使用汇总操作时出现 AttributeError
AttributeError while using summary operation
我使用 TensorFlow 构建了一个 CNN。网络运行良好，但我遇到了一个问题：我无法从学习过程中可视化和绘制图表。
因此，为了使用 TensorBoard，我按照 this 教程实施了必要的命令。
但是，当我 运行 代码时，我收到以下 错误消息：
AttributeError: 'module' object has no attribute 'scalar'
参考以下命令（具体到带**的行）：
在main函数中：
W_conv1 = weight_variable([first_conv_kernel_size, first_conv_kernel_size,
with tf.name_scope('weights'):
**variable_summaries(W_conv1)**
在variable_summaries函数中：
def variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
**tf.summary.scalar('mean', mean)**
这是什么错误消息？我是按照教程一步一步来的，没发现错误。
感谢您的帮助，谢谢！ :)
全部代码：
import build_database_tuple
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
# few functions to initialize the weights of the layers properly (positive etc.)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# convolution and pooling layers definition
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def variable_summaries(var):
"""Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev)
tf.summary.scalar('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
tf.summary.histogram('histogram', var)
# from the previous code (mnist):
print('START')
# INTIAL PARAMETERS
# database:
data_home_dir='/home/dir/to/data/'
validation_ratio=(1.0/8)
patch_size=32
test_images_num=5000*1 # csv_batchsize*number of test batches files
train_images_num=78000+78000-test_images_num # posnum + negnum
# model parameters:
first_conv_kernel_size=5
first_conv_output_channels=32
sec_conv_kernel_size=5
sec_conv_output_channels=64
fc_vec_size=512
# train and test parameters
train_epoches_num=5
train_batch_size=100
test_batch_size=100
learning_rate=1*(10**(-4))
summaries_dir='/dir/to/log/files/'
# load data
folds = build_database_tuple.load_data(data_home_dir=data_home_dir,validation_ratio=validation_ratio,patch_size=patch_size)
# starting the session. using the InteractiveSession we avoid build the entiee comp. graph before starting the session
sess = tf.InteractiveSession()
# start building the computational graph
# the 'None' indicates the number of classes - a value that we wanna leave open for now
x = tf.placeholder(tf.float32, shape=[None, patch_size**2]) #input images - 28x28=784
y_ = tf.placeholder(tf.float32, shape=[None, 2]) #output classes (using one-hot vectors)
# the vriables for the linear layer
W = tf.Variable(tf.zeros([(patch_size**2),2])) #weights - 784 input features and 10 outputs
b = tf.Variable(tf.zeros([2])) #biases - 10 classes
# initialize all the variables using the session, in order they could be used in it
sess.run(tf.initialize_all_variables())
# implementation of the regression model
y = tf.nn.softmax(tf.matmul(x,W) + b)
# Done!
# FIRST LAYER:
with tf.name_scope('layer1'):
# build the first layer
W_conv1 = weight_variable([first_conv_kernel_size, first_conv_kernel_size, 1, first_conv_output_channels]) # 5x5 patch, 1 input channel, 32 output channels (features)
b_conv1 = bias_variable([first_conv_output_channels])
x_image = tf.reshape(x, [-1,patch_size,patch_size,1]) # reshape x to a 4d tensor. 2,3 are the image dimensions, 4 is ine color channel
# apply the layers
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('weights'):
variable_summaries(W_conv1)
with tf.name_scope('biases'):
variable_summaries(b_conv1)
# SECOND LAYER:
with tf.name_scope('layer2'):
# 64 features each 5x5 patch
W_conv2 = weight_variable([sec_conv_kernel_size, sec_conv_kernel_size, patch_size, sec_conv_output_channels])
b_conv2 = bias_variable([sec_conv_output_channels])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('weights'):
variable_summaries(W_conv2)
with tf.name_scope('biases'):
variable_summaries(b_conv2)
# FULLY CONNECTED LAYER:
with tf.name_scope('fc'):
# 1024 neurons, 8x8 - new size after 2 pooling layers
W_fc1 = weight_variable([(patch_size/4) * (patch_size/4) * sec_conv_output_channels, fc_vec_size])
b_fc1 = bias_variable([fc_vec_size])
h_pool2_flat = tf.reshape(h_pool2, [-1, (patch_size/4) * (patch_size/4) * sec_conv_output_channels])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout layer - meant to reduce over-fitting
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.summary.scalar('dropout_keep_probability', keep_prob)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
with tf.name_scope('weights'):
variable_summaries(W_fc1)
with tf.name_scope('biases'):
variable_summaries(b_fc1)
# READOUT LAYER:
with tf.name_scope('softmax'):
# softmax regression
W_fc2 = weight_variable([fc_vec_size, 2])
