Add at new repo again
This commit is contained in:
@@ -0,0 +1,156 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
|
||||
"""
|
||||
@Author : Peike Li
|
||||
@Contact : peike.li@yahoo.com
|
||||
@File : mobilenetv2.py
|
||||
@Time : 8/4/19 3:35 PM
|
||||
@Desc :
|
||||
@License : This source code is licensed under the license found in the
|
||||
LICENSE file in the root directory of this source tree.
|
||||
"""
|
||||
|
||||
import torch.nn as nn
|
||||
import math
|
||||
import functools
|
||||
|
||||
from modules import InPlaceABN, InPlaceABNSync
|
||||
|
||||
BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')
|
||||
|
||||
__all__ = ['mobilenetv2']
|
||||
|
||||
|
||||
def conv_bn(inp, oup, stride):
|
||||
return nn.Sequential(
|
||||
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
|
||||
BatchNorm2d(oup),
|
||||
nn.ReLU6(inplace=True)
|
||||
)
|
||||
|
||||
|
||||
def conv_1x1_bn(inp, oup):
|
||||
return nn.Sequential(
|
||||
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
|
||||
BatchNorm2d(oup),
|
||||
nn.ReLU6(inplace=True)
|
||||
)
|
||||
|
||||
|
||||
class InvertedResidual(nn.Module):
|
||||
def __init__(self, inp, oup, stride, expand_ratio):
|
||||
super(InvertedResidual, self).__init__()
|
||||
self.stride = stride
|
||||
assert stride in [1, 2]
|
||||
|
||||
hidden_dim = round(inp * expand_ratio)
|
||||
self.use_res_connect = self.stride == 1 and inp == oup
|
||||
|
||||
if expand_ratio == 1:
|
||||
self.conv = nn.Sequential(
|
||||
# dw
|
||||
nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
|
||||
BatchNorm2d(hidden_dim),
|
||||
nn.ReLU6(inplace=True),
|
||||
# pw-linear
|
||||
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
|
||||
BatchNorm2d(oup),
|
||||
)
|
||||
else:
|
||||
self.conv = nn.Sequential(
|
||||
# pw
|
||||
nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
|
||||
BatchNorm2d(hidden_dim),
|
||||
nn.ReLU6(inplace=True),
|
||||
# dw
|
||||
nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
|
||||
BatchNorm2d(hidden_dim),
|
||||
nn.ReLU6(inplace=True),
|
||||
# pw-linear
|
||||
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
|
||||
BatchNorm2d(oup),
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
if self.use_res_connect:
|
||||
return x + self.conv(x)
|
||||
else:
|
||||
return self.conv(x)
|
||||
|
||||
|
||||
class MobileNetV2(nn.Module):
|
||||
def __init__(self, n_class=1000, input_size=224, width_mult=1.):
|
||||
super(MobileNetV2, self).__init__()
|
||||
block = InvertedResidual
|
||||
input_channel = 32
|
||||
last_channel = 1280
|
||||
interverted_residual_setting = [
|
||||
# t, c, n, s
|
||||
[1, 16, 1, 1],
|
||||
[6, 24, 2, 2], # layer 2
|
||||
[6, 32, 3, 2], # layer 3
|
||||
[6, 64, 4, 2],
|
||||
[6, 96, 3, 1], # layer 4
|
||||
[6, 160, 3, 2],
|
||||
[6, 320, 1, 1], # layer 5
|
||||
]
|
||||
|
||||
# building first layer
|
||||
assert input_size % 32 == 0
|
||||
input_channel = int(input_channel * width_mult)
|
||||
self.last_channel = int(last_channel * width_mult) if width_mult > 1.0 else last_channel
|
||||
self.features = [conv_bn(3, input_channel, 2)]
|
||||
# building inverted residual blocks
|
||||
for t, c, n, s in interverted_residual_setting:
|
||||
output_channel = int(c * width_mult)
|
||||
for i in range(n):
|
||||
if i == 0:
|
||||
self.features.append(block(input_channel, output_channel, s, expand_ratio=t))
|
||||
else:
|
||||
self.features.append(block(input_channel, output_channel, 1, expand_ratio=t))
|
||||
input_channel = output_channel
|
||||
# building last several layers
|
||||
self.features.append(conv_1x1_bn(input_channel, self.last_channel))
|
||||
# make it nn.Sequential
|
||||
self.features = nn.Sequential(*self.features)
|
||||
|
||||
# building classifier
|
||||
self.classifier = nn.Sequential(
|
||||
nn.Dropout(0.2),
|
||||
nn.Linear(self.last_channel, n_class),
|
||||
)
|
||||
|
||||
self._initialize_weights()
|
||||
|
||||
def forward(self, x):
|
||||
x = self.features(x)
|
||||
x = x.mean(3).mean(2)
|
||||
x = self.classifier(x)
|
||||
return x
|
||||
|
||||
def _initialize_weights(self):
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
m.weight.data.normal_(0, math.sqrt(2. / n))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
elif isinstance(m, BatchNorm2d):
|
||||
m.weight.data.fill_(1)
|
||||
m.bias.data.zero_()
|
||||
elif isinstance(m, nn.Linear):
|
||||
n = m.weight.size(1)
|
||||
m.weight.data.normal_(0, 0.01)
|
||||
m.bias.data.zero_()
|
||||
|
||||
|
||||
def mobilenetv2(pretrained=False, **kwargs):
|
||||
"""Constructs a MobileNet_V2 model.
