Negative dimension size caused by subtracting 3 from 1 for 'conv2d_8/convolution' (op: 'Conv2D') wi

Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_8/convolution’ (op: ‘Conv2D’) with input shapes: [?,1,28,28], [3,3,28,32].

问题描述：
在Keras中声明输入层时，我得到了这个错误消息。
解决办法：
改成这样即可：
model.add(Convolution2D(32,(3,3),activation = 'relu' ,input_shape = (1,28,28),data_format = 'channels_first'))
参考网址：https://stackoverflow.com/questions/45645276/negative-dimension-size-caused-by-subtracting-3-from-1-for-conv2d-2-convolution/45647715#45647715