在下面的神经网络训练的Keras和Tensorflow实现中,keras实现中的model.train_on_batch([x], [y])
与Tensorflow实现中的sess.run([train_optimizer, cross_entropy, accuracy_op], feed_dict=feed_dict)
有何不同?特别是:这两条线如何导致训练中的不同计算?:
keras_version.py
input_x = Input(shape=input_shape, name="x")
c = Dense(num_classes, activation="softmax")(input_x)
model = Model([input_x], [c])
opt = Adam(lr)
model.compile(loss=['categorical_crossentropy'], optimizer=opt)
nb_batchs = int(len(x_train)/batch_size)
for epoch in range(epochs):
loss = 0.0
for batch in range(nb_batchs):
x = x_train[batch*batch_size:(batch+1)*batch_size]
y = y_train[batch*batch_size:(batch+1)*batch_size]
loss_batch, acc_batch = model.train_on_batch([x], [y])
loss += loss_batch
print(epoch, loss / nb_batchs)
tensorflow_version.py
input_x = Input(shape=input_shape, name="x")
c = Dense(num_classes)(input_x)
input_y = tf.placeholder(tf.float32, shape=[None, num_classes], name="label")
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(labels=input_y, logits=c, name="xentropy"),
name="xentropy_mean"
)
train_optimizer = tf.train.AdamOptimizer(learning_rate=lr).minimize(cross_entropy)
nb_batchs = int(len(x_train)/batch_size)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for epoch in range(epochs):
loss = 0.0
acc = 0.0
for batch in range(nb_batchs):
x = x_train[batch*batch_size:(batch+1)*batch_size]
y = y_train[batch*batch_size:(batch+1)*batch_size]
feed_dict = {input_x: x,
input_y: y}
_, loss_batch = sess.run([train_optimizer, cross_entropy], feed_dict=feed_dict)
loss += loss_batch
print(epoch, loss / nb_batchs)
注意:Same (?) model converges in Keras but not in Tensorflow后面是这个问题,该问题被认为过于笼统,但在其中我确切地说明了为什么我认为这两个语句有所不同并导致不同的计算。 >
答案 0 :(得分:6)
是的,结果可能会有所不同。如果您事先了解以下内容,结果就不会令人惊讶:
corss-entropy
的实现方式有所不同。 Tensorflow假定tf.nn.softmax_cross_entropy_with_logits_v2
的输入为未标准化的原始logit,而Keras
接受的输入为概率optimizers
的实现方式不同。