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = MobileNetV2(n_class=1000, **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(load_url(model_urls['mobilenetv2']), strict=False)
|
||||
return model
|
||||
205
vton-api/preprocess/humanparsing/networks/backbone/resnet.py
Normal file
205
vton-api/preprocess/humanparsing/networks/backbone/resnet.py
Normal file
@@ -0,0 +1,205 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
|
||||
"""
|
||||
@Author : Peike Li
|
||||
@Contact : peike.li@yahoo.com
|
||||
@File : resnet.py
|
||||
@Time : 8/4/19 3:35 PM
|
||||
@Desc :
|
||||
@License : This source code is licensed under the license found in the
|
||||
LICENSE file in the root directory of this source tree.
|
||||
"""
|
||||
|
||||
import functools
|
||||
import torch.nn as nn
|
||||
import math
|
||||
from torch.utils.model_zoo import load_url
|
||||
|
||||
from modules import InPlaceABNSync
|
||||
|
||||
BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')
|
||||
|
||||
__all__ = ['ResNet', 'resnet18', 'resnet50', 'resnet101'] # resnet101 is coming soon!
|
||||
|
||||
model_urls = {
|
||||
'resnet18': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnet18-imagenet.pth',
|
||||
'resnet50': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnet50-imagenet.pth',
|
||||
'resnet101': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnet101-imagenet.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 = BatchNorm2d(planes)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.conv2 = conv3x3(planes, planes)
|
||||
self.bn2 = 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 = BatchNorm2d(planes)
|
||||
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
|
||||
padding=1, bias=False)
|
||||
self.bn2 = BatchNorm2d(planes)
|
||||
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
|
||||
self.bn3 = BatchNorm2d(planes * 4)
|
||||
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 ResNet(nn.Module):
|
||||
|
||||
def __init__(self, block, layers, num_classes=1000):
|
||||
self.inplanes = 128
|
||||
super(ResNet, self).__init__()
|
||||
self.conv1 = conv3x3(3, 64, stride=2)
|
||||
self.bn1 = BatchNorm2d(64)
|
||||
self.relu1 = nn.ReLU(inplace=True)
|
||||
self.conv2 = conv3x3(64, 64)
|
||||
self.bn2 = BatchNorm2d(64)
|
||||
self.relu2 = nn.ReLU(inplace=True)
|
||||
self.conv3 = conv3x3(64, 128)
|
||||
self.bn3 = BatchNorm2d(128)
|
||||
self.relu3 = 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=2)
|
||||
self.avgpool = nn.AvgPool2d(7, stride=1)
|
||||
self.fc = nn.Linear(512 * block.expansion, num_classes)
|
||||
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
m.weight.data.normal_(0, math.sqrt(2. / n))
|
||||
elif isinstance(m, BatchNorm2d):
|
||||
m.weight.data.fill_(1)
|
||||
m.bias.data.zero_()
|
||||
|
||||
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),
|
||||
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 forward(self, x):
|
||||
x = self.relu1(self.bn1(self.conv1(x)))
|
||||
x = self.relu2(self.bn2(self.conv2(x)))
|
||||
x = self.relu3(self.bn3(self.conv3(x)))
|
||||
x = self.maxpool(x)
|
||||
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
|
||||
x = self.avgpool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
x = self.fc(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def resnet18(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-18 model.
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(load_url(model_urls['resnet18']))
|
||||
return model
|
||||
|
||||
|
||||
def resnet50(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-50 model.
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(load_url(model_urls['resnet50']), strict=False)
|
||||
return model
|
||||
|
||||
|
||||
def resnet101(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-101 model.
