"""
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
)
[docs]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