Related
I'm using this code as a base and wish to view the learning progress by the loss within Tensorboard. After adding the writer and attempting to add_summary, I receive the above error presented within the title.
""" Convolutional Neural Network.
Build and train a convolutional neural network with TensorFlow.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
"""
from __future__ import division, print_function, absolute_import
import tensorflow as tf
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Training Parameters
learning_rate = 0.001
num_steps = 200
batch_size = 128
display_step = 10
# Network Parameters
num_input = 784 # MNIST data input (img shape: 28*28)
num_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
X = tf.placeholder(tf.float32, [None, num_input])
Y = tf.placeholder(tf.float32, [None, num_classes])
keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)
# 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):
# MNIST data input is a 1-D vector of 784 features (28*28 pixels)
# Reshape to match picture format [Height x Width x Channel]
# Tensor input become 4-D: [Batch Size, Height, Width, Channel]
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, 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, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# 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([7*7*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, num_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([num_classes]))
}
# Construct model
logits = conv_net(X, weights, biases, keep_prob)
prediction = tf.nn.softmax(logits)
# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)
# Evaluate model
correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()
# Start training
with tf.Session() as sess:
# Run the initializer
sess.run(init)
for step in range(1, num_steps+1):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.8})
if step % display_step == 0 or step == 1:
# Calculate batch loss and accuracy
loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,
Y: batch_y,
keep_prob: 1.0})
print("Step " + str(step) + ", Minibatch Loss= " + \
"{:.4f}".format(loss) + ", Training Accuracy= " + \
"{:.3f}".format(acc))
print("Optimization Finished!")
# Calculate accuracy for 256 MNIST test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={X: mnist.test.images[:256],
Y: mnist.test.labels[:256],
keep_prob: 1.0}))
Running it works completely fine, I then added the writer variable to write to the root tmp directory of my OS.
# Start training
with tf.Session() as sess:
writer = tf.summary.FileWriter("/tmp/log/", graph=sess.graph)
# Run the initializer
sess.run(init)
for step in range(1, num_steps+1):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.8})
if step % display_step == 0 or step == 1:
# Calculate batch loss and accuracy
summary, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,
Y: batch_y,
keep_prob: 1.0})
print("Step " + str(step) + ", Minibatch Loss= " + \
"{:.4f}".format(summary) + ", Training Accuracy= " + \
"{:.3f}".format(acc))
writer.add_summary(summary=summary, global_step=step)
writer.flush()
writer.close()
print("Optimization Finished!")
# Calculate accuracy for 256 MNIST test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={X: mnist.test.images[:256],
Y: mnist.test.labels[:256],
keep_prob: 1.0}))
But that's when the error occurs. What exactly am I doing wrong and what is the correction that needs to be applied to fix this. I'm still quite new to Tensorflow but I've used summary writer before without this error.
I also used this tutorial as well in hopes of fixing this issue:
https://www.tensorflow.org/guide/summaries_and_tensorboard
Error just so everyone knows the culprit
Step 1, Minibatch Loss= 98733.8750, Training Accuracy= 0.102
Traceback (most recent call last):
File "convolutional_network_raw.py", line 137, in <module>
writer.add_summary(summary=summary, global_step=step)
File "/home/kyle/.conda/envs/csc/lib/python3.6/site-packages/tensorflow/python/summary/writer/writer.py", line 126, in add_summary
for value in summary.value:
AttributeError: 'numpy.float32' object has no attribute 'value'
The summary that goes into the file writer is a tf.Summary object. You need to first convert the loss value into a summary object, for example below (also change the variable in the print so you don't get an error):
loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,
Y: batch_y,
keep_prob: 1.0})
summary = tf.Summary(value=[tf.Summary.Value(tag="loss", simple_value=loss)])
print("Step " + str(step) + ", Minibatch Loss= " + \
"{:.4f}".format(loss) + ", Training Accuracy= " + \
"{:.3f}".format(acc))
I wrote alexnet in tensorflow to perform on the mnist dataset. I get a ValueErorr saying: Negative dimension size caused by subtracting 2 from 1 for 'pool5' (op: 'MaxPool') with input shapes: [?,1,1,1024]. How to solve it? Here is my code:
