[人工智能]理解深度学习代码之Conv2d(kernel_size) 记录

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)

kernel_size:卷积核尺寸，可以设为1个int型数或者一个(int, int)型的元组。例如(2,3)是高2宽3卷积核

kernel_size=(1, 3)[flag]
if flag == False: kernel_size = 3 else: kernel_size = 1