import torch
import torch.nn as nn
__all__ = [
'ShuffleNetV2', 'shufflenet_v2_x0_5', 'shufflenet_v2_x1_0',
'shufflenet_v2_x1_5', 'shufflenet_v2_x2_0'
]
model_urls = {
'shufflenetv2_x0.5': 'https://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth',
'shufflenetv2_x1.0': 'https://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pth',
'shufflenetv2_x1.5': None,
'shufflenetv2_x2.0': None,
}
def channel_shuffle(x, groups):
batchsize, num_channels, height, width = x.data.size()
channels_per_group = num_channels // groups
# reshape
x = x.view(batchsize, groups,
channels_per_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
# flatten
x = x.view(batchsize, -1, height, width)
return x
class Flatten(nn.Module):
def forward(self, input):
return input.view(input.size(0), -1)
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride):
super(InvertedResidual, self).__init__()
if not (1 <= stride <= 3):
raise ValueError('illegal stride value')
self.stride = stride
branch_features = oup // 2
assert (self.stride != 1) or (inp == branch_features << 1)
if self.stride > 1:
self.branch1 = nn.Sequential(
self.depthwise_conv(inp, inp, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(inp),
nn.Conv2d(inp, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
self.branch2 = nn.Sequential(
nn.Conv2d(inp if (self.stride > 1) else branch_features,
branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
self.depthwise_conv(branch_features, branch_features, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(branch_features),
nn.Conv2d(branch_features, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
@staticmethod
def depthwise_conv(i, o, kernel_size, stride=1, padding=0, bias=False):
return nn.Conv2d(i, o, kernel_size, stride, padding, bias=bias, groups=i)
def forward(self, x):
if self.stride == 1:
x1, x2 = x.chunk(2, dim=1)
out = torch.cat((x1, self.branch2(x2)), dim=1)
else:
out = torch.cat((self.branch1(x), self.branch2(x)), dim=1)
out = channel_shuffle(out, 2)
return out
class ShuffleNetV2(nn.Module):
def __init__(self, stages_repeats, stages_out_channels):
super(ShuffleNetV2, self).__init__()
drop_ratio = 0.4
feature_dim = 512
if len(stages_repeats) != 3:
raise ValueError('expected stages_repeats as list of 3 positive ints')
if len(stages_out_channels) != 5:
raise ValueError('expected stages_out_channels as list of 5 positive ints')
self._stage_out_channels = stages_out_channels
input_channels = 3
output_channels = self._stage_out_channels[0]
self.conv1 = nn.Sequential(
nn.Conv2d(input_channels, output_channels, 3, 2, 1, bias=False),
nn.BatchNorm2d(output_channels),
nn.ReLU(inplace=True),
)
input_channels = output_channels
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
stage_names = ['stage{}'.format(i) for i in [2, 3, 4]]
for name, repeats, output_channels in zip(
stage_names, stages_repeats, self._stage_out_channels[1:]):
seq = [InvertedResidual(input_channels, output_channels, 2)]
for i in range(repeats - 1):
seq.append(InvertedResidual(output_channels, output_channels, 1))
setattr(self, name, nn.Sequential(*seq))
input_channels = output_channels
output_channels = self._stage_out_channels[-1]
self.conv5 = nn.Sequential(
nn.Conv2d(input_channels, output_channels, 1, 1, 0, bias=False),
nn.BatchNorm2d(output_channels),
nn.ReLU(inplace=True),
)
self.output_layer = nn.Sequential(nn.BatchNorm2d(output_channels),
nn.Dropout(drop_ratio),
Flatten(),
nn.Linear(output_channels * 7 * 7, feature_dim),
nn.BatchNorm1d(feature_dim))
def forward(self, x):
x = self.conv1(x)
x = self.maxpool(x)
x = self.stage2(x)
x = self.stage3(x)
x = self.stage4(x)
x = self.conv5(x)
x = self.output_layer(x)
return x
def _shufflenetv2(arch, pretrained, progress, *args, **kwargs):
model = ShuffleNetV2(*args, **kwargs)
if pretrained:
model_url = model_urls[arch]
if model_url is None:
raise NotImplementedError('pretrained {} is not supported as of now'.format(arch))
else:
state_dict = load_state_dict_from_url(model_url, progress=progress)
model.load_state_dict(state_dict)
return model
def shufflenet_v2_x0_5(pretrained=False, progress=True, **kwargs):
return _shufflenetv2('shufflenetv2_x0.5', pretrained, progress,
[4, 8, 4], [24, 48, 96, 192, 1024], **kwargs)
def shufflenet_v2_x1_0(pretrained=False, progress=True, **kwargs):
return _shufflenetv2('shufflenetv2_x1.0', pretrained, progress,
[4, 8, 4], [24, 116, 232, 464, 1024], **kwargs)
def shufflenet_v2_x1_5(pretrained=False, progress=True, **kwargs):
return _shufflenetv2('shufflenetv2_x1.5', pretrained, progress,
[4, 8, 4], [24, 176, 352, 704, 1024], **kwargs)
def shufflenet_v2_x2_0(pretrained=False, progress=True, **kwargs):
return _shufflenetv2('shufflenetv2_x2.0', pretrained, progress,
[4, 8, 4], [24, 244, 488, 976, 2048], **kwargs)
if __name__ == "__main__":
input = torch.Tensor(2, 3, 112, 112)
net = shufflenet_v2_x0_5(pretrained=False)
print(net)
x = net(input)
print(x.shape)
I added self.output_layer to use shufflenetv2 as feature extractor.
However, I got the error as below. How can I fix it?
Traceback (most recent call last):
File "shufflenetv2.py", line 221, in <module>
x = net(input)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs)
File "shufflenetv2.py", line 146, in forward
x = self.output_layer(x)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/modules/linear.py", line 55, in forward
return F.linear(input, self.weight, self.bias)
File "/home/cobie/.local/lib/python3.5/site-packages/torch/nn/functional.py", line 992, in linear
return torch.addmm(bias, input, weight.t())
RuntimeError: size mismatch, m1: [2 x 16384], m2: [50176 x 512] at /pytorch/aten/src/TH/generic/THTensorMath.c:2033