I have been trying to develop a CNN model for image classification. I am new to tensorflow and getting help from the following books
Learning.TensorFlow.A.Guide.to.Building.Deep.Learning.Systems
TensorFlow For Machine Intelligence by Sam Abrahams
For the past few weeks I have been working to develop a good model but I always get the same prediction. I have tried many different architectures but no luck!
Lately I decided to test my model with CIFAR-10 dataset and using the exact same model as given in the Learning Tensorflow book. But the outcome was same (same class for every image) even after training for 50K steps.
Here is highlight of my model and code.
1.) Downloaded CIFAR-10 image sets, converted them into tfrecord files with labels(labels are string for each category of CIFAR-10 in the tfrecord file) each for training and test set.
2) Reading the images from tfrecord file and generating random shuffle batch of size 100.
3) Converting the label from string to the integer32 type from 0-9 each for given category
4) Pass the training and test batches to the network and getting the output of [batch_size , num_class] size.
5) Train the model using Adam optimizer and softmax cross entropy loss function (Have tried gradient optimizer as well)
7) evaluate the model for test batches before and after the training.
8) Getting the same prediction for entire data set (But different every time I re run the code to try again)
Is there something wrong I am doing here? I would appreciate if someone could help me out with this problem.
Note - My approach of converting images and labels into tfrecord could be unusual but believe me I have come up with this idea from the books I mentioned earlier.
My code for the problem:
import tensorflow as tf
import numpy as np
import _datetime as dt
import PIL
# The glob module allows directory listing
import glob
import random
from itertools import groupby
from collections import defaultdict
H , W = 32 , 32 # Height and weight of the image
C = 3 # Number of channels
sessInt = tf.InteractiveSession()
# Read file and return the batches of the input data
def get_Batches_From_TFrecord(tf_record_filenames_list, batch_size):
# Match and load all the tfrecords found in the specified directory
tf_record_filename_queue = tf.train.string_input_producer(tf_record_filenames_list)
# It may have more than one example in them.
tf_record_reader = tf.TFRecordReader()
tf_image_name, tf_record_serialized = tf_record_reader.read(tf_record_filename_queue)
# The label and image are stored as bytes but could be stored as int64 or float64 values in a
# serialized tf.Example protobuf.
tf_record_features = tf.parse_single_example(tf_record_serialized,
features={'label': tf.FixedLenFeature([], tf.string),
'image': tf.FixedLenFeature([], tf.string), })
# Using tf.uint8 because all of the channel information is between 0-255
tf_record_image = tf.decode_raw(tf_record_features['image'], tf.uint8)
try:
# Reshape the image to look like the input image
tf_record_image = tf.reshape(tf_record_image, [H, W, C])
except:
print(tf_image_name)
tf_record_label = tf.cast(tf_record_features['label'], tf.string)
'''
#Check the image and label
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sessInt, coord=coord)
label = tf_record_label.eval().decode()
print(label)
image = PIL.Image.fromarray(tf_record_image.eval())
image.show()
coord.request_stop()
coord.join(threads)
'''
# creating a batch to feed the data
min_after_dequeue = 10 * batch_size
capacity = min_after_dequeue + 5 * batch_size
# Shuffle examples while feeding in the queue
image_batch, label_batch = tf.train.shuffle_batch([tf_record_image, tf_record_label], batch_size=batch_size,
capacity=capacity, min_after_dequeue=min_after_dequeue)
# Sequential feed in the examples in the queue (Don't shuffle)
# image_batch, label_batch = tf.train.batch([tf_record_image, tf_record_label], batch_size=batch_size, capacity=capacity)
# Converting the images to a float to match the expected input to convolution2d
float_image_batch = tf.image.convert_image_dtype(image_batch, tf.float32)
string_label_batch = label_batch
return float_image_batch, string_label_batch
#Count the number of images in the tfrecord file
def number_of_records(tfrecord_file_name):
count = 0
record_iterator = tf.python_io.tf_record_iterator(path = tfrecord_file_name)
for record in record_iterator:
count+=1
return count
def get_num_of_samples(tfrecords_list):
total_samples = 0
for tfrecord in tfrecords_list:
total_samples += number_of_records(tfrecord)
return total_samples
# Provide the input tfrecord names in a list
train_filenames = ["./TFRecords/cifar_train.tfrecord"]
test_filename = ["./TFRecords/cifar_test.tfrecord"]
num_train_samples = get_num_of_samples(train_filenames)
num_test_samples = get_num_of_samples(test_filename)
print("Number of Training samples: ", num_train_samples)
print("Number of Test samples: ", num_test_samples)
'''
IMP Note : (Batch_size * Training_Steps) should be at least greater than (2*Number_of_samples) for shuffling of batches
'''
