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.
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 am using CNN to classifies MNIST dataset into 10 classes.
But the error shows the batch size of the pred is different.
InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[36,10] labels_size=[64,10]
[[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]
I can't find the reason why the batch size became 36 instead of 64.
Here is my code. The image size is 28*28*1.
import tensorflow as tf
# input data
from tensorflow.examples.tutorials.mnist import input_data
# mnist = input_data.read_data_sets('/tmp/data/', one_hot=True)
mnist = input_data.read_data_sets('./MNIST_data', one_hot=True) # runing on server
learning_rate = 0.001
training_iters = 200000
batch_size = 64
display_step = 10
n_input = 784
n_classes = 10
dropout = 0.75
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) # dropout
def conv2d(name, x, W, b, s=1):
return tf.nn.relu(tf.nn.conv2d(x, W, strides=[1, s, s, 1], padding='SAME'))
def maxpool2d(name, x, k=2, s=2):
return tf.nn.max_pool(x, 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
x = tf.reshape(x, shape=[-1, 28, 28, 1])
conv1 = conv2d('conv1', x, weights['wc1'], biases['bc1'], s=1)
pool1 = maxpool2d('pool1', conv1, k=2, s=2)
norm1 = norm('norm1', pool1)
conv2 = conv2d('conv2', norm1, weights['wc2'], biases['bc2'], s=1)
pool2 = maxpool2d('pool2', conv2, k=2, s=2)
norm2 = norm('norm2', pool2)
conv3 = conv2d('conv3', norm2, weights['wc3'], biases['bc3'], s=1)
pool3 = maxpool2d('pool3', conv3, k=2, s=2)
norm3 = norm('norm3', pool3)
fc1 = tf.reshape(norm3, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
fc2 = tf.add(tf.matmul(fc1, weights['wd2']), biases['bd2'])
fc2 = tf.nn.relu(fc2)
out = tf.matmul(fc2, weights['out']) + biases['out']
return out
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, n_classes]))
}
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]))
}
pred = alex_net(x, weights, biases, keep_prob)
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)
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
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!")
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))
It should be because the padding used for maxpool2d is 'VALID' instead of 'SAME'. How it affected the batch layer was due to reshaping fc1 = tf.reshape(norm3, [-1, weights['wd1'].get_shape().as_list()[0]])
If the above answer didn't correct the error, you should check the output shape of each function by running function_name.eval(sess, feed_dict = {x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})).shape in your terminal and see what is the output shape, and whether it is the desired shape for that layer.
I wrote a convolutional neural network in tensorflow to perform on the mnist dataset. Everything works just fine, but i want to save the model with the tf.train.Saver(). 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.}))
Simplest way to save and restore:
To save:
saver = tf.train.Saver(max_to_keep=1)
with tf.Session() as sess:
# train your model, then:
savePath = saver.save(sess, 'someDir/my_model.ckpt')
To restore:
with tf.Session() as sess:
saver = tf.train.import_meta_graph('someDir/my_model.ckpt.meta')
saver.restore(sess, pathModel + 'someDir/my_model.ckpt')
# access a variable from the saved Graph, and so on:
someVar = sess.run('varName:0')
This should do it
Consider saving results of Neural Network training to database.
The root of the idea is described here:
A neural network scoring engine in PL/SQL for recognizing handwritten digits
https://db-blog.web.cern.ch/blog/luca-canali/2016-07-neural-network-scoring-engine-plsql-recognizing-handwritten-digits
The code repository for this example is located here:
https://github.com/LucaCanali/Miscellaneous/tree/master/PLSQL_Neural_Network
By doing so it's possible to train the network once and then use database procedures to use it.
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.)