AttributeError: 'dict' object has no attribute 'train' error when trying to implement a convolution neural network program using tensorflow in python
AttributeError: 'dict' object has no attribute 'train' error when trying to implement a convolution neural network program using tensorflow in python
尽管我对这个话题非常陌生，但我正在尝试实现一个 CNN 程序，该程序可用于在不使用 Keras 的情况下识别图像。我目前正在使用 python 和 Jupyter/Google Colab。
在修复了我的代码中出现的其他一些错误后，我现在遇到了这个错误：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py:1761: UserWarning: An interactive session is already active. This can cause out-of-memory errors in some cases. You must explicitly call `InteractiveSession.close()` to release resources held by the other session(s).
warnings.warn('An interactive session is already active. This can '
Training the model....
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-28-1af250ed46b3> in <module>()
108 for i in range(num_iterations):
109 # Get the next batch of images
--> 110 batch = mnist.train.next_batch(batch_size) #third got an error for this line -
111 # x_batch, y_batch = mnist.train.next_batch(batch_size)
112
AttributeError: 'dict' object has no attribute 'train'
这是我当前的代码：
!pip install tensorflow_datasets
!pip install --upgrade tensorflow
!pip install tensorflow-datasets
!pip install mnist
#!pip install tensorflow.examples.tutorials.mnist
import argparse
print ('argparse version: ', argparse.__version__)
import mnist
print ('MNIST version: ', mnist.__version__)
import tensorflow_datasets
print ('tensorflow_datasets version: ', tensorflow_datasets.__version__)
import tensorflow.compat.v1 as tf
print ('tf version: ', tf.__version__)
tf.disable_v2_behavior()
#from tensorflow.examples.tutorials.mnist import input_data
#def build_arg_parser():
# parser = argparse.ArgumentParser(description='Build a CNN classifier \
# using MNIST data')
# parser.add_argument('--input-dir', dest='input_dir', type=str,
# default='./mnist_data', help='Directory for storing data')
# return parser
def get_weights(shape):
data = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(data)
def get_biases(shape):
data = tf.constant(0.1, shape=shape)
return tf.Variable(data)
def create_layer(shape):
# Get the weights and biases
W = get_weights(shape)
b = get_biases([shape[-1]])
return W, b
def convolution_2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],
padding='SAME')
def max_pooling(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
if __name__ == '__main__':
#args = build_arg_parser().parse_args()
# Get the MNIST data
mnist = tensorflow_datasets.load('mnist')
# The images are 28x28, so create the input layer
# with 784 neurons (28x28=784)
x = tf.placeholder(tf.float32, [None, 784])
# Reshape 'x' into a 4D tensor
x_image = tf.reshape(x, [-1, 28, 28, 1])
# Define the first convolutional layer
W_conv1, b_conv1 = create_layer([5, 5, 1, 32])
# Convolve the image with weight tensor, add the
# bias, and then apply the ReLU function
h_conv1 = tf.nn.relu(convolution_2d(x_image, W_conv1) + b_conv1)
# Apply the max pooling operator
h_pool1 = max_pooling(h_conv1)
# Define the second convolutional layer
W_conv2, b_conv2 = create_layer([5, 5, 32, 64])
# Convolve the output of previous layer with the
# weight tensor, add the bias, and then apply
# the ReLU function
h_conv2 = tf.nn.relu(convolution_2d(h_pool1, W_conv2) + b_conv2)
# Apply the max pooling operator
h_pool2 = max_pooling(h_conv2)
# Define the fully connected layer
W_fc1, b_fc1 = create_layer([7 * 7 * 64, 1024])
# Reshape the output of the previous layer
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# Multiply the output of previous layer by the
# weight tensor, add the bias, and then apply
# the ReLU function
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Define the dropout layer using a probability placeholder
# for all the neurons
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Define the readout layer (output layer)
W_fc2, b_fc2 = create_layer([1024, 10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define the entropy loss and the optimizer
y_loss = tf.placeholder(tf.float32, [None, 10])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
# Define the accuracy computation
predicted = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_loss, 1))
accuracy = tf.reduce_mean(tf.cast(predicted, tf.float32))
# Create and run a session
sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
sess.run(init)
# Start training
num_iterations = 21000
batch_size = 75
print('\nTraining the model....')