from __future__ import print_function
import tensorflow as tf
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import os
import random
import matplotlib.pyplot as plt
import numpy as np
# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 1000
display = True
display_step_console = 5
learn_from_scratch = False
train = False
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.80 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create AlexNet model
def conv1st(name, l_input, w, b):
cov = tf.nn.conv2d(l_input, w, strides=[1, 4, 4, 1], padding='VALID')
return tf.nn.relu(tf.nn.bias_add(cov,b), name=name)
def conv2d(name, l_input, w, b):
cov = tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME')
return tf.nn.relu(tf.nn.bias_add(cov,b), name=name)
def max_pool(name, l_input, k, s):
return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, s, s, 1],
padding='VALID', name=name)
def norm(name, l_input, lsize=4):
return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name=name)
def alex_net(_X, weights, biases, _dropout):
# Reshape input picture OH WAIT NOPE CUS JE SUIS UN TENSAI DESU
_X = tf.reshape(_X, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv1st('conv1', _X, _weights['wc1'], _biases['bc1'])
# Max Pooling (down-sampling)
pool1 = max_pool('pool1', conv1, k=2, s=2)
# Apply Normalization
norm1 = norm('norm1', pool1, lsize=4)
# Apply Dropout
norm1 = tf.nn.dropout(norm1, _dropout)
# Convolution Layer
conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
# Max Pooling (down-sampling)
pool2 = max_pool('pool2', conv2, k=2, s=2)
# Apply Normalization
norm2 = norm('norm2', pool2, lsize=4)
# Apply Dropout
norm2 = tf.nn.dropout(norm2, _dropout)
# Convolution Layer
conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
conv4 = conv2d('conv4', conv3, _weights['wc4'], _biases['bc4'])
conv5 = conv2d('conv5', conv4, _weights['wc5'], _biases['bc5'])
# Max Pooling (down-sampling)
pool5 = max_pool('pool5', conv5, k=2, s=2)
# Apply Normalization
norm5 = norm('norm5', pool5, lsize=4)
# Apply Dropout
norm5 = tf.nn.dropout(norm5, _dropout)
# Fully connected layer
dense1 = tf.reshape(norm5, [-1, _weights['wd1'].get_shape().as_list()
[0]]) # Reshape conv3 output to fit dense layer input
dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'],
name='fc1') # Relu activation
dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'],
name='fc2') # Relu activation
# Output, class prediction
out = tf.matmul(dense2, _weights['out']) + _biases['out']
return out
# Store layers weight & bias
_weights = {
'wc1': tf.Variable(tf.random_normal([11, 11, 1, 96])),
'wc2': tf.Variable(tf.random_normal([5, 5, 96, 256])),
'wc3': tf.Variable(tf.random_normal([3, 3, 256, 512])),
'wc4': tf.Variable(tf.random_normal([3, 3, 512, 1024])),
'wc5': tf.Variable(tf.random_normal([3, 3, 1024, 1024])),
#'wd1': tf.Variable(tf.random_normal([8*8*256, 1024])),
'wd1': tf.Variable(tf.random_normal([6*6*256, 3072])),
'wd2': tf.Variable(tf.random_normal([3072, 4096])),
'out': tf.Variable(tf.random_normal([4096, n_classes]))
}
_biases = {
'bc1': tf.Variable(tf.random_normal([96])),
'bc2': tf.Variable(tf.random_normal([256])),
'bc3': tf.Variable(tf.random_normal([512])),
'bc4': tf.Variable(tf.random_normal([1024])),
'bc5': tf.Variable(tf.random_normal([1024])),
'bd1': tf.Variable(tf.random_normal([3072])),
'bd2': tf.Variable(tf.random_normal([4096])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
############### NOT SO IMPORTANT ANYMORE###################################
# Construct model
pred = alex_net(x, _weights, _biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,
labels=y))
optimizer =
tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
#Create summary scalars and operation
n1 = tf.summary.scalar("cost", cost)
n2 = tf.summary.scalar("accuracy", accuracy)
train_summary_op = tf.summary.merge([n1,n2])
#Do writer
log_dir = "./alexnet-classification-model-checkpoints/summary"
train_writer = tf.summary.FileWriter(log_dir+'/train',
graph=tf.get_default_graph())
# Initializing the variables
init = tf.global_variables_initializer()
saver = tf.train.Saver(max_to_keep=1)
initial_step = 0
# Launch the graph
with tf.Session() as sess:
if learn_from_scratch == False:
if os.path.isfile('./alexnet-classification-model-
checkpoints/step.txt'):
with open("alexnet-classification-model-checkpoints/step.txt",
"r") as file:
step = file.read()
print(step)
initial_step = int(step)
if os.path.isfile('./alexnet-classification-model-
checkpoints/checkpoint') and os.path.isfile('./alexnet-classification-model-
checkpoints/my-model.ckpt.meta'):
saver = tf.train.import_meta_graph('alexnet-classification-
model-checkpoints/my-model.ckpt.meta')
saver.restore(sess, 'alexnet-classification-model-checkpoints/my-
model.ckpt')
print("Loaded model successfully!")
