def _make_layer(self, block, channels, blocks, stride=1, **kwargs):
layers = [block(self.in_channels, channels, stride=stride, **kwargs)]
self.in_channels = channels * block.expansion
for i in range(1, blocks):
layers.append(block(self.in_channels, channels, stride=1,
**kwargs))
return Sequential(layers)
def __init__(self, in_channels, channels, stride, group_channels, cardinality,
start_block=False, end_block=False, exclude_bn0=False):
super().__init__()
out_channels = channels * self.expansion
width = group_channels * cardinality
if not start_block and not exclude_bn0:
self.bn0 = Norm(in_channels)
if not start_block:
self.act0 = Act()
self.conv1 = Conv2d(in_channels, width, kernel_size=1)
self.bn1 = Norm(width)
self.act1 = Act()
self.conv2 = Conv2d(width, width, kernel_size=3, stride=stride, groups=cardinality,
norm='def', act='def')
self.conv3 = Conv2d(width, out_channels, kernel_size=1)
if start_block:
self.bn3 = Norm(out_channels)
if end_block:
self.bn3 = Norm(out_channels)
self.act3 = Act()
if stride != 1 or in_channels != out_channels:
shortcut = []
if stride != 1:
shortcut.append(Pool2d(2, 2, type='avg'))
shortcut.append(
Conv2d(in_channels, out_channels, kernel_size=1, norm='def'))
self.shortcut = Sequential(shortcut)
else:
self.shortcut = Identity()
self.start_block = start_block
self.end_block = end_block
self.exclude_bn0 = exclude_bn0
def __init__(self, in_channels, channels, stride, erase_relu):
super().__init__()
out_channels = channels * self.expansion
self.conv1 = Conv2d(in_channels,
out_channels,
kernel_size=3,
stride=stride,
norm='def',
act='def')
self.conv2 = Conv2d(out_channels,
out_channels,
kernel_size=3,
norm='def')
if stride != 1 or in_channels != out_channels:
shortcut = []
if stride != 1:
shortcut.append(Pool2d(2, 2, type='avg'))
shortcut.append(
Conv2d(in_channels, out_channels, kernel_size=1, norm='def'))
self.shortcut = Sequential(shortcut)
else:
self.shortcut = Identity()
self.act = Act() if not erase_relu else Identity()
def _make_layer(self, block, channels, blocks, stride, **kwargs):
layers = [block(self.in_channels, channels, stride=stride, start_block=True,
**kwargs)]
self.in_channels = channels * block.expansion
for i in range(1, blocks):
layers.append(block(self.in_channels, channels, stride=1,
exclude_bn0=i == 1, end_block=i == blocks - 1,
**kwargs))
return Sequential(layers)
def __init__(self,
in_channels,
channels,
stride,
dropout,
drop_path,
start_block=False,
end_block=False,
exclude_bn0=False):
super().__init__()
# For torch.jit.script
self.bn0 = Identity()
self.act0 = Identity()
self.act2 = Identity()
self.bn2 = Identity()
out_channels = channels * self.expansion
if not start_block and not exclude_bn0:
self.bn0 = Norm(in_channels)
if not start_block:
self.act0 = Act()
self.conv1 = Conv2d(in_channels,
out_channels,
kernel_size=3,
stride=stride)
self.bn1 = Norm(out_channels)
self.act1 = Act()
self.dropout = Dropout(dropout) if dropout else Identity()
self.conv2 = Conv2d(out_channels, out_channels, kernel_size=3)
if start_block:
self.bn2 = Norm(out_channels)
self.drop_path = DropPath(drop_path) if drop_path else Identity()
if end_block:
self.bn2 = Norm(out_channels)
self.act2 = Act()
if stride != 1 or in_channels != out_channels:
shortcut = []
if stride != 1:
shortcut.append(Pool2d(2, 2, type='avg'))
shortcut.append(
Conv2d(in_channels, out_channels, kernel_size=1, norm='def'))
self.shortcut = Sequential(shortcut)
else:
self.shortcut = Identity()
self.start_block = start_block
self.end_block = end_block
self.exclude_bn0 = exclude_bn0