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(load_url(model_urls['resnet101']), strict=False)
|
||||
return model
|
||||
149
vton-api/preprocess/humanparsing/networks/backbone/resnext.py
Normal file
149
vton-api/preprocess/humanparsing/networks/backbone/resnext.py
Normal file
@@ -0,0 +1,149 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
|
||||
"""
|
||||
@Author : Peike Li
|
||||
@Contact : peike.li@yahoo.com
|
||||
@File : resnext.py.py
|
||||
@Time : 8/11/19 8:58 PM
|
||||
@Desc :
|
||||
@License : This source code is licensed under the license found in the
|
||||
LICENSE file in the root directory of this source tree.
|
||||
"""
|
||||
import functools
|
||||
import torch.nn as nn
|
||||
import math
|
||||
from torch.utils.model_zoo import load_url
|
||||
|
||||
from modules import InPlaceABNSync
|
||||
|
||||
BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')
|
||||
|
||||
__all__ = ['ResNeXt', 'resnext101'] # support resnext 101
|
||||
|
||||
model_urls = {
|
||||
'resnext50': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnext50-imagenet.pth',
|
||||
'resnext101': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnext101-imagenet.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 GroupBottleneck(nn.Module):
|
||||
expansion = 2
|
||||
|
||||
def __init__(self, inplanes, planes, stride=1, groups=1, downsample=None):
|
||||
super(GroupBottleneck, self).__init__()
|
||||
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
|
||||
self.bn1 = BatchNorm2d(planes)
|
||||
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
|
||||
padding=1, groups=groups, bias=False)
|
||||
self.bn2 = BatchNorm2d(planes)
|
||||
self.conv3 = nn.Conv2d(planes, planes * 2, kernel_size=1, bias=False)
|
||||
self.bn3 = BatchNorm2d(planes * 2)
|
||||
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 ResNeXt(nn.Module):
|
||||
|
||||
def __init__(self, block, layers, groups=32, num_classes=1000):
|
||||
self.inplanes = 128
|
||||
super(ResNeXt, self).__init__()
|
||||
self.conv1 = conv3x3(3, 64, stride=2)
|
||||
self.bn1 = BatchNorm2d(64)
|
||||
self.relu1 = nn.ReLU(inplace=True)
|
||||
self.conv2 = conv3x3(64, 64)
|
||||
self.bn2 = BatchNorm2d(64)
|
||||
self.relu2 = nn.ReLU(inplace=True)
|
||||
self.conv3 = conv3x3(64, 128)
|
||||
self.bn3 = BatchNorm2d(128)
|
||||
self.relu3 = nn.ReLU(inplace=True)
|
||||
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
|
||||
|
||||
self.layer1 = self._make_layer(block, 128, layers[0], groups=groups)
|
||||
self.layer2 = self._make_layer(block, 256, layers[1], stride=2, groups=groups)
|
||||
self.layer3 = self._make_layer(block, 512, layers[2], stride=2, groups=groups)
|
||||
self.layer4 = self._make_layer(block, 1024, layers[3], stride=2, groups=groups)
|
||||
self.avgpool = nn.AvgPool2d(7, stride=1)
|
||||
self.fc = nn.Linear(1024 * block.expansion, num_classes)
|
||||
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels // m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2. / n))
|
||||
elif isinstance(m, BatchNorm2d):
|
||||
m.weight.data.fill_(1)
|
||||
m.bias.data.zero_()
|
||||
|
||||
def _make_layer(self, block, planes, blocks, stride=1, groups=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),
|
||||
BatchNorm2d(planes * block.expansion),
|
||||
)
|
||||
|
||||
layers = []
|
||||
layers.append(block(self.inplanes, planes, stride, groups, downsample))
|
||||
self.inplanes = planes * block.expansion
|
||||
for i in range(1, blocks):
|
||||
layers.append(block(self.inplanes, planes, groups=groups))
|
||||
|
||||
return nn.Sequential(*layers)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.relu1(self.bn1(self.conv1(x)))
|
||||
x = self.relu2(self.bn2(self.conv2(x)))
|
||||
x = self.relu3(self.bn3(self.conv3(x)))
|
||||
x = self.maxpool(x)
|
||||
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
|
||||
x = self.avgpool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
x = self.fc(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def resnext101(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-101 model.
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on Places
|
||||
"""
|
||||
model = ResNeXt(GroupBottleneck, [3, 4, 23, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(load_url(model_urls['resnext101']), strict=False)
|
||||
return model
|
||||
Reference in New Issue
Block a user