else:
print("A saved model wasn't found, starting from scratch")
sess.run(init)
else:
sess.run(init)
if train:
print("Starting training!")
step = 1
# Keep training until reach max iterations
while step * batch_size <= training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step_console == 0:
if display:
batch_x_eval, batch_y_eval = mnist.train.next_batch(500,
shuffle=True)
# Calculate batch loss and accuracy
loss, acc, summary = sess.run([cost, accuracy,
train_summary_op], feed_dict={x: batch_x_eval,
y: batch_y_eval,
keep_prob: 1.0})
train_writer.add_summary(summary, global_step=((step +
initial_step)*batch_size))
print("Iter " + str((step + initial_step)*batch_size) +
", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " +
\
"{:.5f}".format(acc))
else:
print("Still training...
{}%".format(round((step*batch_size / training_iters)*100), 2))
step += 1
print("Optimization Finished!")
savePath = saver.save(sess, 'alexnet-classification-model-
checkpoints/my-model.ckpt')
with open("alexnet-classification-model-checkpoints/step.txt", "w") as file:
file.write(str(initial_step+step))
print("Saved!")
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images,
y: mnist.test.labels,
keep_prob: 1.}))
num = random.randint(0, mnist.test.images.shape[0])
img = mnist.test.images[num]
cls = sess.run(tf.argmax(conv_net(img, weights, biases, dropout), 1))
cls2 = mnist.test.labels[num]
plt.imshow(img.reshape(28, 28), cmap=plt.cm.binary)
print ('NN predicted', cls, np.argmax(cls2))
plt.show()
I wrote a convolutional neural network in tensorflow to perform on the mnist dataset. Everything works just fine, but i want to visualize the model in tensorboard. How am i gonna do it? Here is my code:
from __future__ import print_function
import tensorflow as tf
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 128
display_step = 10
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# 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
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, 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, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# 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([7*7*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]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,
labels=y))
optimizer =
tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# 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:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print("Optimization Finished!")
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))
Create summary scalars and operation:
cost = tf.summary.scalar("cost", cost)
accuracy = tf.summary.scalar("accuracy", accuracy)
train_summary_op = tf.summary.merge([cost,accuracy])
Do writer:
train_writer = tf.summary.FileWriter(log_dir+'/train',
graph=tf.get_default_graph())
Use it in session run and write the summary:
loss, acc, summary = sess.run([cost, accuracy, train_summary_op], feed_dict={x: batch_x,y: batch_y,keep_prob: 1.})
train_writer.add_summary(train_summary_str, step)
Later, use tensorboard (point to folder you're writing summary) to visualize graphs of loss and accuracy.
I hope this is helpful.
I posted a similar question the other day here, but I have since made edits to bugs that I found, and the problem of bad predictions remains.
