def __init__(self,
block,
layers,
channels,
drop_rate,
classes=10,
**kwargs):
super(CIFARWideResNet, self).__init__(**kwargs)
assert len(layers) == len(channels) - 2
self.features = list()
self.features.append(_bn_no_affine(channels[0]))
self.features.append(
nn.Conv2d(channels[0], channels[1], 3, 1, 1, bias=False))
self.features.append(nn.BatchNorm2d(channels[1]))
in_channels = channels[1]
for i, num_layer in enumerate(layers):
stride = 1 if i == 0 else 2
self.features.append(
self._make_layer(block, num_layer, in_channels,
channels[i + 2], drop_rate, stride))
in_channels = channels[i + 2]
self.features.append(nn.BatchNorm2d(channels[-1]))
self.features.append(nn.ReLU(inplace=True))
self.features = nn.Sequential(*self.features)
self.output = nn.Linear(channels[-1], classes)
def __init__(self,
block,
layers,
channels,
classes=1000,
thumbnail=False,
last_gamma=False,
**kwargs):
super(ResNetV2, self).__init__(**kwargs)
assert len(layers) == len(channels) - 2
self.features = list()
self.features.append(_bn_no_affine(channels[0]))
if thumbnail:
self.features.append(_conv3x3(channels[0], channels[1], 1))
else:
self.features.append(
nn.Conv2d(channels[0], channels[1], 7, 2, 3, bias=False))
self.features.append(nn.BatchNorm2d(channels[1]))
self.features.append(nn.ReLU(inplace=True))
self.features.append(nn.MaxPool2d(3, 2, 1))
for i, num_layer in enumerate(layers):
stride = 1 if i == 0 else 2
self.features.append(
self._make_layer(block,
num_layer,
channels[i + 1],
channels[i + 2],
stride,
last_gamma=last_gamma))
self.features.append(nn.BatchNorm2d(channels[-1]))
self.features.append(nn.ReLU(inplace=True))
self.features = nn.Sequential(*self.features)
self.output = nn.Linear(channels[-1], classes)