for i in range(num_iterations):
# Get the next batch of images
batch = mnist.train.next_batch(batch_size)
# Print progress
if i % 50 == 0:
cur_accuracy = accuracy.eval(feed_dict = {
x: batch[0], y_loss: batch[1], keep_prob: 1.0})
print('Iteration', i, ', Accuracy =', cur_accuracy)
Train on the current batch
optimizer.run(feed_dict = {x: batch[0], y_loss: batch[1], keep_prob: 0.5})
# Compute accuracy using test data
print('Test accuracy =', accuracy.eval(feed_dict = {
x: mnist.test.images, y_loss: mnist.test.labels,
keep_prob: 1.0}))
我发现一些 post 与我的代码完全相同，但它们的所有实现都以某种方式 运行。我尝试查找解决方案，但最终没有找到适合我的解决方案。
我发现一个 post 说“基础词典没有 'train' 属性。”
这让我很好奇，如果字典通常没有这些属性，但其他人有相同的代码，为什么我会收到这个错误。
另一个post使用了这条线：
x_batch, y_batch = mnist.train.next_batch(batch_size)
而不是行：
batch = mnist.train.next_batch(batch_size)
但似乎都不适合我。另一个 changes/solutions 的 None 我试着调查了一下，但最终还是成功了。
有没有人知道如何解决这个无属性错误？
您的代码似乎是 old/out-dated，这就是它不再起作用的原因。 TensorFlow 库经常更改是很常见的，它们也经常破坏接口，因此旧代码停止工作。
首先，您尝试import mnist，这是一些错误的模块，它几乎不包含任何代码，并且似乎没有用，可能它以前有用并且可以工作，但现在没有。
此外函数 mnist.train.next_batch(...) 不再工作，因为它不再在数据集 mnist 中实现，可能它之前也工作过。
我决定实现我自己的助手 class MyDS 来实现所有这些缺失的功能。下面是您的完整更正代码，包括我的 class（开头）：
if __name__ == '__main__':
import tensorflow.compat.v1 as tf
tf.enable_eager_execution()
import tensorflow_datasets as tfds
class MyDS(object):
class SubDS(object):
import numpy as np
def __init__(self, ds, *, one_hot):
np = self.__class__.np
self.ds = [e for e in ds.as_numpy_iterator()]
self.sds = {(k + 's') : np.stack([
(e[k] if len(e[k].shape) > 0 else e[k][None]).reshape(-1) for e in self.ds
], 0) for k in self.ds[0].keys()}
self.one_hot = one_hot
if one_hot is not None:
self.max_one_hot = np.max(self.sds[one_hot + 's'])
def _to_one_hot(self, a, maxv):
np = self.__class__.np
na = np.zeros((a.shape[0], maxv + 1), dtype = a.dtype)
for i, e in enumerate(a[:, 0]):
na[i, e] = True
return na
def _apply_one_hot(self, key, maxv):
assert maxv >= self.max_one_hot, (maxv, self.max_one_hot)
self.max_one_hot = maxv
self.sds[key + 's'] = self._to_one_hot(self.sds[key + 's'], self.max_one_hot)
def next_batch(self, num = 16):
np = self.__class__.np
idx = np.random.choice(len(self.ds), num)
res = {k : np.stack([
(self.ds[i][k] if len(self.ds[i][k].shape) > 0 else self.ds[i][k][None]).reshape(-1) for i in idx
], 0) for k in self.ds[0].keys()}
if self.one_hot is not None:
res[self.one_hot] = self._to_one_hot(res[self.one_hot], self.max_one_hot)
for i, (k, v) in enumerate(list(res.items())):
res[i] = v
return res
def __getattr__(self, name):
if name not in self.__dict__['sds']:
return self.__dict__[name]
return self.__dict__['sds'][name]
def __init__(self, name, *, one_hot = None):
self.ds = tfds.load(name)
self.sds = {}
for k, v in self.ds.items():
self.sds[k] = self.__class__.SubDS(self.ds[k], one_hot = one_hot)
if one_hot is not None:
maxh = max(e.max_one_hot for e in self.sds.values())
for e in self.sds.values():
e._apply_one_hot(one_hot, maxh)
def __getattr__(self, name):
if name not in self.__dict__['sds']:
return self.__dict__[name]
return self.__dict__['sds'][name]
# Get the MNIST data
mnist = MyDS('mnist', one_hot = 'label') # tensorflow_datasets.load('mnist')
