Keras输出形状错误

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())

但是,模型摘要提供以下输出

____________________________________________________________________________________________________
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

这是由设置引起的问题input_shape.在当前设置中,您希望输入带有3个通道的256x256.但是,Keras认为你提供的是具有256个通道的3x256图像.有几种方法可以纠正它.

• 选项1:更改订单 input_shape

• 选项2:image_dim_ordering在图层中指定

• 选项3:通过在〜/ .keras/keras.json中将'tf'更改为'th'来修改keras配置文件