train_batch_size = 100
# Total number of batches for input records
# Note - Num of samples in the tfrecord file can be determined by the tfrecord iterator.
# Batch size for test samples
test_batch_size = 50
train_image_batch, train_label_batch = get_Batches_From_TFrecord(train_filenames, train_batch_size)
test_image_batch, test_label_batch = get_Batches_From_TFrecord(test_filename, test_batch_size)
# Definition of the convolution network which returns a single neuron for each input image in the batch
# Define a placeholder for keep probability in dropout
# (Dropout should only use while training, for testing dropout should be always 1.0)
fc_prob = tf.placeholder(tf.float32)
conv_prob = tf.placeholder(tf.float32)
#Helper function to add learned filters(images) into tensorboard summary - for a random input in the batch
def add_filter_summary(name, filter_tensor):
rand_idx = random.randint(0,filter_tensor.get_shape()[0]-1) #Choose any random number from[0,batch_size)
#dispay_filter = filter_tensor[random.randint(0,filter_tensor.get_shape()[3])]
dispay_filter = filter_tensor[5] #keeping the index fix for consistency in visualization
with tf.name_scope("Filter_Summaries"):
img_summary = tf.summary.image(name, tf.reshape(dispay_filter,[-1 , filter_tensor.get_shape()[1],filter_tensor.get_shape()[1],1] ), max_outputs = 500)
# Helper functions for the network
def weight_initializer(shape):
weights = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(weights)
def bias_initializer(shape):
biases = tf.constant(0.1, shape=shape)
return tf.Variable(biases)
def conv2d(input, weights, stride):
return tf.nn.conv2d(input, filter=weights, strides=[1, stride, stride, 1], padding="SAME")
def pool_layer(input, window_size=2 , stride=2):
return tf.nn.max_pool(input, ksize=[1, window_size, window_size, 1], strides=[1, stride, stride, 1], padding='VALID')
# This is the actual layer we will use.
# Linear convolution as defined in conv2d, with a bias,
# followed by the ReLU nonlinearity.
def conv_layer(input, filter_shape , stride=1):
W = weight_initializer(filter_shape)
b = bias_initializer([filter_shape[3]])
return tf.nn.relu(conv2d(input, W, stride) + b)
# A standard full layer with a bias. Notice that here we didn’t add the ReLU.
# This allows us to use the same layer for the final output,
# where we don’t need the nonlinear part.
def full_layer(input, out_size):
in_size = int(input.get_shape()[1])
W = weight_initializer([in_size, out_size])
b = bias_initializer([out_size])
return tf.matmul(input, W) + b
## Model fro the book learning tensorflow - for CIFAR data
def conv_network(image_batch, batch_size):
# Now create the model which returns the output neurons (eequals to the number of labels)
# as a final fully connecetd layer output. Which we can use as input to the softmax classifier
C1 , C2 , C3 = 30 , 50, 80 # Number of output features for each convolution layer
F1 = 500 # Number of output neuron for FC1 layer
#Add original image to tensorboard summary
add_filter_summary("Original" , image_batch)
# First convolutaion layer with 5x5 filter size and 32 filters
conv1 = conv_layer(image_batch, filter_shape=[3, 3, C, C1])
pool1 = pool_layer(conv1, window_size=2)
pool1 = tf.nn.dropout(pool1, keep_prob=conv_prob)
add_filter_summary("conv1" , pool1)
# Second convolutaion layer with 5x5 filter_size and 64 filters
conv2 = conv_layer(pool1, filter_shape=[5, 5, C1, C2])
pool2 = pool_layer(conv2, 2)
pool2 = tf.nn.dropout(pool2, keep_prob=conv_prob)
add_filter_summary("conv2" , pool2)
# Third convolution layer
conv3 = conv_layer(pool2, filter_shape=[5, 5, C2, C3])