import argparse
print ('argparse version: ', argparse.__version__)
#import mnist
#print ('MNIST version: ', mnist.__version__)
#import tensorflow_datasets
print ('tensorflow_datasets version: ', tfds.__version__)
#import tensorflow.compat.v1 as tf
print ('tf version: ', tf.__version__)
tf.disable_eager_execution()
tf.disable_v2_behavior()
#from tensorflow.examples.tutorials.mnist import input_data
#def build_arg_parser():
# parser = argparse.ArgumentParser(description='Build a CNN classifier \
# using MNIST data')
# parser.add_argument('--input-dir', dest='input_dir', type=str,
# default='./mnist_data', help='Directory for storing data')
# return parser
def get_weights(shape):
data = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(data)
def get_biases(shape):
data = tf.constant(0.1, shape=shape)
return tf.Variable(data)
def create_layer(shape):
# Get the weights and biases
W = get_weights(shape)
b = get_biases([shape[-1]])
return W, b
def convolution_2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],
padding='SAME')
def max_pooling(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#args = build_arg_parser().parse_args()
# The images are 28x28, so create the input layer
# with 784 neurons (28x28=784)
x = tf.placeholder(tf.float32, [None, 784])
# Reshape 'x' into a 4D tensor
x_image = tf.reshape(x, [-1, 28, 28, 1])
# Define the first convolutional layer
W_conv1, b_conv1 = create_layer([5, 5, 1, 32])
# Convolve the image with weight tensor, add the
# bias, and then apply the ReLU function
h_conv1 = tf.nn.relu(convolution_2d(x_image, W_conv1) + b_conv1)
# Apply the max pooling operator
h_pool1 = max_pooling(h_conv1)
# Define the second convolutional layer
W_conv2, b_conv2 = create_layer([5, 5, 32, 64])
# Convolve the output of previous layer with the
# weight tensor, add the bias, and then apply
# the ReLU function
h_conv2 = tf.nn.relu(convolution_2d(h_pool1, W_conv2) + b_conv2)
# Apply the max pooling operator
h_pool2 = max_pooling(h_conv2)
# Define the fully connected layer
W_fc1, b_fc1 = create_layer([7 * 7 * 64, 1024])
# Reshape the output of the previous layer
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# Multiply the output of previous layer by the
# weight tensor, add the bias, and then apply
# the ReLU function
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Define the dropout layer using a probability placeholder
# for all the neurons
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Define the readout layer (output layer)
W_fc2, b_fc2 = create_layer([1024, 10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define the entropy loss and the optimizer
y_loss = tf.placeholder(tf.float32, [None, 10])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
# Define the accuracy computation
predicted = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_loss, 1))
accuracy = tf.reduce_mean(tf.cast(predicted, tf.float32))
# Create and run a session
sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
sess.run(init)
# Start training
num_iterations = 21000
batch_size = 75
print('\nTraining the model....')
