卷积网络中FeatureMap的height/width计算

Feature Map:

Height:  (input_height - kernel_size + 2*padding )/stride[0]  +  1

Width:   (input_width  - kernel_size + 2*padding )/stride[1]   +  1

反卷积：

ConvTranspose2d(in_channel, out_channel, kernel_size, stride, 

                   padding, output_padding, groups=1, bias=True, dilation=1)

Height_out = (Height_in - 1) * stride[0] - 2 * padding[0] + kernel_size[0] + output_padding[0]

Width_out = (Width_in - 1) * stride[1] - 2 * padding[1] + kernel_size[1] + output_padding[1]