Related
I'm working on this classification program where i'm training my model to predict whether the object is a nut or a screw. I created my own dataset since i did not get any. I trained my model but i'm not getting correct predictions. Probability of values go beyond 1, basically i get garbage values.
I get this predicted value: [[9.990779e-01 9.220659e-04]]
#Training code
import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np
import os
# 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 = os.listdir('training_set')
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_set'
# 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 = 32
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_flat = create_flatten_layer(layer_conv3)
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, 'C:\\Nutsbolts\\nuts-screws-model')
total_iterations += num_iteration
train(num_iteration=3000)
#Prediction code
import tensorflow as tf
import numpy as np
import os,glob,cv2
import sys,argparse
# First, pass the path of the image
dir_path = 'C:\\nutsbolts\\testing_set\\nuts'
image_path= 'nuts11.jpg'
filename = dir_path +'/' +image_path
image_size=128
num_channels=3
images = []
# Reading the image using OpenCV
image = cv2.imread(filename)
# Resizing the image to our desired size and preprocessing will be done
exactly as done during training
image = cv2.resize(image, (image_size, image_size),0,0, cv2.INTER_LINEAR)
images.append(image)
images = np.array(images, dtype=np.uint8)
images = images.astype('float32')
images = np.multiply(images, 1.0/255.0)
#The input to the network is of shape [None image_size image_size
num_channels]. Hence we reshape.
x_batch = images.reshape(1, image_size,image_size,num_channels)
## Let us restore the saved model
sess = tf.Session()
# Step-1: Recreate the network graph. At this step only graph is created.
saver = tf.train.import_meta_graph('nuts-screws-model.meta')
# Step-2: Now let's load the weights saved using the restore method.
saver.restore(sess, tf.train.latest_checkpoint('./'))
# Accessing the default graph which we have restored
graph = tf.get_default_graph()
# Now, let's get hold of the op that we can be processed to get the output.
# In the original network y_pred is the tensor that is the prediction of the
network
y_pred = graph.get_tensor_by_name("y_pred:0")
## Let's feed the images to the input placeholders
x= graph.get_tensor_by_name("x:0")
y_true = graph.get_tensor_by_name("y_true:0")
y_test_images = np.zeros((1, len(os.listdir('testing_set'))))
### Creating the feed_dict that is required to be fed to calculate y_pred
feed_dict_testing = {x: x_batch, y_true: y_test_images}
result=sess.run(y_pred, feed_dict=feed_dict_testing)
# result is of this format [probabiliy_of_nuts probability_of_screws]
print(result)
9.990779e-01 actually is below 1. You could see it as: 9.990779 * (the exponential of -01).
I am using tensorflow version 1.5 on Windows 10. I am using the Tensorflow slim model of Inception V4 network which has been picked up from the Github page, using their pretrained weights and adding my own layers at the end to classify 120 different objects.The size of my training dataset is around 10,000 images each of 299*299*3. This is the complete code except the lines containing the import modules and dataset paths.
tf.logging.set_verbosity(tf.logging.INFO)
with slim.arg_scope(inception_blocks_v4.inception_v4_arg_scope()):
X_input = tf.placeholder(tf.float32, shape = (None, image_size, image_size, 3))
Y_label = tf.placeholder(tf.float32, shape = (None, num_classes))
targets = convert_to_onehot(labels_dir, no_of_features = num_classes)
targets = tf.convert_to_tensor(targets, dtype = tf.float32)
Images = [] #TO STORE THE RESIZED IMAGES IN THE FORM OF LIST TO PASS IT TO tf.train.batch()
images = glob.glob(images_file_path)
i = 0
for my_img in images:
image = mpimg.imread(my_img)[:, :, :3]
image = tf.convert_to_tensor(image, dtype = tf.float32)
Images.append(image)
logits, end_points = inception_blocks_v4.inception_v4(inputs = X_input, num_classes = pre_num_classes, is_training = True, create_aux_logits= False)
pretrained_weights = slim.assign_from_checkpoint_fn(ckpt_dir, slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