b_fc2 = bias_variable([2])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
with tf.name_scope('weights'):
variable_summaries(W_fc2)
with tf.name_scope('biases'):
variable_summaries(b_fc2)
# TRAIN AND EVALUATION:
with tf.name_scope('cross_entropy'):
# cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1])) # can be numerically unstable. old working calculation
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
tf.summary.scalar('cross_entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.summary.merge_all()
train_writer = tf.train.SummaryWriter(summaries_dir + '/train', sess.graph)
test_writer = tf.train.SummaryWriter(summaries_dir + '/test')
#tf.global_variables_initializer().run()
sess.run(tf.initialize_all_variables())
# variables for the plotting process
p11 = []
p12 = []
p21 = []
p22 = []
f0 = plt.figure()
f1 = plt.figure()
train_accuracy=0
# starting the training process
for i in range(((train_images_num*train_epoches_num)/train_batch_size)):
if i%50 == 0: # for every 100 iterations
#train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
# calculate test accuracy
val_batch = folds.validation.next_batch(train_batch_size)
#val_accuracy = accuracy.eval(feed_dict={x: val_batch[0], y_: val_batch[1], keep_prob: 1.0})
summary, val_accuracy = sess.run([merged, accuracy], feed_dict={x: val_batch[0], y_: val_batch[1], keep_prob: 1.0})
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, val_accuracy))
# The train step
else:
summary, _ = sess.run([merged, train_step], feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
train_writer.add_summary(summary, i)
# Save Network
saver = tf.train.Saver()
save_path = saver.save(sess,'/dir/to/model/files/model.ckpt')
print("Model saved in file: %s" % save_path)
按照 of sunside，我更新了我的tensorflow版本，问题解决了。
显然，tf.scalar_summary() 在 tensorflow 版本 0.10 上工作，但在更新版本（至少 0.12）更新为 tf.summary.scalar()。
终端中的 pip install -U tensorflow 立即解决了问题:)
我使用 TensorFlow 构建了一个 CNN。网络运行良好，但我遇到了一个问题：我无法从学习过程中可视化和绘制图表。
因此，为了使用 TensorBoard，我按照 this 教程实施了必要的命令。
但是，当我 运行 代码时，我收到以下 错误消息：
AttributeError: 'module' object has no attribute 'scalar'
参考以下命令（具体到带**的行）：
在main函数中：
W_conv1 = weight_variable([first_conv_kernel_size, first_conv_kernel_size,
with tf.name_scope('weights'):
**variable_summaries(W_conv1)**
在variable_summaries函数中：
def variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
**tf.summary.scalar('mean', mean)**
这是什么错误消息？我是按照教程一步一步来的，没发现错误。
感谢您的帮助，谢谢！ :)
全部代码：
import build_database_tuple
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
# few functions to initialize the weights of the layers properly (positive etc.)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# convolution and pooling layers definition
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def variable_summaries(var):
"""Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev)
tf.summary.scalar('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
tf.summary.histogram('histogram', var)
# from the previous code (mnist):
print('START')
# INTIAL PARAMETERS
# database:
data_home_dir='/home/dir/to/data/'
validation_ratio=(1.0/8)
patch_size=32
test_images_num=5000*1 # csv_batchsize*number of test batches files
train_images_num=78000+78000-test_images_num # posnum + negnum
# model parameters:
first_conv_kernel_size=5
first_conv_output_channels=32
sec_conv_kernel_size=5
sec_conv_output_channels=64
fc_vec_size=512
# train and test parameters
train_epoches_num=5
train_batch_size=100
test_batch_size=100
learning_rate=1*(10**(-4))
summaries_dir='/dir/to/log/files/'
# load data
folds = build_database_tuple.load_data(data_home_dir=data_home_dir,validation_ratio=validation_ratio,patch_size=patch_size)
# starting the session. using the InteractiveSession we avoid build the entiee comp. graph before starting the session
sess = tf.InteractiveSession()
# start building the computational graph
# the 'None' indicates the number of classes - a value that we wanna leave open for now
x = tf.placeholder(tf.float32, shape=[None, patch_size**2]) #input images - 28x28=784
y_ = tf.placeholder(tf.float32, shape=[None, 2]) #output classes (using one-hot vectors)
# the vriables for the linear layer
W = tf.Variable(tf.zeros([(patch_size**2),2])) #weights - 784 input features and 10 outputs
b = tf.Variable(tf.zeros([2])) #biases - 10 classes
# initialize all the variables using the session, in order they could be used in it
sess.run(tf.initialize_all_variables())
# implementation of the regression model
y = tf.nn.softmax(tf.matmul(x,W) + b)
