ValueError：conv2d 层的输入 0 与层不兼容：：预期 min_ndim=4，发现 ndim=3。 收到的完整形状：（无、400、50）

Question

I keep on getting this error related to the input shape. Any help would be very appreciated. Thank you!

def deep_model():

    model = Sequential()
    model.add(keras.layers.Conv1D(filters=50, kernel_size=9, strides=1, padding='same', 
               batch_input_shape=(None, Length, 4), activation='relu'))

    model.add(keras.layers.Conv2D(32, kernel_size =(9, 9), strides =(1, 1),
                    activation ='relu'))
    model.add(MaxPooling2D(pool_size =(2, 2), strides =(2, 2)))
    model.add(keras.layers.Conv2D(64, (9, 9), activation ='relu'))
    model.add(MaxPooling2D(pool_size =(2, 2)))
    model.add(Flatten())
    model.add(Dense(100, activation ='relu'))
    model.add(Dropout(0.3))
    model.add(Dense(3, activation ='softmax'))

    # training the model
    model.compile(loss = keras.losses.categorical_crossentropy,
                optimizer = keras.optimizers.SGD(lr = 0.01),
                metrics =['accuracy'])

    return model

x_train = x_train.reshape(-1, 400, 4)

raise ValueError('Input ' + str(input_index) + ' of layer ' + ValueError: Input 0 of layer conv2d is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: (None, 400, 50)

I tried to reshape the x_train also but got this error:

x_train = x_train.reshape(-1, 400, 400, 4) ValueError: cannot reshape array of size 43200000 into shape (400,400,4)

Answer 1

I think you need the input shape to have an extra dimension. The reason your reshaping failed is because 400 * 400 * 4 is equal to 640000 and not 43200000

This is how you would do it:

x_train = x_train[np.newaxis]