pretrained_weights(sess)
#MY LAYERS, add bias as well
my_layer = slim.fully_connected(logits, 560, activation_fn=tf.nn.relu, scope='myLayer1', weights_initializer = tf.truncated_normal_initializer(stddev = 0.001), weights_regularizer=slim.l2_regularizer(0.00005),biases_initializer = tf.truncated_normal_initializer(stddev=0.001), biases_regularizer=slim.l2_regularizer(0.00005))
my_layer = slim.dropout(my_layer, keep_prob = 0.6, scope = 'myLayer2')
my_layer = slim.fully_connected(my_layer, num_classes,activation_fn = tf.nn.relu,scope= 'myLayer3', weights_initializer = tf.truncated_normal_initializer(stddev=0.001), weights_regularizer=slim.l2_regularizer(0.00005), biases_initializer = tf.truncated_normal_initializer(stddev=0.001), biases_regularizer=slim.l2_regularizer(0.00005))
my_layer_logits = slim.fully_connected(my_layer, num_classes, activation_fn=None,scope='myLayer4')
loss = tf.losses.softmax_cross_entropy(onehot_labels = Y_label, logits = my_layer_logits)
optimizer = tf.train.AdamOptimizer(learning_rate=0.0001)
train_op = optimizer.minimize(loss)
batch_size = 8
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100):
images, labels = tf.train.batch([Images, targets], batch_size = batch_size, num_threads = 1, capacity = (4*batch_size), enqueue_many=True)
print (images) #To check their shape
print (labels)
train_op.run(feed_dict = {X_input:images.eval(session = sess) ,Y_label:labels.eval(session = sess)})
print (i)
I used the print(i) statement to keep track of how many epochs are done. After running the script for more than 3 hours, not even a single epoch of training is completed. It seems that it gets stuck at train_op.run() step. I don't know what is the problem.
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()
Here is the screenshot of my Pre training result:
Here is the screenshot of the result during training:
Hereis the screenshot of the Post training result
I did not run the code to verify that this is the only issue, but here is one important issue. When classifying, you should use one-hot encoding for your labels. Meaning that if you have 3 classes, you want your labels to be [1, 0, 0] for class 1, [0, 1, 0] for class 2, [0, 0, 1] for class 3. Your approach of using 1, 2, and 3 as labels leads to various issues. For examples, the network is penalized more for predicting class 1 versus predicting class 2 for an image from class 3. TensorFlow functions like tf.nn.softmax_cross_entropy_with_logits work with such representations.
Here is the basic example of correctly using one_hot labels to compute loss: https://github.com/tensorflow/tensorflow/blob/r1.4/tensorflow/examples/tutorials/mnist/mnist_softmax.py
Here is how the one_hot label is constructed for mnist digits:
https://github.com/tensorflow/tensorflow/blob/438604fc885208ee05f9eef2d0f2c630e1360a83/tensorflow/contrib/learn/python/learn/datasets/mnist.py#L69
I have undertaken a project in which I must use a convolutional network which will output an image instead of logit class predictors. For this purpose I've adapter the CNN code I downloaded from https://github.com/aymericdamien/TensorFlow-Examples
My input data are 64x64 images read from a binary file. The binary file is comprised of records of two 64x64 images in sequence. I need to minimize a cost function which is the difference of the second image and the 64x64 output of the network.
This is the module I've written to read the input data:
import tensorflow as tf
# various initialization variables
BATCH_SIZE = 128
N_FEATURES = 9
# This function accepts a tensor of size [batch_size, 2 ,record_size]
# and segments in into two tensors of size [batch_size, record] along the second dimension
# IMPORTANT: to be executed within an active session
def segment_batch(batch_p, batch_size, n_input):
batch_xs = tf.slice(batch_p, [0,0,0], [batch_size,1,n_input]) # optical data tensor
batch_ys = tf.slice(batch_p, [0,1,0], [batch_size,1,n_input]) # GT data tensor
optical = tf.reshape([batch_xs], [batch_size, n_input])
gt = tf.reshape([batch_ys], [batch_size, n_input])
return [optical, gt]
def batch_generator(filenames, record_size, batch_size):
""" filenames is the list of files you want to read from.
