Keras（Tensorflow）重塑图层输入错误

Question

我有一个整形输入错误，我不知道为什么。 请求的形状是 1058400，等于 (1, 21168) 乘以批量大小 50。 我不明白的是 677376 的表观输入大小。 我不知道这个值是从哪里来的。 reshape 之前的图层是 flatten 图层，我在定义 Reshape 图层的目标形状时直接使用它的形状。

模型编译得很好，我使用 Tensorflow 作为后端，所以它是在运行时之前定义的。但是只有在我输入日期时才会出现错误。

代码：

import numpy as np
import tensorflow as tf

import keras.backend as K
from keras import Model
from keras.layers import LSTM, Conv2D, Dense, Flatten, Input, Reshape
from keras.optimizers import Adam

config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
K.set_session(sess)

input = Input(batch_shape=(50, 230, 230, 1))

conv1 = Conv2D(
    filters=12, kernel_size=(7, 7), strides=(1, 1), padding="valid", activation="relu"
)(input)
conv2 = Conv2D(
    filters=24, kernel_size=(5, 5), strides=(1, 1), padding="valid", activation="relu"
)(conv1)
conv3 = Conv2D(
    filters=48, kernel_size=(3, 3), strides=(2, 2), padding="valid", activation="relu"
)(conv2)
conv4 = Conv2D(
    filters=48, kernel_size=(5, 5), strides=(5, 5), padding="valid", activation="relu"
)(conv3)

conv_out = Flatten()(conv4)
conv_out = Reshape(target_shape=(1, int(conv_out.shape[1])))(conv_out)
conv_out = Dense(128, activation="relu")(conv_out)

rnn_1 = LSTM(128, stateful=True, return_sequences=True)(conv_out)
rnn_2 = LSTM(128, stateful=True, return_sequences=True)(rnn_1)
rnn_3 = LSTM(128, stateful=True, return_sequences=False)(rnn_2)

value = Dense(1, activation="linear")(rnn_3)
policy = Dense(5, activation="softmax")(rnn_3)

model = Model(inputs=input, outputs=[value, policy])
adam = Adam(lr=0.001)
model.compile(loss="mse", optimizer=adam)

model.summary()

out = model.predict(np.random.randint(1, 5, size=(50, 230, 230, 1)))
print(out)

总结：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (50, 230, 230, 1)    0                                            
__________________________________________________________________________________________________
conv2d (Conv2D)                 (50, 224, 224, 12)   600         input_1[0][0]                    
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (50, 220, 220, 24)   7224        conv2d[0][0]                     
__________________________________________________________________________________________________
conv2d_2 (Conv2D)               (50, 109, 109, 48)   10416       conv2d_1[0][0]                   
__________________________________________________________________________________________________
conv2d_3 (Conv2D)               (50, 21, 21, 48)     57648       conv2d_2[0][0]                   
__________________________________________________________________________________________________
flatten (Flatten)               (50, 21168)          0           conv2d_3[0][0]                   
 __________________________________________________________________________________________________
reshape (Reshape)               (50, 1, 21168)       0           flatten[0][0]                    
__________________________________________________________________________________________________
dense (Dense)                   (50, 1, 128)         2709632     reshape[0][0]                    
 __________________________________________________________________________________________________
lstm (LSTM)                     (50, 1, 128)         131584      dense[0][0]                      
__________________________________________________________________________________________________
lstm_1 (LSTM)                   (50, 1, 128)         131584      lstm[0][0]                       
__________________________________________________________________________________________________
lstm_2 (LSTM)                   (50, 128)            131584      lstm_1[0][0]                     
__________________________________________________________________________________________________
dense_1 (Dense)                 (50, 1)              129         lstm_2[0][0]                     
__________________________________________________________________________________________________
dense_2 (Dense)                 (50, 5)              645         lstm_2[0][0] 
==================================================================================================
Total params: 3,181,046
Trainable params: 3,181,046
Non-trainable params: 0

编辑：

上述代码错误：

Traceback (most recent call last):
  File "foo.py", line 45, in <module>
    out = model.predict(np.random.randint(1, 5, size=(50, 230, 230, 1)))
  File "/home/vyz/.conda/envs/stackoverflow/lib/python3.6/site-packages/keras/engine/training.py", line 1157, in predict
    'Batch size: ' + str(batch_size) + '.')
ValueError: In a stateful network, you should only pass inputs with a number of samples that can be divided by the batch size. Found: 50 samples. Batch size: 32.

Answer 1

问题的版本

重要提示：我已经编辑了您的问题，因此它可以实际运行并代表您的问题。 Input 应采用当前提供的 batch_shape。下次请确保您的代码有效，会更容易。

解决方案

解决方法很简单；您传递给网络的批次尺寸错误。

677376 / 21168 = 32 它是批次的默认大小，这是predict 所期望的。如果它不同（在您的情况下为 50），您应该指定它，如下所示：

out = model.predict(np.random.randint(1, 5, size=(50, 230, 230, 1)), batch_size=50)

现在一切都应该正常了，如果你想硬编码，记得指定批量大小。