for i in range(num_iterations):
# Get the next batch of images
batch = mnist.train.next_batch(batch_size)
# Print progress
if i % 50 == 0:
cur_accuracy = accuracy.eval(feed_dict = {
x: batch[0], y_loss: batch[1], keep_prob: 1.0})
print('Iteration', i, ', Accuracy =', cur_accuracy)
# Train on the current batch
optimizer.run(feed_dict = {x: batch[0], y_loss: batch[1], keep_prob: 0.5})
# Compute accuracy using test data
print('Test accuracy =', accuracy.eval(feed_dict = {
x: mnist.test.images, y_loss: mnist.test.labels,
keep_prob: 1.0}))
尽管我对这个话题非常陌生，但我正在尝试实现一个 CNN 程序，该程序可用于在不使用 Keras 的情况下识别图像。我目前正在使用 python 和 Jupyter/Google Colab。
在修复了我的代码中出现的其他一些错误后，我现在遇到了这个错误：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py:1761: UserWarning: An interactive session is already active. This can cause out-of-memory errors in some cases. You must explicitly call `InteractiveSession.close()` to release resources held by the other session(s).
warnings.warn('An interactive session is already active. This can '
Training the model....
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-28-1af250ed46b3> in <module>()
108 for i in range(num_iterations):
109 # Get the next batch of images
--> 110 batch = mnist.train.next_batch(batch_size) #third got an error for this line -
111 # x_batch, y_batch = mnist.train.next_batch(batch_size)
112
AttributeError: 'dict' object has no attribute 'train'
这是我当前的代码：
!pip install tensorflow_datasets
!pip install --upgrade tensorflow
!pip install tensorflow-datasets
!pip install mnist
#!pip install tensorflow.examples.tutorials.mnist
import argparse
print ('argparse version: ', argparse.__version__)
import mnist
print ('MNIST version: ', mnist.__version__)
import tensorflow_datasets
print ('tensorflow_datasets version: ', tensorflow_datasets.__version__)
import tensorflow.compat.v1 as tf
print ('tf version: ', tf.__version__)
tf.disable_v2_behavior()
#from tensorflow.examples.tutorials.mnist import input_data
#def build_arg_parser():
# parser = argparse.ArgumentParser(description='Build a CNN classifier \
# using MNIST data')
# parser.add_argument('--input-dir', dest='input_dir', type=str,
# default='./mnist_data', help='Directory for storing data')
# return parser
def get_weights(shape):
data = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(data)
def get_biases(shape):
data = tf.constant(0.1, shape=shape)
return tf.Variable(data)
def create_layer(shape):
# Get the weights and biases
W = get_weights(shape)
b = get_biases([shape[-1]])
return W, b
def convolution_2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],
padding='SAME')
def max_pooling(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
if __name__ == '__main__':
#args = build_arg_parser().parse_args()
# Get the MNIST data
mnist = tensorflow_datasets.load('mnist')
# The images are 28x28, so create the input layer
# with 784 neurons (28x28=784)
x = tf.placeholder(tf.float32, [None, 784])
# Reshape 'x' into a 4D tensor
x_image = tf.reshape(x, [-1, 28, 28, 1])
# Define the first convolutional layer
W_conv1, b_conv1 = create_layer([5, 5, 1, 32])
# Convolve the image with weight tensor, add the
# bias, and then apply the ReLU function
h_conv1 = tf.nn.relu(convolution_2d(x_image, W_conv1) + b_conv1)
# Apply the max pooling operator
h_pool1 = max_pooling(h_conv1)
# Define the second convolutional layer
W_conv2, b_conv2 = create_layer([5, 5, 32, 64])
# Convolve the output of previous layer with the
# weight tensor, add the bias, and then apply
# the ReLU function
h_conv2 = tf.nn.relu(convolution_2d(h_pool1, W_conv2) + b_conv2)
# Apply the max pooling operator
h_pool2 = max_pooling(h_conv2)
# Define the fully connected layer
W_fc1, b_fc1 = create_layer([7 * 7 * 64, 1024])
# Reshape the output of the previous layer
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# Multiply the output of previous layer by the
# weight tensor, add the bias, and then apply
# the ReLU function
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Define the dropout layer using a probability placeholder
# for all the neurons
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Define the readout layer (output layer)
W_fc2, b_fc2 = create_layer([1024, 10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define the entropy loss and the optimizer
y_loss = tf.placeholder(tf.float32, [None, 10])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
# Define the accuracy computation
predicted = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_loss, 1))
accuracy = tf.reduce_mean(tf.cast(predicted, tf.float32))
# Create and run a session
sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
sess.run(init)
# Start training
num_iterations = 21000
batch_size = 75
print('\nTraining the model....')
