_train)
    val_acc = session.run(accuracy, feed_dict=feed_dict_validate)
    msg = "Training Epoch {0} --- Training Accuracy: {1:>6.1%}, Validation Accuracy: {2:>6.1%},  Validation Loss: {3:.3f}"
    print(msg.format(epoch + 1, acc, val_acc, val_loss))

total_iterations = 0

saver = tf.train.Saver()


def train(num_iteration):
    global total_iterations
    
    for i in range(total_iterations,
                   total_iterations + num_iteration):

        x_batch, y_true_batch, _, cls_batch = data.train.next_batch(batch_size)
        x_valid_batch, y_valid_batch, _, valid_cls_batch = data.valid.next_batch(batch_size)

        
        feed_dict_tr = {x: x_batch,
                           y_true: y_true_batch}
        feed_dict_val = {x: x_valid_batch,
                              y_true: y_valid_batch}

        session.run(optimizer, feed_dict=feed_dict_tr)

        if i % int(data.train.num_examples/batch_size) == 0: 
            val_loss = session.run(cost, feed_dict=feed_dict_val)
            epoch = int(i / int(data.train.num_examples/batch_size))    
            
            show_progress(epoch, feed_dict_tr, feed_dict_val, val_loss)
            saver.save(session, 'clite-model') 


    total_iterations += num_iteration

train(num_iteration=3000)


    

    




Going to read training images
Now going to read clite files (Index: 0)
Now going to read non_clite files (Index: 1)
Complete reading input data. Will Now print a snippet of it
Number of files in Training-set:		804
Number of files in Validation-set:	201
Training Epoch 1 --- Training Accuracy:  80.0%, Validation Accuracy:  75.0%,  Validation Loss: 0.642
Training Epoch 2 --- Training Accuracy:  80.0%, Validation Accuracy:  75.0%,  Validation Loss: 0.439
Training Epoch 3 --- Training Accuracy: 100.0%, Validation Accuracy:  95.0%,  Validation Loss: 0.135
Training Epoch 4 --- Training Accuracy: 100.0%, Validation Accuracy:  95.0%,  Validation Loss: 0.103
Training Epoch 5 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.052
Training Epoch 6 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.047
Training Epoch 7 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.062
Training Epoch 8 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.057
Training Epoch 9 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.052
Training Epoch 10 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.048
Training Epoch 11 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.043
Training Epoch 12 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.040
Training Epoch 13 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.037
Training Epoch 14 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.035
Training Epoch 15 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.030
Training Epoch 16 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.028
Training Epoch 17 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.026
Training Epoch 18 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.025
Training Epoch 19 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.023
Training Epoch 20 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.022
Training Epoch 21 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.021
Training Epoch 22 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.021
Training Epoch 23 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.021
Training Epoch 24 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.020
Training Epoch 25 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.018
Training Epoch 26 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.016
Training Epoch 27 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.013
Training Epoch 28 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.011
Training Epoch 29 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.006
Training Epoch 30 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.003
Training Epoch 31 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 32 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 33 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 34 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 35 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 36 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 37 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.001
Training Epoch 38 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 39 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 40 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 41 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 42 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 43 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 44 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 45 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 46 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 47 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 48 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 49 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 50 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 51 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 52 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 53 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 54 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 55 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 56 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 57 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 58 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 59 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 60 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 61 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 62 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 63 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 64 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 65 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 66 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 67 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 68 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 69 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 70 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 71 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 72 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 73 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 74 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000
Training Epoch 75 --- Training Accuracy: 100.0%, Validation Accuracy: 100.0%,  Validation Loss: 0.000

In [ ]: