Keras得到错误的输出形状

Question

对于以下CNN

model = Sequential()
model.add(Convolution2D(64, 3, 3, border_mode='same', input_shape=(3, 256, 256)))
# now model.output_shape == (None, 64, 256, 256)
# add a 3x3 convolution on top, with 32 output filters:
model.add(Convolution2D(32, 3, 3, border_mode='same'))
# now model.output_shape == (None, 32, 256, 256)
print(model.summary())

然而，模型摘要给出了以下输出

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
convolution2d_44 (Convolution2D) (None, 3, 256, 64)    147520      convolution2d_input_24[0][0]     
____________________________________________________________________________________________________
convolution2d_45 (Convolution2D) (None, 3, 256, 32)    18464       convolution2d_44[0][0]           
====================================================================================================
Total params: 165984

为什么我得到给定的输出形状?

Answer 1

这是input_shape的设置导致的问题。在当前设置中，您想要输入3通道的256x256。但是，Keras认为您提供的是带有256通道的3x256图像。有几种方法可以纠正它。

• 选项1:更改input_shape

中的顺序

• 选项2:在图层中指定image_dim_ordering

• 选项3:通过将~/.keras/keras.json

中的'tf'更改为'th'来修改keras配置文件