237 lines
7.4 KiB
Python
237 lines
7.4 KiB
Python
"""
|
|
Code source: https://github.com/pytorch/vision
|
|
"""
|
|
from __future__ import division, absolute_import
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.utils.model_zoo as model_zoo
|
|
|
|
__all__ = ['squeezenet1_0', 'squeezenet1_1', 'squeezenet1_0_fc512']
|
|
|
|
model_urls = {
|
|
'squeezenet1_0':
|
|
'https://download.pytorch.org/models/squeezenet1_0-a815701f.pth',
|
|
'squeezenet1_1':
|
|
'https://download.pytorch.org/models/squeezenet1_1-f364aa15.pth',
|
|
}
|
|
|
|
|
|
class Fire(nn.Module):
|
|
|
|
def __init__(
|
|
self, inplanes, squeeze_planes, expand1x1_planes, expand3x3_planes
|
|
):
|
|
super(Fire, self).__init__()
|
|
self.inplanes = inplanes
|
|
self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
|
|
self.squeeze_activation = nn.ReLU(inplace=True)
|
|
self.expand1x1 = nn.Conv2d(
|
|
squeeze_planes, expand1x1_planes, kernel_size=1
|
|
)
|
|
self.expand1x1_activation = nn.ReLU(inplace=True)
|
|
self.expand3x3 = nn.Conv2d(
|
|
squeeze_planes, expand3x3_planes, kernel_size=3, padding=1
|
|
)
|
|
self.expand3x3_activation = nn.ReLU(inplace=True)
|
|
|
|
def forward(self, x):
|
|
x = self.squeeze_activation(self.squeeze(x))
|
|
return torch.cat(
|
|
[
|
|
self.expand1x1_activation(self.expand1x1(x)),
|
|
self.expand3x3_activation(self.expand3x3(x))
|
|
], 1
|
|
)
|
|
|
|
|
|
class SqueezeNet(nn.Module):
|
|
"""SqueezeNet.
|
|
|
|
Reference:
|
|
Iandola et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters
|
|
and< 0.5 MB model size. arXiv:1602.07360.
|
|
|
|
Public keys:
|
|
- ``squeezenet1_0``: SqueezeNet (version=1.0).
|
|
- ``squeezenet1_1``: SqueezeNet (version=1.1).
|
|
- ``squeezenet1_0_fc512``: SqueezeNet (version=1.0) + FC.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
num_classes,
|
|
loss,
|
|
version=1.0,
|
|
fc_dims=None,
|
|
dropout_p=None,
|
|
**kwargs
|
|
):
|
|
super(SqueezeNet, self).__init__()
|
|
self.loss = loss
|
|
self.feature_dim = 512
|
|
|
|
if version not in [1.0, 1.1]:
|
|
raise ValueError(
|
|
'Unsupported SqueezeNet version {version}:'
|
|
'1.0 or 1.1 expected'.format(version=version)
|
|
)
|
|
|
|
if version == 1.0:
|
|
self.features = nn.Sequential(
|
|
nn.Conv2d(3, 96, kernel_size=7, stride=2),
|
|
nn.ReLU(inplace=True),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(96, 16, 64, 64),
|
|
Fire(128, 16, 64, 64),
|
|
Fire(128, 32, 128, 128),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(256, 32, 128, 128),
|
|
Fire(256, 48, 192, 192),
|
|
Fire(384, 48, 192, 192),
|
|
Fire(384, 64, 256, 256),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(512, 64, 256, 256),
|
|
)
|
|
else:
|
|
self.features = nn.Sequential(
|
|
nn.Conv2d(3, 64, kernel_size=3, stride=2),
|
|
nn.ReLU(inplace=True),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(64, 16, 64, 64),
|
|
Fire(128, 16, 64, 64),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(128, 32, 128, 128),
|
|
Fire(256, 32, 128, 128),
|
|
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
|
|
Fire(256, 48, 192, 192),
|
|
Fire(384, 48, 192, 192),
|
|
Fire(384, 64, 256, 256),
|
|
Fire(512, 64, 256, 256),
|
|
)
|
|
|
|
self.global_avgpool = nn.AdaptiveAvgPool2d(1)
|
|
self.fc = self._construct_fc_layer(fc_dims, 512, dropout_p)
|
|
self.classifier = nn.Linear(self.feature_dim, num_classes)