I have two networks -- one with 3 conv layers and another with 3 conv layers followed by 3 deconv layers. Both take a 200x200 input image. The output is the same resolution 200x200 but it has two classifications (either a zero of a 1 -- it's a segmentation network), so the network predictions dimensions are 200x200x2 (plus batch_size). Let's talk about the network with deconv layers.
Here's the weird thing... out of 10 training runs, maybe 3 of them will converge. The other 7 will diverge down to an accuracy of 0.0.
The conv and deconv layers are activated by a ReLu. The optimizer does something weird. When I print predictions after every training iteration, the magnitude of the values start large -- which is correct considering they are all passed through ReLu's -- but after each iterations, the values get smaller until they are roughly between 0 and 2. I subsequently pass them through a sigmoid function (sigmoid_cross_entropy_wight_logits) -- thus squashing the large negative values to 0 and the large positive values to 1. When I make predictions, I reactivate the outputs by passing them through the sigmoid function again.
So after the first iteration, prediction values are reasonable...
Accuracy = 0.508033
[[[[ 1. 0.]
[ 0. 1.]
[ 0. 0.]
...,
[ 1. 0.]
[ 1. 1.]
[ 1. 0.]]
[[ 0. 1.]
[ 1. 1.]
[ 0. 0.]
...,
[ 1. 1.]
[ 1. 1.]
[ 0. 1.]]
but then after some iterations, and let's say it actually converges this time, the prediction values look like... (because the optimizer makes the outputs smaller, they are all in that weird middle ground of the sigmoid function)
[[ 0.51028508 0.63202268]
[ 0.24386917 0.52015287]
[ 0.62086064 0.6953823 ]
...,
[ 0.2593964 0.13163178]
[ 0.24617286 0.5210492 ]
[ 0.24692698 0.5876413 ]]]]
Accuracy = 0.999913
do I have the wrong optimizer function?
Here's the entire code... jump to def conv_net to see the network creation... and after that function is the definition of the cost function, optimizer, and accuracy. You'll notice when I measure accuracy and make predictions I reactivate the output with tf.nn.sigmoid(pred) -- this is because the cost function sigmoid_cross_entropy_with_logits combines the activation and the loss in the same function. In other words, pred (the network) outputs a linear value.
import tensorflow as tf
import pdb
import numpy as np
from numpy import genfromtxt
from PIL import Image
# Parameters
learning_rate = 0.001
training_iters = 10000
batch_size = 10
display_step = 1
# Network Parameters
n_input = 200 # MNIST data input (img shape: 28*28)
n_output = 40000
n_classes = 2 # MNIST total classes (0-9 digits)
#n_input = 200
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input, n_input])
y = tf.placeholder(tf.float32, [None, n_input, n_input, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
def convert_to_2_channel(x, batch_size):
#assume input has dimension (batch_size,x,y)
#output will have dimension (batch_size,x,y,2)
output = np.empty((batch_size, 200, 200, 2))
temp_arr1 = np.empty((batch_size, 200, 200))
temp_arr2 = np.empty((batch_size, 200, 200))
for i in xrange(batch_size):
for j in xrange(3):
for k in xrange(3):
if x[i][j][k] == 1:
temp_arr1[i][j][k] = 1
temp_arr2[i][j][k] = 0
else:
temp_arr1[i][j][k] = 0
temp_arr2[i][j][k] = 1
for i in xrange(batch_size):
for j in xrange(200):
for k in xrange(200):
for l in xrange(2):
if l == 0:
output[i][j][k][l] = temp_arr1[i][j][k]
else:
output[i][j][k][l] = temp_arr2[i][j][k]
return output
# 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
x = tf.reshape(x, shape=[-1, 200, 200, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
#conv1 = tf.nn.local_response_normalization(conv1)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
#conv2 = tf.nn.local_response_normalization(conv2)
conv2 = maxpool2d(conv2, k=2)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# # Max Pooling (down-sampling)
#conv3 = tf.nn.local_response_normalization(conv3)
conv3 = maxpool2d(conv3, k=2)
temp_batch_size = tf.shape(x)[0]
output_shape = [temp_batch_size, 50, 50, 64]
conv4 = tf.nn.conv2d_transpose(conv3, weights['wdc1'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv4 = tf.nn.bias_add(conv4, biases['bdc1'])
