ZF/insightface
1
0
Fork 0
mirror of https://github.com/deepinsight/insightface.git synced 2026-05-21 09:07:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

refine repo structure

Browse Source
This commit is contained in:
nttstar
2020-11-06 13:59:21 +08:00
parent 9fc3cc9c0b
commit b774d6a1b7
309 changed files with 24974 additions and 34253 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
recognition/partial_fc/pytorch/backbones/__init__.py
View File

@@ -1 +1 @@
from .iresnet import iresnet34,iresnet50,iresnet100
from .iresnet import iresnet34, iresnet50, iresnet100

128
recognition/partial_fc/pytorch/backbones/iresnet.py
View File

@@ -13,32 +13,59 @@ model_urls = {
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, groups=groups, bias=False, dilation=dilation)
return nn.Conv2d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=dilation,
groups=groups,
bias=False,
dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
return nn.Conv2d(in_planes,
out_planes,
kernel_size=1,
stride=stride,
bias=False)
class IBasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1):
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1):
super(IBasicBlock, self).__init__()
if groups != 1 or base_width != 64:
raise ValueError('BasicBlock only supports groups=1 and base_width=64')
raise ValueError(
'BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
raise NotImplementedError(
"Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.bn1 = nn.BatchNorm2d(inplanes, eps=1e-05, )
self.bn1 = nn.BatchNorm2d(
inplanes,
eps=1e-05,
)
self.conv1 = conv3x3(inplanes, planes)
self.bn2 = nn.BatchNorm2d(planes, eps=1e-05, )
self.bn2 = nn.BatchNorm2d(
planes,
eps=1e-05,
)
self.prelu = nn.PReLU(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn3 = nn.BatchNorm2d(planes, eps=1e-05, )
self.bn3 = nn.BatchNorm2d(
planes,
eps=1e-05,
)
self.downsample = downsample
self.stride = stride
@@ -63,8 +90,14 @@ class IBasicBlock(nn.Module):
class IResNet(nn.Module):
fc_scale = 7 * 7
def __init__(self, block, layers, num_features=512, zero_init_residual=False,
groups=1, width_per_group=64, replace_stride_with_dilation=None):
def __init__(self,
block,
layers,
num_features=512,
zero_init_residual=False,
groups=1,
width_per_group=64,
replace_stride_with_dilation=None):
super(IResNet, self).__init__()
self.inplanes = 64
@@ -75,30 +108,53 @@ class IResNet(nn.Module):
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(replace_stride_with_dilation))
"or a 3-element tuple, got {}".format(
replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1,
self.conv1 = nn.Conv2d(3,
self.inplanes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(self.inplanes, eps=1e-05)
self.prelu = nn.PReLU(self.inplanes)
self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
self.layer2 = self._make_layer(block,
128,
layers[1],
stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
self.layer4 = self._make_layer(block,
512,
layers[3],
stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.bn2 = nn.BatchNorm2d(512 * block.expansion, eps=1e-05, )
self.bn2 = nn.BatchNorm2d(
512 * block.expansion,
eps=1e-05,
)
self.dropout = nn.Dropout(p=0.4, inplace=True)
self.fc = nn.Linear(512 * block.expansion * self.fc_scale, num_features)
self.features = nn.BatchNorm1d(num_features, eps=1e-05, )
self.fc = nn.Linear(512 * block.expansion * self.fc_scale,
num_features)
self.features = nn.BatchNorm1d(
num_features,
eps=1e-05,
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
@@ -117,16 +173,24 @@ class IResNet(nn.Module):
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion, eps=1e-05, ),
nn.BatchNorm2d(
planes * block.expansion,
eps=1e-05,
),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation))
layers.append(
block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, dilation=self.dilation))
layers.append(
block(self.inplanes,
planes,
groups=self.groups,
base_width=self.base_width,
dilation=self.dilation))
return nn.Sequential(*layers)
@@ -159,15 +223,15 @@ def _iresnet(arch, block, layers, pretrained, progress, **kwargs):
def iresnet34(pretrained=False, progress=True, **kwargs):
return _iresnet('iresnet34', IBasicBlock, [3, 4, 6, 3], pretrained, progress,
**kwargs)
return _iresnet('iresnet34', IBasicBlock, [3, 4, 6, 3], pretrained,
progress, **kwargs)
def iresnet50(pretrained=False, progress=True, **kwargs):
return _iresnet('iresnet50', IBasicBlock, [3, 4, 14, 3], pretrained, progress,
**kwargs)
return _iresnet('iresnet50', IBasicBlock, [3, 4, 14, 3], pretrained,
progress, **kwargs)
def iresnet100(pretrained=False, progress=True, **kwargs):
return _iresnet('iresnet100', IBasicBlock, [3, 13, 30, 3], pretrained, progress,
**kwargs)
return _iresnet('iresnet100', IBasicBlock, [3, 13, 30, 3], pretrained,
progress, **kwargs)