我使用Keras编写了一个包含BatchNormalization层的神经网络。
当我用model.fit进行训练时，一切都很好。如此处所述，在天真Tensorflow中进行训练时，训练过程十分艰辛！
我意识到我需要explicitly run the BatchNormalization operations。当我尝试实施上一个链接中提供的解决方案时，似乎遇到了一些问题：
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
from tensorflow.python.keras import optimizers
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Conv2D, Dense, Flatten, MaxPooling2D
from tensorflow.python.keras.layers import BatchNormalization
from tensorflow.python.keras.regularizers import l2
sess = tf.Session()
def train(sess):
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
print(update_ops)
with tf.control_dependencies(update_ops):
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)
sess.run(tf.global_variables_initializer())
history = []
iterep = 500
for i in range(iterep * 30):
x_train, y_train = mnist.train.next_batch(100)
x_train = x_train.reshape((100, 28, 28, 1))
sess.run(train_step,feed_dict={'x:0': x_train,'y:0': y_train})
if (i + 1) % iterep == 0:
epoch = (i + 1)/iterep
tr = sess.run([loss, accuracy],
feed_dict={'x:0': mnist.train.images.reshape((55000, 28, 28, 1)),'y:0': mnist.train.labels})
t = sess.run([loss, accuracy],
feed_dict={'x:0': mnist.test.images.reshape((10000, 28, 28, 1)),'y:0': mnist.test.labels})
history += [[epoch] + tr + t]
print(history[-1])
return history
x = tf.placeholder('float32', (None, 28, 28, 1), name='x')
y = tf.placeholder('float32', (None, 10), name='y')
phase = tf.placeholder(tf.bool, name='phase')
weight_decay = 0.0001
model = Sequential()
model.add(Conv2D(6, (5, 5), padding='valid', kernel_regularizer=l2(weight_decay), activation = 'relu', kernel_initializer='he_normal', input_shape=(28, 28, 1)))
model.add(BatchNormalization())
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Conv2D(16, (5, 5), padding='valid', activation = 'relu', kernel_initializer='he_normal'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(120, activation = 'relu', kernel_initializer='he_normal'))
model.add(Dense(84, activation = 'relu', kernel_initializer='he_normal'))
model.add(Dense(10, activation = 'softmax', kernel_initializer='he_normal'))
sgd = optimizers.SGD(lr=0.1, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
out = model(x)
with tf.name_scope('accuracy'):accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(y, 1), tf.argmax(out, 1)), 'float32'))
loss = tf.reduce_mean(tf.keras.backend.categorical_crossentropy(out, y))
print('Training ...')
history_lenet = train(sess)
试图执行以上代码，我遇到以下错误，并将所需的参数传递给张量操作，但似乎仍然抱怨我没有。
Traceback (most recent call last):
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1361, in _do_call
return fn(*args)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _run_fn
target_list, status, run_metadata)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 516, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'conv2d_1_input' with dtype float and shape [?,28,28,1]
[[Node: conv2d_1_input = Placeholder[dtype=DT_FLOAT, shape=[?,28,28,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "ex.py", line 56, in <module>
history_lenet = train(sess)
File "ex.py", line 25, in train
sess.run(train_step,feed_dict={'x:0': x_train,'y:0': y_train})
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 905, in run
run_metadata_ptr)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1137, in _run
feed_dict_tensor, options, run_metadata)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1355, in _do_run
options, run_metadata)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1374, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'conv2d_1_input' with dtype float and shape [?,28,28,1]
[[Node: conv2d_1_input = Placeholder[dtype=DT_FLOAT, shape=[?,28,28,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Caused by op 'conv2d_1_input', defined at:
File "ex.py", line 41, in <module>
model.add(Conv2D(6, (5, 5), padding='valid', kernel_regularizer=l2(weight_decay), activation = 'relu', kernel_initializer='he_normal', input_shape=(28, 28, 1)))
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/models.py", line 489, in add
batch_shape=batch_shape, dtype=dtype, name=layer.name + '_input')
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/engine/topology.py", line 634, in Input
input_tensor=tensor)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/engine/topology.py", line 543, in __init__
name=name)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/layers/network.py", line 98, in __init__
name=self.name)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1746, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3051, in _placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3271, in create_op
op_def=op_def)
File "/Users/deepak/.pyenv/versions/3.6.4/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1650, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'conv2d_1_input' with dtype float and shape [?,28,28,1]
[[Node: conv2d_1_input = Placeholder[dtype=DT_FLOAT, shape=[?,28,28,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]