conv4 = tf.nn.relu(conv4)
# conv4 = tf.nn.local_response_normalization(conv4)
# output_shape = tf.pack([temp_batch_size, 100, 100, 32])
output_shape = [temp_batch_size, 100, 100, 32]
conv5 = tf.nn.conv2d_transpose(conv4, weights['wdc2'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv5 = tf.nn.bias_add(conv5, biases['bdc2'])
conv5 = tf.nn.relu(conv5)
# conv5 = tf.nn.local_response_normalization(conv5)
# output_shape = tf.pack([temp_batch_size, 200, 200, 1])
output_shape = [temp_batch_size, 200, 200, 2]
conv6 = tf.nn.conv2d_transpose(conv5, weights['wdc3'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv6 = tf.nn.bias_add(conv6, biases['bdc3'])
conv6 = tf.nn.relu(conv6)
# pdb.set_trace()
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv6, [-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)
return (tf.add(tf.matmul(fc1, weights['out']), biases['out']))# 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])),
# 5x5 conv, 32 inputs, 64 outputs
'wc3' : tf.Variable(tf.random_normal([5, 5, 64, 128])),
'wdc1' : tf.Variable(tf.random_normal([2, 2, 64, 128])),
'wdc2' : tf.Variable(tf.random_normal([2, 2, 32, 64])),
'wdc3' : tf.Variable(tf.random_normal([2, 2, 2, 32])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([80000, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, 80000]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bc3': tf.Variable(tf.random_normal([128])),
'bdc1': tf.Variable(tf.random_normal([64])),
'bdc2': tf.Variable(tf.random_normal([32])),
'bdc3': tf.Variable(tf.random_normal([2])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([80000]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
pred = tf.reshape(pred, [-1,n_input,n_input,n_classes])
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
# cost = (tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(0,tf.cast(tf.sub(tf.nn.sigmoid(pred),y), tf.int32))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph)
step = 1
from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data
data = scroll_data.read_data('/home/kendall/Desktop/')
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = data.train.next_batch(batch_size)
# Run optimization op (backprop)
batch_x = batch_x.reshape((batch_size, n_input, n_input))
batch_y = batch_y.reshape((batch_size, n_input, n_input))
batch_y = convert_to_2_channel(batch_y, batch_size) #converts the 200x200 ground truth to a 200x200x2 classification
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
#measure prediction
prediction = sess.run(tf.nn.sigmoid(pred), feed_dict={x: batch_x, keep_prob: 1.})
print prediction
if step % display_step == 0:
# Calculate batch loss and accuracdef conv_net(x, weights, biases, dropout):
save_path = "model.ckpt"
saver.save(sess, save_path)
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: dropout})
print "Accuracy = " + str(acc)
if acc > 0.73:
break
step += 1
print "Optimization Finished!"
#make prediction
im = Image.open('/home/kendall/Desktop/HA900_frames/frame0035.tif')
batch_x = np.array(im)
# pdb.set_trace()
batch_x = batch_x.reshape((1, n_input, n_input))
batch_x = batch_x.astype(float)
pdb.set_trace()
prediction = sess.run(tf.nn.sigmoid(pred), feed_dict={x: batch_x, keep_prob: dropout})
print prediction
arr1 = np.empty((n_input,n_input))
arr2 = np.empty((n_input,n_input))
for i in xrange(n_input):
for j in xrange(n_input):
for k in xrange(2):
if k == 0:
arr1[i][j] = (prediction[0][i][j][k])
else:
arr2[i][j] = (prediction[0][i][j][k])
# prediction = np.asarray(prediction)
# prediction = np.reshape(prediction, (200,200))
# np.savetxt("prediction.csv", prediction, delimiter=",")
np.savetxt("prediction1.csv", arr1, delimiter=",")
np.savetxt("prediction2.csv", arr2, delimiter=",")
# np.savetxt("prediction2.csv", arr2, delimiter=",")
# Calculate accuracy for 256 mnist test images
print "Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: data.test.images[:256],
y: data.test.labels[:256],
keep_prob: 1.})
The correct_pred variable (the variable that measures accuracy) is a simple subtraction operator between the predictions and the ground truth, and then compared to zero (if the two are equivalent, then the difference should be zero).
