Input（shape =（6,7））在model.predict上需要3个维度

Question

ValueError: Error when checking input: 
expected input_1 to have 3 dimensions, but got array with shape (6, 7)

_____________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to
==============================================================================
input_1 (InputLayer)            (None, 6, 7)         0

    out1, out2 = model.predict(board)

    inputs = Input(shape=(6,7))
    inputs_reshape = Reshape((6,7,1))(inputs) # channels, batch_size, rows, cols
    net = Conv2D(4, kernel_size=3, activation='relu', 
            padding='same', data_format='channels_last')(inputs_reshape)
    net = Flatten()(net)
    pi = Dense(7, activation='softmax', name='pi')(net) 
    v = Dense(1, activation='tanh', name='v')(net)

    model = Model(inputs=inputs, outputs=[v, pi])

来自keras.io文档，它说shape的{​​{1}}维度不包括批量大小，并且Input()默认设置mdoel.predict()。

如果batch_size=32期望model.predict(data)为data.shape，那么(batches, 6,7)和model.predict(data, batch_size=1有什么区别

Answer 1

是的，模型的batch_shape是(None, 6, 7)，三个维度。第一个值None是批处理大小（可以是任意值）。

因此，正如batch_shape确定的那样，期望您的数据具有3维。