我的张量流版本是1.3.0。
我的python版本是3.5。
我实施CNN，然后是bid-LSTM。我在CPU上运行代码。
实施CNN后，pool2的形状将为[batch_size（None），None，106,64]。然后 tf.reshape（pool2，[ - 1，tf.shape（pool2）[1]，tf.shape（pool2）[2] xtf.shape（pool2）[3]]） 。我希望tf.reshape可以在pool2上将4D重塑为3D。然后将其提供给bid-LSTM，但 tf.nn.bidirectional_dynamic_rnn 发生错误。
它表示 ＆＃34;输入大小（输入深度）必须可通过形状推理访问，＆＃34; ValueError：输入大小（输入深度）必须可通过形状推理访问，但锯值为无。
我很久没有找到问题的解决方案了。也许我使用错误的关键字在互联网上搜索。或者给我一些正确的关键字。
x = tf.placeholder('float', shape=[None, None, 108])
y = tf.placeholder('float')
n_steps = tf.placeholder('int64')
def CNN(x):
input_layer = tf.reshape(x, [-1, tf.shape(x)[1], 108, 1])
conv1 = tf.layers.conv2d(inputs=input_layer, filters=32, kernel_size=[5, 3], padding="same", activation=tf.nn.relu)
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=1)
conv2 = tf.layers.conv2d(inputs=conv1, filters=64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=1)
output = tf.reshape(pool2, [-1, tf.shape(pool2)[1], tf.shape(pool2)[2]*tf.shape(pool2)[3]])
return output
def recurrent_neural_network(x):
layer1 = {'weights':tf.Variable(tf.random_normal([rnn_size*2,n_classes])),'biases':tf.Variable(tf.random_normal([n_classes]))}
lstm_fw_cell = tf.nn.rnn_cell.BasicLSTMCell(rnn_size,state_is_tuple=True)
lstm_bw_cell = tf.nn.rnn_cell.BasicLSTMCell(rnn_size,state_is_tuple=True)
outputs, states = tf.nn.bidirectional_dynamic_rnn(cell_fw=lstm_fw_cell, cell_bw=lstm_bw_cell, inputs=x, dtype=tf.float32) #[batch_size, max_time, cell_output_size]
outputs = tf.concat(outputs, 2)
max_length = tf.shape(outputs)[1]
outputs = tf.reshape(outputs, [-1, rnn_size*2])
prediction = tf.matmul(outputs,layer1['weights']) + layer1['biases']
prediction = tf.reshape(prediction, [-1, max_length, n_classes])
return prediction
def train_neural_network(x):
CNN_result = CNN(x)
prediction = recurrent_neural_network(CNN_result)
tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y) )
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
i=0
while i < len(train_X):
start = i
end = i+batch_size
batch_x = train_X[start:end]
batch_y = train_Y[start:end]
batch_sen_len = train_sen_len[start:end]
max_batch_sen_len = max(batch_sen_len)
#padding zero
for j in range(len(batch_x)):
k = max_batch_sen_len - len(batch_x[j])
for _ in range(k):
batch_x[j].append([0]*108)
batch_y[j].append([0]*48)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y, n_steps: batch_sen_len})
epoch_loss += c
i+=batch_size
print('Epoch', epoch+1, 'completed out of',hm_epochs,'loss:',epoch_loss)