ValueError: Input 0 of layer sequential_40 is incompatible with the layer

Question

我正在通过向模型添加注意力层来修改旧代码。但我无法弄清楚如何以正确的输入大小堆叠图层。

实际输入数据为(200,189,1).

//我正在尝试这样的事情

def mocap_model(optimizer='SGD'):
    model = Sequential()
    model.add(Conv2D(32, 3, strides=(2, 2), padding ='same', input_shape=(200, 189, 1)))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Conv2D(64, 3, strides=(2, 2), padding ='same'))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Conv2D(64, 3, strides=(2, 2), padding ='same'))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Conv2D(128, 3, strides=(2, 2), padding ='same'))
    model.add(Dropout(0.2))
    model.add(Flatten())

    return model

cnn = mocap_model()
    
main_input = Input(shape=(200, 189, 1))
    
rnn = Sequential()
rnn = LSTM(256, return_sequences=True, input_shape=(200,189))
    
model = TimeDistributed(cnn)(main_input) 
model = rnn(model)
    
att_in=LSTM(256,return_sequences=True,dropout=0.3,recurrent_dropout=0.2)(model)
att_out=attention()(att_in)
output3=Dense(256,activation='relu',trainable=True)(att_out)
output4=Dense(4,activation='softmax',trainable=True)(output3)
model=Model(main_input,output4)
    
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()

但是我得到这个错误：

----> 8 model = TimeDistributed(cnn)(main_input)

ValueError：层 sequential_40 的输入 0 与层不兼容：：预期 min_ndim=4，发现 ndim=3。已收到完整形状：(None, 189, 1)

Answer 1

输入形状有问题。 tf.keras.layers.TimeDistributed 需要批量大小作为输入。期望输入：形状为 (batch, time, ...) 的输入张量。在 main_input 添加 batch_size

main_input = Input(shape=(10, 200, 189, 1))

工作示例代码

import tensorflow as tf

cnn = tf.keras.Sequential()
cnn.add(tf.keras.layers.Conv2D(64, 1, 1, input_shape=(200, 189, 1)))
cnn.add(tf.keras.layers.Flatten())
cnn.output_shape

main_input = tf.keras.Input(shape=(10, 200, 189, 1))
outputs = tf.keras.layers.TimeDistributed(cnn)(main_input)
outputs.shape

输出

TensorShape([None, 10, 2419200])

ValueError: Input 0 of layer sequential_40 is incompatible with the layer

ValueError: Input 0 of layer sequential_40 is incompatible with the layer

python

tensorflow

machine-learning

keras

recurrent-neural-network