for i in range(num_iterations):
# Get the next batch of images
batch = mnist.train.next_batch(batch_size)
# Print progress
if i % 50 == 0:
cur_accuracy = accuracy.eval(feed_dict = {
x: batch[0], y_loss: batch[1], keep_prob: 1.0})
print('Iteration', i, ', Accuracy =', cur_accuracy)
Train on the current batch
optimizer.run(feed_dict = {x: batch[0], y_loss: batch[1], keep_prob: 0.5})
# Compute accuracy using test data
print('Test accuracy =', accuracy.eval(feed_dict = {
x: mnist.test.images, y_loss: mnist.test.labels,
keep_prob: 1.0}))
我发现一些 post 与我的代码完全相同，但它们的所有实现都以某种方式 运行。我尝试查找解决方案，但最终没有找到适合我的解决方案。
我发现一个 post 说“基础词典没有 'train' 属性。” 这让我很好奇，如果字典通常没有这些属性，但其他人有相同的代码，为什么我会收到这个错误。
另一个post使用了这条线：
x_batch, y_batch = mnist.train.next_batch(batch_size)
而不是行：
batch = mnist.train.next_batch(batch_size)
但似乎都不适合我。另一个 changes/solutions 的 None 我试着调查了一下，但最终还是成功了。
有没有人知道如何解决这个无属性错误？
您的代码似乎是 old/out-dated，这就是它不再起作用的原因。 TensorFlow 库经常更改是很常见的，它们也经常破坏接口，因此旧代码停止工作。
首先，您尝试import mnist，这是一些错误的模块，它几乎不包含任何代码，并且似乎没有用，可能它以前有用并且可以工作，但现在没有。
此外函数 mnist.train.next_batch(...) 不再工作，因为它不再在数据集 mnist 中实现，可能它之前也工作过。
我决定实现我自己的助手 class MyDS 来实现所有这些缺失的功能。下面是您的完整更正代码，包括我的 class（开头）：
if __name__ == '__main__':
import tensorflow.compat.v1 as tf
tf.enable_eager_execution()
import tensorflow_datasets as tfds
class MyDS(object):
class SubDS(object):
import numpy as np
def __init__(self, ds, *, one_hot):
np = self.__class__.np
self.ds = [e for e in ds.as_numpy_iterator()]
self.sds = {(k + 's') : np.stack([
(e[k] if len(e[k].shape) > 0 else e[k][None]).reshape(-1) for e in self.ds
], 0) for k in self.ds[0].keys()}
self.one_hot = one_hot
if one_hot is not None:
self.max_one_hot = np.max(self.sds[one_hot + 's'])
def _to_one_hot(self, a, maxv):
np = self.__class__.np
na = np.zeros((a.shape[0], maxv + 1), dtype = a.dtype)
for i, e in enumerate(a[:, 0]):
na[i, e] = True
return na
def _apply_one_hot(self, key, maxv):
assert maxv >= self.max_one_hot, (maxv, self.max_one_hot)
self.max_one_hot = maxv
self.sds[key + 's'] = self._to_one_hot(self.sds[key + 's'], self.max_one_hot)
def next_batch(self, num = 16):
np = self.__class__.np
idx = np.random.choice(len(self.ds), num)
res = {k : np.stack([
(self.ds[i][k] if len(self.ds[i][k].shape) > 0 else self.ds[i][k][None]).reshape(-1) for i in idx
], 0) for k in self.ds[0].keys()}
if self.one_hot is not None:
res[self.one_hot] = self._to_one_hot(res[self.one_hot], self.max_one_hot)
for i, (k, v) in enumerate(list(res.items())):
res[i] = v
return res
def __getattr__(self, name):
if name not in self.__dict__['sds']:
return self.__dict__[name]
return self.__dict__['sds'][name]
def __init__(self, name, *, one_hot = None):
self.ds = tfds.load(name)
self.sds = {}
for k, v in self.ds.items():
self.sds[k] = self.__class__.SubDS(self.ds[k], one_hot = one_hot)
if one_hot is not None:
maxh = max(e.max_one_hot for e in self.sds.values())
for e in self.sds.values():
e._apply_one_hot(one_hot, maxh)
def __getattr__(self, name):
if name not in self.__dict__['sds']:
return self.__dict__[name]
return self.__dict__['sds'][name]
# Get the MNIST data
mnist = MyDS('mnist', one_hot = 'label') # tensorflow_datasets.load('mnist')
import argparse
print ('argparse version: ', argparse.__version__)
#import mnist
#print ('MNIST version: ', mnist.__version__)
#import tensorflow_datasets
print ('tensorflow_datasets version: ', tfds.__version__)
#import tensorflow.compat.v1 as tf