# Since at this point the feature maps are of size 8×8 (following the first two poolings
# that each reduced the 32×32 pictures by half on each axis).
# This last pool layer pools each of the feature maps and keeps only the maximal value.
# The number of feature maps at the third block was set to 80,
# so at that point (following the max pooling) the representation is reduced to only 80 numbers
pool3 = pool_layer(conv3, window_size = 8 , stride=8)
pool3 = tf.nn.dropout(pool3, keep_prob=conv_prob)
add_filter_summary("conv3" , pool3)
# Reshape the output to feed to the FC layer
flatterned_layer = tf.reshape(pool3, [batch_size,
-1]) # -1 is to specify to use all the dimensions remaining in the input (other than batch_size).reshape(input , )
fc1 = tf.nn.relu(full_layer(flatterned_layer, F1))
full1_drop = tf.nn.dropout(fc1, keep_prob=fc_prob)
# Fully connected layer 2 (output layer)
final_Output = full_layer(full1_drop, 10)
return final_Output, tf.summary.merge_all()
# Now that architecture is created , next step is to create the classification model
# (to predict the output class of the input data)
# Here we have used Logistic regression (Sigmoid function) to predict the output because we have only rwo class.
# For multiple class problem - softmax is the best prediction function
# Prepare the inputs to the input
Train_X , img_summary = conv_network(train_image_batch, train_batch_size)
Test_X , _ = conv_network(test_image_batch, test_batch_size)
# Generate 0 based index for labels
Train_Y = tf.to_int32(tf.argmax(
tf.to_int32(tf.stack([tf.equal(train_label_batch, ["airplane"]), tf.equal(train_label_batch, ["automobile"]),
tf.equal(train_label_batch, ["bird"]),tf.equal(train_label_batch, ["cat"]),
tf.equal(train_label_batch, ["deer"]),tf.equal(train_label_batch, ["dog"]),
tf.equal(train_label_batch, ["frog"]),tf.equal(train_label_batch, ["horse"]),
tf.equal(train_label_batch, ["ship"]), tf.equal(train_label_batch, ["truck"]) ])), 0))
Test_Y = tf.to_int32(tf.argmax(
tf.to_int32(tf.stack([tf.equal(test_label_batch, ["airplane"]), tf.equal(test_label_batch, ["automobile"]),
tf.equal(test_label_batch, ["bird"]),tf.equal(test_label_batch, ["cat"]),
tf.equal(test_label_batch, ["deer"]),tf.equal(test_label_batch, ["dog"]),
tf.equal(test_label_batch, ["frog"]),tf.equal(test_label_batch, ["horse"]),
tf.equal(test_label_batch, ["ship"]), tf.equal(test_label_batch, ["truck"]) ])), 0))
# Y = tf.reshape(float_label_batch, X.get_shape())
# compute inference model over data X and return the result
# (using sigmoid function - as this function is the best to predict two class output)
# (For multiclass problem - Softmax is the bset prediction function)
def inference(X):
return tf.nn.softmax(X)
# compute loss over training data X and expected outputs Y
# Cross entropy function is the best suited for loss calculation (Than the squared error function)
# Get the second column of the input to get only the features
def loss(X, Y):
return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=X, labels=Y))
# train / adjust model parameters according to computed total loss (using gradient descent)
def train(total_loss, learning_rate):
return tf.train.AdamOptimizer(learning_rate).minimize(total_loss)
# evaluate the resulting trained model with dropout probability (Ideally 1.0 for testing)
def evaluate(sess, X, Y, dropout_prob):
# predicted = tf.cast(inference(X) > 0.5 , tf.float32)
#print("\nNetwork output:")
#print(sess.run(inference(X) , feed_dict={conv_prob:1.0 , fc_prob:1.0}))