# Done!
# FIRST LAYER:
with tf.name_scope('layer1'):
# build the first layer
W_conv1 = weight_variable([first_conv_kernel_size, first_conv_kernel_size, 1, first_conv_output_channels]) # 5x5 patch, 1 input channel, 32 output channels (features)
b_conv1 = bias_variable([first_conv_output_channels])
x_image = tf.reshape(x, [-1,patch_size,patch_size,1]) # reshape x to a 4d tensor. 2,3 are the image dimensions, 4 is ine color channel
# apply the layers
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('weights'):
variable_summaries(W_conv1)
with tf.name_scope('biases'):
variable_summaries(b_conv1)
# SECOND LAYER:
with tf.name_scope('layer2'):
# 64 features each 5x5 patch
W_conv2 = weight_variable([sec_conv_kernel_size, sec_conv_kernel_size, patch_size, sec_conv_output_channels])
b_conv2 = bias_variable([sec_conv_output_channels])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('weights'):
variable_summaries(W_conv2)
with tf.name_scope('biases'):
variable_summaries(b_conv2)
# FULLY CONNECTED LAYER:
with tf.name_scope('fc'):
# 1024 neurons, 8x8 - new size after 2 pooling layers
W_fc1 = weight_variable([(patch_size/4) * (patch_size/4) * sec_conv_output_channels, fc_vec_size])
b_fc1 = bias_variable([fc_vec_size])
h_pool2_flat = tf.reshape(h_pool2, [-1, (patch_size/4) * (patch_size/4) * sec_conv_output_channels])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout layer - meant to reduce over-fitting
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.summary.scalar('dropout_keep_probability', keep_prob)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
with tf.name_scope('weights'):
variable_summaries(W_fc1)
with tf.name_scope('biases'):
variable_summaries(b_fc1)
# READOUT LAYER:
with tf.name_scope('softmax'):
# softmax regression
W_fc2 = weight_variable([fc_vec_size, 2])
b_fc2 = bias_variable([2])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
with tf.name_scope('weights'):
variable_summaries(W_fc2)
with tf.name_scope('biases'):
variable_summaries(b_fc2)
# TRAIN AND EVALUATION:
with tf.name_scope('cross_entropy'):
# cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1])) # can be numerically unstable. old working calculation
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
tf.summary.scalar('cross_entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.summary.merge_all()
train_writer = tf.train.SummaryWriter(summaries_dir + '/train', sess.graph)
test_writer = tf.train.SummaryWriter(summaries_dir + '/test')
#tf.global_variables_initializer().run()
sess.run(tf.initialize_all_variables())
# variables for the plotting process
p11 = []
p12 = []
p21 = []
p22 = []
f0 = plt.figure()
f1 = plt.figure()
train_accuracy=0
# starting the training process
for i in range(((train_images_num*train_epoches_num)/train_batch_size)):
if i%50 == 0: # for every 100 iterations
#train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
# calculate test accuracy
val_batch = folds.validation.next_batch(train_batch_size)
#val_accuracy = accuracy.eval(feed_dict={x: val_batch[0], y_: val_batch[1], keep_prob: 1.0})
summary, val_accuracy = sess.run([merged, accuracy], feed_dict={x: val_batch[0], y_: val_batch[1], keep_prob: 1.0})
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, val_accuracy))
# The train step
else:
summary, _ = sess.run([merged, train_step], feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
train_writer.add_summary(summary, i)
# Save Network
saver = tf.train.Saver()
save_path = saver.save(sess,'/dir/to/model/files/model.ckpt')
print("Model saved in file: %s" % save_path)
按照
显然，tf.scalar_summary() 在 tensorflow 版本 0.10 上工作，但在更新版本（至少 0.12）更新为 tf.summary.scalar()。
pip install -U tensorflow 立即解决了问题:)