print ('tf version: ', tf.__version__)
tf.disable_eager_execution()
tf.disable_v2_behavior()
#from tensorflow.examples.tutorials.mnist import input_data
#def build_arg_parser():
# parser = argparse.ArgumentParser(description='Build a CNN classifier \
# using MNIST data')
# parser.add_argument('--input-dir', dest='input_dir', type=str,
# default='./mnist_data', help='Directory for storing data')
# return parser
def get_weights(shape):
data = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(data)
def get_biases(shape):
data = tf.constant(0.1, shape=shape)
return tf.Variable(data)
def create_layer(shape):
# Get the weights and biases
W = get_weights(shape)
b = get_biases([shape[-1]])
return W, b
def convolution_2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],
padding='SAME')
def max_pooling(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#args = build_arg_parser().parse_args()
# The images are 28x28, so create the input layer
# with 784 neurons (28x28=784)
x = tf.placeholder(tf.float32, [None, 784])
# Reshape 'x' into a 4D tensor
x_image = tf.reshape(x, [-1, 28, 28, 1])
# Define the first convolutional layer
W_conv1, b_conv1 = create_layer([5, 5, 1, 32])
# Convolve the image with weight tensor, add the
# bias, and then apply the ReLU function
h_conv1 = tf.nn.relu(convolution_2d(x_image, W_conv1) + b_conv1)
# Apply the max pooling operator
h_pool1 = max_pooling(h_conv1)
# Define the second convolutional layer
W_conv2, b_conv2 = create_layer([5, 5, 32, 64])
# Convolve the output of previous layer with the
# weight tensor, add the bias, and then apply
# the ReLU function
h_conv2 = tf.nn.relu(convolution_2d(h_pool1, W_conv2) + b_conv2)
# Apply the max pooling operator
h_pool2 = max_pooling(h_conv2)
# Define the fully connected layer
W_fc1, b_fc1 = create_layer([7 * 7 * 64, 1024])
# Reshape the output of the previous layer
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# Multiply the output of previous layer by the
# weight tensor, add the bias, and then apply
# the ReLU function
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Define the dropout layer using a probability placeholder
# for all the neurons
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Define the readout layer (output layer)
W_fc2, b_fc2 = create_layer([1024, 10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define the entropy loss and the optimizer
y_loss = tf.placeholder(tf.float32, [None, 10])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
# Define the accuracy computation
predicted = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_loss, 1))
accuracy = tf.reduce_mean(tf.cast(predicted, tf.float32))
# Create and run a session
sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
sess.run(init)
# Start training
num_iterations = 21000
batch_size = 75
print('\nTraining the model....')
for i in range(num_iterations):
# Get the next batch of images
batch = mnist.train.next_batch(batch_size)
# Print progress
if i % 50 == 0:
cur_accuracy = accuracy.eval(feed_dict = {
x: batch[0], y_loss: batch[1], keep_prob: 1.0})
print('Iteration', i, ', Accuracy =', cur_accuracy)
# Train on the current batch
optimizer.run(feed_dict = {x: batch[0], y_loss: batch[1], keep_prob: 0.5})
# Compute accuracy using test data
print('Test accuracy =', accuracy.eval(feed_dict = {
x: mnist.test.images, y_loss: mnist.test.labels,
keep_prob: 1.0}))