I’m having hard time to completely understand the make_layer method here. Could someone please help me with a bit more clarification?
def _make_layer(block,inplanes,planes, blocks, stride=1):
downsample = None
if stride != 1 or inplanes != planes:
downsample = nn.Sequential(
nn.Conv2d(inplanes, planes, 1, stride, bias=False),
nn.BatchNorm2d(planes),
)
layers = []
layers.append(block(inplanes, planes, stride, downsample))
inplanes = planes
for _ in range(1, blocks):
layers.append(block(inplanes, planes))
return nn.Sequential(*layers)