record_bytes: The size of a record in bytes
batch_size: The size a data batch (examples/batch)
"""
filename_queue = tf.train.string_input_producer(filenames)
reader = tf.FixedLengthRecordReader(record_bytes=2*record_size) # record size is double the value given (optical + ground truth images)
_, value = reader.read(filename_queue)
# read in the data (UINT8)
content = tf.decode_raw(value, out_type=tf.uint8)
# The bytes read represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
# read optical data slice
depth_major = tf.reshape(
tf.strided_slice(content, [0],
[record_size]),
[1, 64, 64])
# read GT (ground truth) data slice
depth_major1 = tf.reshape(
tf.strided_slice(content, [record_size],
[2*record_size]),
[1, 64, 64])
# Optical data
# Convert from [depth, height, width] to [height, width, depth].
uint8image = tf.transpose(depth_major, [1, 2, 0])
uint8image = tf.reshape(uint8image, [record_size]) # reshape into a single-dimensional vector
uint8image = tf.cast(uint8image, tf.float32) # cast into a float32
uint8image = uint8image/255 # normalize
# Ground Truth data
# Convert from [depth, height, width] to [height, width, depth].
gt_image = tf.transpose(depth_major1, [1, 2, 0])
gt_image = tf.reshape(gt_image, [record_size]) # reshape into a single-dimensional vector
gt_image = tf.cast(gt_image, tf.float32) # cast into a float32
gt_image = gt_image/255 # normalize
# stack them into a single features tensor
features = tf.stack([uint8image, gt_image])
# minimum number elements in the queue after a dequeue, used to ensure
# that the samples are sufficiently mixed
# I think 10 times the BATCH_SIZE is sufficient
min_after_dequeue = 10 * batch_size
# the maximum number of elements in the queue
capacity = 20 * batch_size
# shuffle the data to generate BATCH_SIZE sample pairs
data_batch = tf.train.shuffle_batch([features], batch_size=batch_size,
capacity=capacity, min_after_dequeue=min_after_dequeue)
return data_batch
This is the main code of my implementation:
from __future__ import print_function
# Various initialization variables
DATA_PATH_OPTICAL_TRAIN = 'data/building_ground_truth_for_training.bin'
DATA_PATH_EVAL = 'data/building_ground_truth_for_eval.bin'
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import time
# custom imports
import data_reader2
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 128
epochs = 10
display_step = 10
rows = 64
cols = 64
# Network Parameters
n_input = 4096 # optical image data (img shape: 64*64)
n_classes = 4096 # output is an image of same resolution as initial image
dropout = 0.75 # Dropout, probability to keep units
# input data parameters
record_size = 64**2
total_bytes_of_optical_binary_file = 893329408 # total size of binary file containing training data ([64z64 optical] [64x64 GT])
# create the data batches (queue)
# Accepts two parameters. The tensor containing the binary files and the size of a record
data_batch = data_reader2.batch_generator([DATA_PATH_OPTICAL_TRAIN],record_size, batch_size) # train set
data_batch_eval = data_reader2.batch_generator([DATA_PATH_EVAL],record_size, batch_size) # train set
##############################################################
######################### FUNCTIONS ##########################
##############################################################
# extract optical array from list
# A helper function. Data returned from segment_batch is a list which contains two arrays.
# The first array contains the optical data while the second contains the ground truth data
def extract_optical_from_list(full_batch):
optical = full_batch[0] # extract array from list
return optical
# extract ground truth array from list
# A helper function. Data returned from segment_batch is a list which contains two arrays.
# The first array contains the optical data while the second contains the ground truth data
def extract_gt_from_list(full_batch):
gt = full_batch[1] # extract array from list
return gt
# This function accepts a tensor of size [batch_size, 2 ,record_size]
# and segments in into two tensors of size [batch_size, record] along the second dimension
# IMPORTANT: to be executed within an active session
def segment_batch(batch_p):
batch_xs = tf.slice(batch_p, [0,0,0], [batch_size,1,n_input]) # optical data tensor
batch_ys = tf.slice(batch_p, [0,1,0], [batch_size,1,n_input]) # GT data tensor
optical = tf.reshape([batch_xs], [batch_size, n_input])
gt = tf.reshape([batch_ys], [batch_size, n_input])
return [optical, gt]
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture into 64x64 subimages [rows, rows, cols, channels]
x1 = tf.reshape(x, shape=[-1, rows, cols, 1]) # this is the 4-dimensional that tf.conv2D expects as Input
# Convolution Layer
conv1 = conv2d(x1, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
#fc1 = tf.nn.dropout(fc1, dropout)
# Output image (edge), prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
# Add print operation
out = tf.Print(out, [out], message="This is out: ")
return [out, x]
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([16*16*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
####################################################################
##################### PLACEHOLDERS #################################
####################################################################
# tf Graph input (only pictures)
X = tf.placeholder_with_default(extract_optical_from_list(segment_batch(data_batch)), [batch_size, n_input])
####################################################################
##################### END OF PLACEHOLDERS ##########################
####################################################################
# tf Graph input
keep_prob = tf.Variable(dropout) #dropout (keep probability)
# Construct model
pred = conv_net(extract_optical_from_list(X), weights, biases, keep_prob) # x[0] is the optical data
y_true = extract_gt_from_list(extract_gt_from_list(X)) # y_true is the ground truth data
# Define loss and optimizer
cost = tf.reduce_mean(tf.pow(y_true - pred[0], 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
print("Optimizing")
sess.run(optimizer)
print("Iter " + str(step*batch_size))
step += 1
print("Optimization Finished!")