|
|
|
|
self._init_params()
|
|
|
|
def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
|
|
"""Constructs fully connected layer
|
|
|
|
Args:
|
|
fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed
|
|
input_dim (int): input dimension
|
|
dropout_p (float): dropout probability, if None, dropout is unused
|
|
"""
|
|
if fc_dims is None:
|
|
self.feature_dim = input_dim
|
|
return None
|
|
|
|
assert isinstance(
|
|
fc_dims, (list, tuple)
|
|
), 'fc_dims must be either list or tuple, but got {}'.format(
|
|
type(fc_dims)
|
|
)
|
|
|
|
layers = []
|
|
for dim in fc_dims:
|
|
layers.append(nn.Linear(input_dim, dim))
|
|
layers.append(nn.BatchNorm1d(dim))
|
|
layers.append(nn.ReLU(inplace=True))
|
|
if dropout_p is not None:
|
|
layers.append(nn.Dropout(p=dropout_p))
|
|
input_dim = dim
|
|
|
|
self.feature_dim = fc_dims[-1]
|
|
|
|
return nn.Sequential(*layers)
|
|
|
|
def _init_params(self):
|
|
for m in self.modules():
|
|
if isinstance(m, nn.Conv2d):
|
|
nn.init.kaiming_normal_(
|
|
m.weight, mode='fan_out', nonlinearity='relu'
|
|
)
|
|
if m.bias is not None:
|
|
nn.init.constant_(m.bias, 0)
|
|
elif isinstance(m, nn.BatchNorm2d):
|
|
nn.init.constant_(m.weight, 1)
|
|
nn.init.constant_(m.bias, 0)
|
|
elif isinstance(m, nn.BatchNorm1d):
|
|
nn.init.constant_(m.weight, 1)
|
|
nn.init.constant_(m.bias, 0)
|
|
elif isinstance(m, nn.Linear):
|
|
nn.init.normal_(m.weight, 0, 0.01)
|
|
if m.bias is not None:
|
|
nn.init.constant_(m.bias, 0)
|
|
|
|
def forward(self, x):
|
|
f = self.features(x)
|
|
v = self.global_avgpool(f)
|
|
v = v.view(v.size(0), -1)
|
|
|
|
if self.fc is not None:
|
|
v = self.fc(v)
|
|
|
|
if not self.training:
|
|
return v
|
|
|
|
y = self.classifier(v)
|
|
|
|
if self.loss == 'softmax':
|
|
return y
|
|
elif self.loss == 'triplet':
|
|
return y, v
|
|
else:
|
|
raise KeyError('Unsupported loss: {}'.format(self.loss))
|
|
|
|
|
|
def init_pretrained_weights(model, model_url):
|
|
"""Initializes model with pretrained weights.
|
|
|
|
Layers that don't match with pretrained layers in name or size are kept unchanged.
|
|
"""
|
|
pretrain_dict = model_zoo.load_url(model_url, map_location=None)
|
|
model_dict = model.state_dict()
|
|
pretrain_dict = {
|
|
k: v
|
|
for k, v in pretrain_dict.items()
|
|
if k in model_dict and model_dict[k].size() == v.size()
|
|
}
|
|
model_dict.update(pretrain_dict)
|
|
model.load_state_dict(model_dict)
|
|
|
|
|
|
def squeezenet1_0(num_classes, loss='softmax', pretrained=True, **kwargs):
|
|
model = SqueezeNet(
|
|
num_classes, loss, version=1.0, fc_dims=None, dropout_p=None, **kwargs
|
|
)
|
|
if pretrained:
|
|
init_pretrained_weights(model, model_urls['squeezenet1_0'])
|
|
return model
|
|
|
|
|
|
def squeezenet1_0_fc512(
|
|
num_classes, loss='softmax', pretrained=True, **kwargs
|
|
):
|
|
model = SqueezeNet(
|
|
num_classes,
|
|
loss,
|
|
version=1.0,
|
|
fc_dims=[512],
|
|
dropout_p=None,
|
|
**kwargs
|
|
)
|
|
if pretrained:
|
|
init_pretrained_weights(model, model_urls['squeezenet1_0'])
|
|
return model
|
|
|
|
|
|
def squeezenet1_1(num_classes, loss='softmax', pretrained=True, **kwargs):
|
|
model = SqueezeNet(
|
|
num_classes, loss, version=1.1, fc_dims=None, dropout_p=None, **kwargs
|
|
)
|
|
if pretrained:
|
|
init_pretrained_weights(model, model_urls['squeezenet1_1'])
|
|
return model
|