Also, I have graphed the network, and it just looks very off to me. Here is a picture, I had to crop for viewing.
EDIT: I found out why my graph looks terrible (thanks Olivier), and I also tried changing my loss function, but to no end -- it still diverges in the same manor
with tf.name_scope("loss") as scope:
# cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
temp_pred = tf.reshape(pred, [-1, 2])
temp_y = tf.reshape(y, [-1, 2])
cost = (tf.nn.softmax_cross_entropy_with_logits(temp_pred, temp_y))
EDIT full code now looks like this (still diverging)
import tensorflow as tf
import pdb
import numpy as np
from numpy import genfromtxt
from PIL import Image
# Parameters
learning_rate = 0.001
training_iters = 10000
batch_size = 10
display_step = 1
# Network Parameters
n_input = 200 # MNIST data input (img shape: 28*28)
n_output = 40000
n_classes = 2 # MNIST total classes (0-9 digits)
#n_input = 200
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input, n_input])
y = tf.placeholder(tf.float32, [None, n_input, n_input, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
def convert_to_2_channel(x, batch_size):
#assume input has dimension (batch_size,x,y)
#output will have dimension (batch_size,x,y,2)
output = np.empty((batch_size, 200, 200, 2))
temp_arr1 = np.empty((batch_size, 200, 200))
temp_arr2 = np.empty((batch_size, 200, 200))
for i in xrange(batch_size):
for j in xrange(3):
for k in xrange(3):
if x[i][j][k] == 1:
temp_arr1[i][j][k] = 1
temp_arr2[i][j][k] = 0
else:
temp_arr1[i][j][k] = 0
temp_arr2[i][j][k] = 1
for i in xrange(batch_size):
for j in xrange(200):
for k in xrange(200):
for l in xrange(2):
if l == 0:
output[i][j][k][l] = temp_arr1[i][j][k]
else:
output[i][j][k][l] = temp_arr2[i][j][k]
return output
# 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
x = tf.reshape(x, shape=[-1, 200, 200, 1])
with tf.name_scope("conv1") as scope:
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
#conv1 = tf.nn.local_response_normalization(conv1)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
with tf.name_scope("conv2") as scope:
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
#conv2 = tf.nn.local_response_normalization(conv2)
conv2 = maxpool2d(conv2, k=2)
# Convolution Layer
with tf.name_scope("conv3") as scope:
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# # Max Pooling (down-sampling)
#conv3 = tf.nn.local_response_normalization(conv3)
conv3 = maxpool2d(conv3, k=2)
temp_batch_size = tf.shape(x)[0]
with tf.name_scope("deconv1") as scope:
output_shape = [temp_batch_size, 50, 50, 64]
conv4 = tf.nn.conv2d_transpose(conv3, weights['wdc1'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv4 = tf.nn.bias_add(conv4, biases['bdc1'])
conv4 = tf.nn.relu(conv4)
# conv4 = tf.nn.local_response_normalization(conv4)
with tf.name_scope("deconv2") as scope:
# output_shape = tf.pack([temp_batch_size, 100, 100, 32])
output_shape = [temp_batch_size, 100, 100, 32]
conv5 = tf.nn.conv2d_transpose(conv4, weights['wdc2'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv5 = tf.nn.bias_add(conv5, biases['bdc2'])
conv5 = tf.nn.relu(conv5)
# conv5 = tf.nn.local_response_normalization(conv5)
with tf.name_scope("deconv3") as scope:
# output_shape = tf.pack([temp_batch_size, 200, 200, 1])
output_shape = [temp_batch_size, 200, 200, 2]
conv6 = tf.nn.conv2d_transpose(conv5, weights['wdc3'], output_shape=output_shape, strides=[1,2,2,1], padding="VALID")
conv6 = tf.nn.bias_add(conv6, biases['bdc3'])
# conv6 = tf.nn.relu(conv6)
# pdb.set_trace()
conv6 = tf.nn.dropout(conv6, dropout)
return conv6
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