After a lot of tweaking with the shape of the tensors I managed to fix the Syntax errors. Unfortunately, it just hangs the moment it starts executing the optimization part of the Graph. Since I have no way to debug this (found very scarce info on using the Tensorflow debugger) I'm really at a loss as to what has gone wrong! If someone with more experience on Tensorflow can point out what is wrong with this code it would help me a lot.
Thanks, in advance
you need to start the queue runner to get the data for optimizing from the queue.
....
coord = tf.train.Coordinator()
with tf.Session() as sess:
sess.run(init)
tf.train.start_queue_runners(sess=sess, coord=coord)
....
# also use tf.nn.sparse_softmax_cross_entropy_with_logits for cost
I know that this is a very broad question, but I have asked many other questions and I have still been unable to properly implement a simple dynamic-k max pooling convolutional neural network as described in this paper. Currently, I am trying to modify the code from this tutorial. I believe I have successfully implemented the dynamic-k part. However, my main problem is because the k value is different for each input, the tensors that are produced are different shapes. I have tried countless things to try and fix this (which is why you may see some funny reshaping), but I can't figure out how. I think that you'd need to pad each tensor to get them all to be the size of the biggest one, but I can't seem to get that to work. Here is my code (I am sorry, it is generally rather sloppy).
# train.py
import datetime
import time
import numpy as np
import os
import tensorflow as tf
from env.src.sentiment_analysis.dcnn.text_dcnn import TextDCNN
from env.src.sentiment_analysis.cnn import data_helpers as data_helpers
from tensorflow.contrib import learn
# Model Hyperparameters
tf.flags.DEFINE_integer("embedding_dim", 128, "Dimensionality of character embedding (default: 128)")
tf.flags.DEFINE_string("filter_sizes", "3,4,5", "Comma-separated filter sizes (default: '3,4,5')")
tf.flags.DEFINE_integer("num_filters", 128, "Number of filters per filter size (default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 0.0, "L2 regularizaion lambda (default: 0.0)")
# Training parameters
tf.flags.DEFINE_integer("batch_size", 256, "Batch Size (default: 64)")
tf.flags.DEFINE_integer("num_epochs", 200, "Number of training epochs (default: 200)")
tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)")
tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")
tf.flags.DEFINE_string("positive_file", "../rotten_tomatoes/rt-polarity.pos", "Location of the rt-polarity.pos file")
tf.flags.DEFINE_string("negative_file", "../rotten_tomatoes/rt-polarity.neg", "Location of the rt-polarity.neg file")
FLAGS = tf.flags.FLAGS
FLAGS._parse_flags()
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{} = {}".format(attr.upper(), value))
print("")
# Data Preparatopn
# Load data
print("Loading data...")
