Question

我有一个重塑问题，但是我不知道如何为inputA调整尺寸。我不断收到错误消息：

ValueError：conv1d_29层的输入0与该层不兼容：预期ndim = 3，找到的ndim = 2。收到完整的图形：[无，3750]

也许有人可以帮助我，为我提供适当尺寸的提示：

# reshape after CV, need to merge all the columns before CV, shouldn't be reshaped in order to match the dimensions

# X_train=X_train.reshape(len(X_train),5200,1)
# X_test=X_test.reshape(len(X_test),5200,1)

def create_model():
    
    n_timesteps=3750
    n_features=1
    n_outputs=1
    
    
    inputA = Input(shape=(X_train.shape[1:]))
    inputB = Input(shape=(1,))
    inputC = Input(shape=(1,))
    inputD = Input(shape=(1,))
    
    x = InputLayer(input_shape=(None, X_train.shape[1:][0],1))(inputA)
    x = Conv1D(64, 3, activation='relu')(inputA) #, input_shape=(None, 3750, n_features)
    x = Conv1D(64, 3, activation='relu')(x)
    x = MaxPooling1D(3)(x)
    x = Conv1D(128, 3, activation='relu')(x)
    x = Conv1D(128, 3, activation='relu')(x)
#     x = Dropout(0.5)(x)
    x = Flatten()(x)

    concatenated_features = concatenate([x,inputB,inputC,inputD])
    x = Dense(64,activation='relu')(concatenated_features)
# Check for the position of the dropout
    #     x = Dropout(0.5)(x)
    x = Dense(n_outputs, activation='sigmoid')(x)

    model = Model(inputs=[inputA, inputB,inputC,inputD], outputs=x)


    model.compile(loss='binary_crossentropy',
                  optimizer=Adam(lr=lr),
                  metrics=['accuracy'])
    print(model.summary())
    return model

仅提供更多信息：我的inputA是X_train的输入，其尺寸为（318，3750）。

ValueError：层conv1d_29的输入0与布局不兼容

0 个答案: