Spaces:
Runtime error
Runtime error
from __future__ import division, absolute_import | |
import torch.utils.model_zoo as model_zoo | |
from torch import nn | |
from torch.nn import functional as F | |
__all__ = ['pcb_p6', 'pcb_p4'] | |
model_urls = { | |
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth', | |
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth', | |
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth', | |
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth', | |
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth', | |
} | |
def conv3x3(in_planes, out_planes, stride=1): | |
"""3x3 convolution with padding""" | |
return nn.Conv2d( | |
in_planes, | |
out_planes, | |
kernel_size=3, | |
stride=stride, | |
padding=1, | |
bias=False | |
) | |
class BasicBlock(nn.Module): | |
expansion = 1 | |
def __init__(self, inplanes, planes, stride=1, downsample=None): | |
super(BasicBlock, self).__init__() | |
self.conv1 = conv3x3(inplanes, planes, stride) | |
self.bn1 = nn.BatchNorm2d(planes) | |
self.relu = nn.ReLU(inplace=True) | |
self.conv2 = conv3x3(planes, planes) | |
self.bn2 = nn.BatchNorm2d(planes) | |
self.downsample = downsample | |
self.stride = stride | |
def forward(self, x): | |
residual = x | |
out = self.conv1(x) | |
out = self.bn1(out) | |
out = self.relu(out) | |
out = self.conv2(out) | |
out = self.bn2(out) | |
if self.downsample is not None: | |
residual = self.downsample(x) | |
out += residual | |
out = self.relu(out) | |
return out | |
class Bottleneck(nn.Module): | |
expansion = 4 | |
def __init__(self, inplanes, planes, stride=1, downsample=None): | |
super(Bottleneck, self).__init__() | |
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) | |
self.bn1 = nn.BatchNorm2d(planes) | |
self.conv2 = nn.Conv2d( | |
planes, | |
planes, | |
kernel_size=3, | |
stride=stride, | |
padding=1, | |
bias=False | |
) | |
self.bn2 = nn.BatchNorm2d(planes) | |
self.conv3 = nn.Conv2d( | |
planes, planes * self.expansion, kernel_size=1, bias=False | |
) | |
self.bn3 = nn.BatchNorm2d(planes * self.expansion) | |
self.relu = nn.ReLU(inplace=True) | |
self.downsample = downsample | |
self.stride = stride | |
def forward(self, x): | |
residual = x | |
out = self.conv1(x) | |
out = self.bn1(out) | |
out = self.relu(out) | |
out = self.conv2(out) | |
out = self.bn2(out) | |
out = self.relu(out) | |
out = self.conv3(out) | |
out = self.bn3(out) | |
if self.downsample is not None: | |
residual = self.downsample(x) | |
out += residual | |
out = self.relu(out) | |
return out | |
class DimReduceLayer(nn.Module): | |
def __init__(self, in_channels, out_channels, nonlinear): | |
super(DimReduceLayer, self).__init__() | |
layers = [] | |
layers.append( | |
nn.Conv2d( | |
in_channels, out_channels, 1, stride=1, padding=0, bias=False | |
) | |
) | |
layers.append(nn.BatchNorm2d(out_channels)) | |
if nonlinear == 'relu': | |
layers.append(nn.ReLU(inplace=True)) | |
elif nonlinear == 'leakyrelu': | |
layers.append(nn.LeakyReLU(0.1)) | |
self.layers = nn.Sequential(*layers) | |
def forward(self, x): | |
return self.layers(x) | |
class PCB(nn.Module): | |
"""Part-based Convolutional Baseline. | |
Reference: | |
Sun et al. Beyond Part Models: Person Retrieval with Refined | |
Part Pooling (and A Strong Convolutional Baseline). ECCV 2018. | |
Public keys: | |
- ``pcb_p4``: PCB with 4-part strips. | |
- ``pcb_p6``: PCB with 6-part strips. | |
""" | |
def __init__( | |
self, | |
num_classes, | |
loss, | |
block, | |
layers, | |
parts=6, | |
reduced_dim=256, | |
nonlinear='relu', | |
**kwargs | |
): | |
self.inplanes = 64 | |
super(PCB, self).__init__() | |
self.loss = loss | |
self.parts = parts | |
self.feature_dim = 512 * block.expansion | |
# backbone network | |
self.conv1 = nn.Conv2d( | |
3, 64, kernel_size=7, stride=2, padding=3, bias=False | |
) | |
self.bn1 = nn.BatchNorm2d(64) | |
self.relu = nn.ReLU(inplace=True) | |
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) | |
self.layer1 = self._make_layer(block, 64, layers[0]) | |
self.layer2 = self._make_layer(block, 128, layers[1], stride=2) | |
self.layer3 = self._make_layer(block, 256, layers[2], stride=2) | |
self.layer4 = self._make_layer(block, 512, layers[3], stride=1) | |
# pcb layers | |
self.parts_avgpool = nn.AdaptiveAvgPool2d((self.parts, 1)) | |
self.dropout = nn.Dropout(p=0.5) | |
self.conv5 = DimReduceLayer( | |
512 * block.expansion, reduced_dim, nonlinear=nonlinear | |
) | |
self.feature_dim = reduced_dim | |
self.classifier = nn.ModuleList( | |
[ | |
nn.Linear(self.feature_dim, num_classes) | |
for _ in range(self.parts) | |
] | |
) | |
self._init_params() | |
def _make_layer(self, block, planes, blocks, stride=1): | |
downsample = None | |
if stride != 1 or self.inplanes != planes * block.expansion: | |
downsample = nn.Sequential( | |
nn.Conv2d( | |
self.inplanes, | |
planes * block.expansion, | |
kernel_size=1, | |
stride=stride, | |
bias=False | |
), | |
nn.BatchNorm2d(planes * block.expansion), | |
) | |
layers = [] | |
layers.append(block(self.inplanes, planes, stride, downsample)) | |
self.inplanes = planes * block.expansion | |
for i in range(1, blocks): | |
layers.append(block(self.inplanes, planes)) | |
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 featuremaps(self, x): | |
x = self.conv1(x) | |
x = self.bn1(x) | |
x = self.relu(x) | |
x = self.maxpool(x) | |
x = self.layer1(x) | |
x = self.layer2(x) | |
x = self.layer3(x) | |
x = self.layer4(x) | |
return x | |
def forward(self, x): | |
f = self.featuremaps(x) | |
v_g = self.parts_avgpool(f) | |
if not self.training: | |
v_g = F.normalize(v_g, p=2, dim=1) | |
return v_g.view(v_g.size(0), -1) | |
v_g = self.dropout(v_g) | |
v_h = self.conv5(v_g) | |
y = [] | |
for i in range(self.parts): | |
v_h_i = v_h[:, :, i, :] | |
v_h_i = v_h_i.view(v_h_i.size(0), -1) | |
y_i = self.classifier[i](v_h_i) | |
y.append(y_i) | |
if self.loss == 'softmax': | |
return y | |
elif self.loss == 'triplet': | |
v_g = F.normalize(v_g, p=2, dim=1) | |
return y, v_g.view(v_g.size(0), -1) | |
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) | |
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 pcb_p6(num_classes, loss='softmax', pretrained=True, **kwargs): | |
model = PCB( | |
num_classes=num_classes, | |
loss=loss, | |
block=Bottleneck, | |
layers=[3, 4, 6, 3], | |
last_stride=1, | |
parts=6, | |
reduced_dim=256, | |
nonlinear='relu', | |
**kwargs | |
) | |
if pretrained: | |
init_pretrained_weights(model, model_urls['resnet50']) | |
return model | |
def pcb_p4(num_classes, loss='softmax', pretrained=True, **kwargs): | |
model = PCB( | |
num_classes=num_classes, | |
loss=loss, | |
block=Bottleneck, | |
layers=[3, 4, 6, 3], | |
last_stride=1, | |
parts=4, | |
reduced_dim=256, | |
nonlinear='relu', | |
**kwargs | |
) | |
if pretrained: | |
init_pretrained_weights(model, model_urls['resnet50']) | |
return model | |