x_text, y = data_helpers.load_data_and_labels(FLAGS.positive_file, FLAGS.negative_file)
# Build vocabulary
max_document_length = max([len(x.split(" ")) for x in x_text])
vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length)
x = np.array(list(vocab_processor.fit_transform(x_text)))
x_arr = np.array(x_text)
seq_lens = []
for s in x_arr:
seq_lens.append(len(s.split(" ")))
# Randomly shuffle data
np.random.seed(10)
shuffle_indices = np.random.permutation(np.arange(len(y)))
x_shuffled = x[shuffle_indices]
y_shuffled = y[shuffle_indices]
# Split train/test set
x_train, x_dev = x_shuffled[:-1000], x_shuffled[-1000:]
y_train, y_dev = y_shuffled[:-1000], y_shuffled[-1000:]
print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev)))
# Training
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement
)
sess = tf.Session(config=session_conf)
with sess.as_default():
print("HERE")
print(x_train.shape)
dcnn = TextDCNN(
sequence_lengths=seq_lens,
sequence_length=x_train.shape[1],
num_classes=y_train.shape[1],
vocab_size=len(vocab_processor.vocabulary_),
embedding_size=FLAGS.embedding_dim,
filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
)
# The training procedure
global_step = tf.Variable(0, name="global_step", trainable=False)
optimizer = tf.train.AdamOptimizer(1e-4)
grads_and_vars = optimizer.compute_gradients(dcnn.loss)
train_op = optimizer.apply_gradients(grads_and_vars, global_step=global_step)
# Output directory for models and summaries
timestamp = str(int(time.time()))
out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
print("Writing to {}\n".format(out_dir))
# Summaries for loss and accuracy
loss_summary = tf.scalar_summary("loss", dcnn.loss)
acc_summary = tf.scalar_summary("accuracy", dcnn.accuracy)
# Summaries for training
train_summary_op = tf.merge_summary([loss_summary, acc_summary])
train_summary_dir = os.path.join(out_dir, "summaries", "train")
train_summary_writer = tf.train.SummaryWriter(train_summary_dir, sess.graph)
# Summaries for devs
dev_summary_op = tf.merge_summary([loss_summary, acc_summary])
dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
dev_summary_writer = tf.train.SummaryWriter(dev_summary_dir, sess.graph)
# Checkpointing
checkpoint_dir = os.path.abspath(os.path.join(out_dir, "checkpoints"))
checkpoint_prefix = os.path.join(checkpoint_dir, "model")
# TensorFlow assumes this directory already exsists so we need to create it
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
saver = tf.train.Saver(tf.all_variables())
# Write vocabulary
vocab_processor.save(os.path.join(out_dir, "vocab"))
# Initialize all variables
sess.run(tf.initialize_all_variables())
def train_step(x_batch, y_batch):
"""
A single training step.
Args:
x_batch: A batch of X training values.
y_batch: A batch of Y training values
Returns: void
"""
feed_dict = {
dcnn.input_x: x_batch,
dcnn.input_y: y_batch,
dcnn.dropout_keep_prob: FLAGS.dropout_keep_prob
}
# Execute train_op
_, step, summaries, loss, accuracy = sess.run(
[train_op, global_step, train_summary_op, dcnn.loss, dcnn.accuracy],
feed_dict
)
# Print and save to disk loss and accuracy of the current training batch
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
train_summary_writer.add_summary(summaries, step)
def dev_step(x_batch, y_batch, writer=None):
"""
Evaluates a model on a dev set.
Args:
x_batch: A batch of X training values.
y_batch: A batch of Y training values.
writer: The writer to use to record the loss and accuracy
Returns: void
"""
feed_dict = {
dcnn.input_x: x_batch,
dcnn.input_y: y_batch,
dcnn.dropout_keep_prob : 1.0
}
step, summaries, loss, accuracy = sess.run(
[global_step, dev_summary_op, dcnn.loss, dcnn.accuracy],
feed_dict
)
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
if writer:
writer.add_summary(summaries, step)
# Generate batches
batches = data_helpers.batch_iter(list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs)
# Training loop. For each batch...
for batch in batches:
x_batch, y_batch = zip(*batch)
train_step(x_batch, y_batch)
current_step = tf.train.global_step(sess, global_step)
if current_step % FLAGS.evaluate_every == 0:
print("\nEvaluation:")
dev_step(x_dev, y_dev, writer=dev_summary_writer)
print("")
if current_step % FLAGS.checkpoint_every == 0:
path = saver.save(sess, checkpoint_prefix, global_step=current_step)
print("Saved model checkpoint to {}\n".format(path))
And here is the actual DCNN class:
import tensorflow as tf
class TextDCNN(object):
"""
A CNN for NLP tasks. Architecture is as follows:
Embedding layer, conv layer, max-pooling and softmax layer
"""
def __init__(self, sequence_lengths, sequence_length, num_classes, vocab_size, embedding_size, filter_sizes, num_filters):
"""
Makes a new CNNClassifier
Args:
sequence_length: The length of each sentence
num_classes: Number of classes in the output layer (positive and negative would be 2 classes)
vocab_size: The size of the vocabulary, needed to define the size of the embedding layer
embedding_size: Dimensionality of the embeddings
filter_sizes: Number of words the convolutional filters will cover, there will be num_filters for each size
specified.
num_filters: The number of filters per filter size.