# fc1 = tf.reshape(conv6, [-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)
#
# return (tf.add(tf.matmul(fc1, weights['out']), biases['out']))# 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])),
# 5x5 conv, 32 inputs, 64 outputs
'wc3' : tf.Variable(tf.random_normal([5, 5, 64, 128])),
'wdc1' : tf.Variable(tf.random_normal([2, 2, 64, 128])),
'wdc2' : tf.Variable(tf.random_normal([2, 2, 32, 64])),
'wdc3' : tf.Variable(tf.random_normal([2, 2, 2, 32])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([80000, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, 80000]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bc3': tf.Variable(tf.random_normal([128])),
'bdc1': tf.Variable(tf.random_normal([64])),
'bdc2': tf.Variable(tf.random_normal([32])),
'bdc3': tf.Variable(tf.random_normal([2])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([80000]))
}
# Construct model
# with tf.name_scope("net") as scope:
pred = conv_net(x, weights, biases, keep_prob)
pred = tf.reshape(pred, [-1,n_input,n_input,n_classes])
# Define loss and optimizer
with tf.name_scope("loss") as scope:
# cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
temp_pred = tf.reshape(pred, [-1, 2])
temp_y = tf.reshape(y, [-1, 2])
cost = (tf.nn.softmax_cross_entropy_with_logits(temp_pred, temp_y))
with tf.name_scope("opt") as scope:
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
with tf.name_scope("acc") as scope:
correct_pred = tf.equal(0,tf.cast(tf.sub(tf.nn.softmax(temp_pred),y), tf.int32))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph)
step = 1
from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data
data = scroll_data.read_data('/home/kendall/Desktop/')
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = data.train.next_batch(batch_size)
# Run optimization op (backprop)
batch_x = batch_x.reshape((batch_size, n_input, n_input))
batch_y = batch_y.reshape((batch_size, n_input, n_input))
batch_y = convert_to_2_channel(batch_y, batch_size) #converts the 200x200 ground truth to a 200x200x2 classification
batch_y = batch_y.reshape(batch_size * n_input * n_input, 2)
sess.run(optimizer, feed_dict={x: batch_x, temp_y: batch_y,
keep_prob: dropout})
#measure prediction
prediction = sess.run(tf.nn.softmax(temp_pred), feed_dict={x: batch_x, keep_prob: dropout})
print prediction
if step % display_step == 0:
# Calculate batch loss and accuracdef conv_net(x, weights, biases, dropout):
save_path = "model.ckpt"
saver.save(sess, save_path)
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: dropout})
print "Accuracy = " + str(acc)
if acc > 0.73:
break
step += 1
print "Optimization Finished!"
#make prediction
im = Image.open('/home/kendall/Desktop/HA900_frames/frame0035.tif')
batch_x = np.array(im)
# pdb.set_trace()
batch_x = batch_x.reshape((1, n_input, n_input))
batch_x = batch_x.astype(float)
pdb.set_trace()
prediction = sess.run(tf.nn.sigmoid(pred), feed_dict={x: batch_x, keep_prob: dropout})
print prediction
arr1 = np.empty((n_input,n_input))
arr2 = np.empty((n_input,n_input))
for i in xrange(n_input):
for j in xrange(n_input):
for k in xrange(2):
if k == 0:
arr1[i][j] = (prediction[0][i][j][k])
else:
arr2[i][j] = (prediction[0][i][j][k])
# prediction = np.asarray(prediction)
# prediction = np.reshape(prediction, (200,200))
# np.savetxt("prediction.csv", prediction, delimiter=",")
np.savetxt("prediction1.csv", arr1, delimiter=",")
np.savetxt("prediction2.csv", arr2, delimiter=",")
# np.savetxt("prediction2.csv", arr2, delimiter=",")
# Calculate accuracy for 256 mnist test images
print "Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: data.test.images[:256],
y: data.test.labels[:256],
keep_prob: 1.})
The concept of deconvolution is to output something of the same size as the input.