# Inference contains the predicted probability of each class for each input image.
# The class having higher probability is the prediction of the network. y_pred_cls = tf.argmax(y_pred, dimension=1)
predicted = tf.cast(tf.argmax(X, 1), tf.int32)
#print("\npredicted labels:")
#print(sess.run(predicted , feed_dict={conv_prob:1.0 , fc_prob:1.0}))
#print("\nTrue Labels:")
#print(sess.run(Y , feed_dict={conv_prob:1.0 , fc_prob:1.0}))
batch_accuracy = tf.reduce_mean(tf.cast(tf.equal(predicted, Y), tf.float32))
# calculate the mean of the accuracies of the each batch (iteration)
# No. of iteration Iteration should cover the (test_batch_size * num_of_iteration ) >= (2* num_of_test_samples ) condition
total_accuracy = np.mean([sess.run(batch_accuracy, feed_dict={conv_prob:1.0 , fc_prob:1.0}) for i in range(250)])
print("Accuracy of the model(in %): {:.4f} ".format(100 * total_accuracy))
# create a saver class to save the training checkpoints
saver = tf.train.Saver(max_to_keep=10)
# Create tensorboard sumamry for loss function
with tf.name_scope("summaries"):
loss_summary = tf.summary.scalar("loss", loss(Train_X, Train_Y))
#merged = tf.summary.merge_all()
# Launch the graph in a session, setup boilerplate
with tf.Session() as sess:
log_writer = tf.summary.FileWriter('./logs', sess.graph)
total_loss = loss(Train_X, Train_Y)
train_op = train(total_loss, 0.001)
#Initialise all variables after defining all variables
tf.global_variables_initializer().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
print(sess.run(Train_Y))
print(sess.run(Test_Y))
evaluate(sess, Test_X, Test_Y,1.0)
# actual training loop------------------------------------------------------
training_steps = 50000
print("\nStarting to train model with", str(training_steps), " steps...")
to1 = dt.datetime.now()
for step in range(1, training_steps + 1):
# print(sess.run(train_label_batch))
sess.run([train_op], feed_dict={fc_prob: 0.5 , conv_prob:0.8}) # Pass the dropout value for training batch to the placeholder
# for debugging and learning purposes, see how the loss gets decremented thru training steps
if step % 100 == 0:
# print("\n")
# print(sess.run(train_label_batch))
loss_summaries, img_summaries , Tloss = sess.run([loss_summary, img_summary, total_loss],
feed_dict={fc_prob: 0.5 , conv_prob:0.8}) # evaluate total loss to add it in summary object
log_writer.add_summary(loss_summaries, step) # add summary for each step
log_writer.add_summary(img_summaries, step)
print("Step:", step, " , loss: ", Tloss)
if step%2000 == 0:
saver.save(sess, "./Models/BookLT_CIFAR", global_step=step, latest_filename="model_chkpoint")
print("\n")
evaluate(sess, Test_X, Test_Y,1.0)
saver.save(sess, "./Models/BookLT_CIFAR", global_step=step, latest_filename="model_chkpoint")
to2 = dt.datetime.now()
print("\nTotal Trainig time Elapsed: ", str(to2 - to1))
# once the training is complete, evaluate the model with test (validation set)-------------------------------------------
# Restore the model file and perform the testing
#saver.restore(sess, "./Models/BookLT3_CIFAR-15000")
print("\nPost Training....")
# Performs Evaluation of model on batches of test samples
# In order to evaluate entire test set , number of iteration should be chosen such that ,
# (test_batch_size * num_of_iteration ) >= (2* num_of_test_samples )
evaluate(sess, Test_X, Test_Y,1.0) # Evaluate multiple batch of test data set (randomly chosen by shuffle train batch queue)
evaluate(sess, Test_X, Test_Y,1.0)
evaluate(sess, Test_X, Test_Y,1.0)
coord.request_stop()
coord.join(threads)
sess.close()