Returns: A new CNNClassifier with the given parameters.
"""
# Define the inputs and the dropout
print("SEQL")
print(sequence_length)
self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y")
self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")
# Runs the operations on the CPU and organizes them into an embedding scope
with tf.device("/cpu:0"), tf.name_scope("embedding"):
W = tf.Variable( # Make a 4D tensor to store batch, width, height, and channel
tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
name="W"
)
self.embedded_chars = tf.nn.embedding_lookup(W, self.input_x)
self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# Conv layer
filter_shape = [filter_size, embedding_size, 1, num_filters]
# W is the filter matrix
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv2d(
self.embedded_chars_expanded,
W,
strides=[1, 1, 1, 1],
padding="VALID",
name="conv"
)
# Apply nonlinearity
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# Max-pooling layer over the outputs
print(sequence_lengths[i] - filter_size + 1)
print(h)
pooled = tf.nn.max_pool(
h,
ksize=[1, sequence_lengths[i] - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding="VALID",
name="pool"
)
pooled = tf.reshape(pooled, [-1, 1, 1, num_filters])
print(pooled)
pooled_outputs.append(pooled)
# Combine all of the pooled features
num_filters_total = num_filters * len(filter_sizes)
max_shape = tf.reduce_max(pooled_outputs, 1)
print("shapes")
print([p.get_shape() for p in pooled_outputs])
# pooled_outputs = [tf.pad(p, [[0, int(max_shape.get_shape()[0]) - int(p.get_shape()[0])], [0, 0], [0, 0], [0, 0]]) for p in pooled_outputs]
# pooled_outputs = [tf.reshape(p, [-1, 1, 1, num_filters]) for p in pooled_outputs]
# pooled_outputs = [tf.reshape(out, [-1, 1, 1, self.max_length]) for out in pooled_outputs]
self.h_pool = tf.concat(3, pooled_outputs)
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
print("here")
print(self.h_pool_flat)
self.h_pool_flat = tf.reshape(self.h_pool, [max(sequence_lengths), num_filters_total])
# Add dropout
with tf.name_scope("dropout"):
# casted = tf.cast(self.dropout_keep_prob, tf.int32)
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
self.h_drop = tf.reshape(self.h_drop, [-1, num_filters_total])
# Do raw predictions (no softmax)
with tf.name_scope("output"):
W = tf.Variable(tf.truncated_normal([num_filters_total, num_classes], stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
# xw_plus_b(...) is just Wx + b matmul alias
self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.predictions = tf.argmax(self.scores, 1, name="predictions")
# Calculate mean cross-entropy loss
with tf.name_scope("loss"):
# softmax_cross_entropy_with_logits(...) calculates cross-entropy loss
losses = tf.nn.softmax_cross_entropy_with_logits(self.scores, self.input_y)
'''print("here")
print(losses.get_shape())
print(self.scores.get_shape())
print(self.input_y.get_shape())'''
self.loss = tf.reduce_mean(losses)
# Calculate accuracy
with tf.name_scope("accuracy"):
correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")
I am using the Rotten Tomatoes sentiment labeled data set. The current error I am getting is this:
InvalidArgumentError (see above for traceback): input[1,0] mismatch: 5888 vs. 4864
[[Node: gradients/concat_grad/ConcatOffset = ConcatOffset[N=3, _device="/job:localhost/replica:0/task:0/cpu:0"](concat/concat_dim, gradients/concat_grad/ShapeN, gradients/concat_grad/ShapeN:1, gradients/concat_grad/ShapeN:2)]]
How can I fix this code so that all of the tensors are normalized to the same size after pooling (while keeping pooling dynamic) and so that the code runs to completion?
Sorry about all of the random commented out lines and prints and stuff, but I have tried extensively to make this work.
Although tensorflow doesn't provide k-max pooling directly, I think tf.nn.top_k might help you build that op.
There are three things to note here.
max-pooling and k-max pooling are two different operations.
max-pooling retrieves the maximum valued activation out of the pooling window while k-max pooling retrieves k maximum values from the pooling window.
Tensorflow doesn't provide API for k-max pooling as of now. The one
which you are trying now is max-pooling operation and not k-max
pooling operation.
As per my knowledge, tensorflow does not provide functionality to handle pooling resulting in different size of matrices. So, you may use bucketing to create batches of sentences of similar length and the use k-max pooling.