At the line:
conv6 = tf.nn.bias_add(conv6, biases['bdc3'])
You have this output of shape [batch_size, 200, 200, 2], so you don't need to add your fully connected layers. Just return conv6 (without the final ReLU).
If you use 2 categories in your prediction and the true labels y, you need to use tf.nn.softmax_cross_entropy_with_logits(), not the sigmoid cross entropy.
Make sure that y always has values like: y[i, j] = [0., 1.] or y[i, j] = [1., 0.]
pred = conv_net(x, weights, biases, keep_prob) # NEW prediction conv6
pred = tf.reshape(pred, [-1, n_classes])
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
And if you want your TensorBoard graph to look nice (or at least readable), make sure to use tf.name_scope()
EDIT:
Your accuracy is also wrong. You measure if softmax(pred) and y are equal, but softmax(pred) can never be equal to 0. or 1., so you will have an accuracy of 0..
Here is what you should do:
with tf.name_scope("acc") as scope:
correct_pred = tf.equal(tf.argmax(temp_pred, 1), tf.argmax(temp_y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
EDIT 2:
The real error was a typo in convert_to_2_channel, in the loop
for j in xrange(3):
It should be 200 instead of 3.
Lesson: when debugging, print everything step by step with very simple examples and you will find your that the buggy function returns bad output.
I have an implementation of the AlexNet. I'm interested in extracting the vector of features of a trained model before the fully-connected classification layers
I want to first train the model (below I included the evaluation methods for training and testing).
How do I get a list of final output feature vectors (during the forward pass) for all the images in the training/test set before they get classified?
Here is the code (full version available https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/alexnet.py) :
weights = {
'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),
'wd2': tf.Variable(tf.random_normal([1024, 1024])),
'out': tf.Variable(tf.random_normal([1024, 10]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([64])),
'bc2': tf.Variable(tf.random_normal([128])),
'bc3': tf.Variable(tf.random_normal([256])),
'bd1': tf.Variable(tf.random_normal([1024])),
'bd2': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
def alex_net(_X, _weights, _biases, _dropout):
# Reshape input picture
_X = tf.reshape(_X, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
# Max Pooling (down-sampling)
pool1 = max_pool('pool1', conv1, k=2)
# Apply Normalization
norm1 = norm('norm1', pool1, lsize=4)
# Apply Dropout
norm1 = tf.nn.dropout(norm1, _dropout)
# Convolution Layer
conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
...
# right before feeding the fully connected, classification layers
# I'm interested in the vector after the weights
# are applied during the forward pass of a trained model.
dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
# Relu activation
dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
# Relu activation
dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2')
# Output, class prediction
out = tf.matmul(dense2, _weights['out']) + _biases['out']
return out
pred = alex_net(x, weights, biases, keep_prob)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
summary_writer = tf.train.SummaryWriter('/tmp/tensorflow_logs', graph_def=sess.graph_def)
while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Fit training using batch data
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
if step % display_step == 0:
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
print "Iter " + str(step*batch_size) + ", Minibatch Loss= " \
+ "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
step += 1
print "Optimization Finished!"
# Calculate accuracy for 256 mnist test images
print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.})
It sounds like you want the value of dense2 from alex_net()? If so, you will need to return that from alex_net() in addition to out, so
return out
becomes
return dense2, out
and
pred = alex_net(x, weights, biases, keep_prob)
becomes
before_classification_layer, pred = alex_net(...)
Then you can fetch before_classification_layer when calling sess.run() whenever you want that value. See tf.Session.run in https://www.tensorflow.org/versions/0.6.0/api_docs/python/client.html#Session.run. Note that the fetches may be a list, so to avoid evaluating your graph twice in your example code, you can do
# Calculate batch accuracy and loss
acc, loss = sess.run([accuracy, cost], feed_dict={...})
instead of
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={...})
# Calculate batch loss
loss = sess.run(cost, feed_dict={...})
(Adding before_classification_layer to that list when desired.)