restructure model structure
Esse commit está contido em:
Adrian Bulat
+1
-1
@@ -1,4 +1,4 @@
|
||||
# Based on https://github.com/pytorch/pytorch/blob/master/Dockerfile
|
||||
# Based on a older version of https://github.com/pytorch/pytorch/blob/master/Dockerfile
|
||||
FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
|
||||
+3
-41
@@ -85,7 +85,7 @@ Please also see the ``examples`` folder
|
||||
|
||||
### Requirements
|
||||
|
||||
* Python 3.5+ or Python 2.7 (it may work with other versions too). Support for Python 2.7 is deprecated.
|
||||
* Python 3.5+ (it may work with other versions too).
|
||||
* Linux, Windows or macOS
|
||||
* pytorch (>=1.0)
|
||||
|
||||
@@ -104,39 +104,7 @@ Alternatively, bellow, you can find instruction to build it from source.
|
||||
|
||||
### From source
|
||||
|
||||
Install pytorch and pytorch dependencies. Instructions taken from [pytorch readme](https://github.com/pytorch/pytorch). For a more updated version check the framework github page.
|
||||
|
||||
On Linux
|
||||
```bash
|
||||
export CMAKE_PREFIX_PATH="$(dirname $(which conda))/../" # [anaconda root directory]
|
||||
|
||||
# Install basic dependencies
|
||||
conda install numpy pyyaml mkl setuptools cmake gcc cffi
|
||||
|
||||
# Add LAPACK support for the GPU
|
||||
conda install -c soumith magma-cuda80 # or magma-cuda75 if CUDA 7.5
|
||||
```
|
||||
|
||||
On OSX
|
||||
```bash
|
||||
export CMAKE_PREFIX_PATH=[anaconda root directory]
|
||||
conda install numpy pyyaml setuptools cmake cffi
|
||||
```
|
||||
#### Get the PyTorch source
|
||||
```bash
|
||||
git clone --recursive https://github.com/pytorch/pytorch
|
||||
```
|
||||
|
||||
#### Install PyTorch
|
||||
On Linux
|
||||
```bash
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
On OSX
|
||||
```bash
|
||||
MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py install
|
||||
```
|
||||
Install pytorch and pytorch dependencies. Please check the [pytorch readme](https://github.com/pytorch/pytorch) for this.
|
||||
|
||||
#### Get the Face Alignment source code
|
||||
```bash
|
||||
@@ -150,7 +118,7 @@ python setup.py install
|
||||
|
||||
### Docker image
|
||||
|
||||
A Dockerfile is provided to build images with cuda support and cudnn v5. For more instructions about running and building a docker image check the orginal Docker documentation.
|
||||
A Dockerfile is provided to build images with cuda support and cudnn. For more instructions about running and building a docker image check the orginal Docker documentation.
|
||||
```
|
||||
docker build -t face-alignment .
|
||||
```
|
||||
@@ -175,9 +143,3 @@ All contributions are welcomed. If you encounter any issue (including examples o
|
||||
```
|
||||
|
||||
For citing dlib, pytorch or any other packages used here please check the original page of their respective authors.
|
||||
|
||||
## Acknowledgements
|
||||
|
||||
* To the [pytorch](http://pytorch.org/) team for providing such an awesome deeplearning framework
|
||||
* To [my supervisor](http://www.cs.nott.ac.uk/~pszyt/) for his patience and suggestions.
|
||||
* To all other python developers that made available the rest of the packages used in this repository.
|
||||
|
||||
@@ -1,15 +1,9 @@
|
||||
import os
|
||||
import torch
|
||||
from torch.utils.model_zoo import load_url
|
||||
from enum import Enum
|
||||
from skimage import io
|
||||
from skimage import color
|
||||
import numpy as np
|
||||
import cv2
|
||||
try:
|
||||
import urllib.request as request_file
|
||||
except BaseException:
|
||||
import urllib as request_file
|
||||
|
||||
from .models import FAN, ResNetDepth
|
||||
from .utils import *
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
from .fan import FAN
|
||||
from .resnet import ResNetDepth
|
||||
@@ -1,261 +1,160 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import math
|
||||
|
||||
|
||||
def conv3x3(in_planes, out_planes, strd=1, padding=1, bias=False):
|
||||
"3x3 convolution with padding"
|
||||
return nn.Conv2d(in_planes, out_planes, kernel_size=3,
|
||||
stride=strd, padding=padding, bias=bias)
|
||||
|
||||
|
||||
class ConvBlock(nn.Module):
|
||||
def __init__(self, in_planes, out_planes):
|
||||
super(ConvBlock, self).__init__()
|
||||
self.bn1 = nn.BatchNorm2d(in_planes)
|
||||
self.conv1 = conv3x3(in_planes, int(out_planes / 2))
|
||||
self.bn2 = nn.BatchNorm2d(int(out_planes / 2))
|
||||
self.conv2 = conv3x3(int(out_planes / 2), int(out_planes / 4))
|
||||
self.bn3 = nn.BatchNorm2d(int(out_planes / 4))
|
||||
self.conv3 = conv3x3(int(out_planes / 4), int(out_planes / 4))
|
||||
|
||||
if in_planes != out_planes:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.BatchNorm2d(in_planes),
|
||||
nn.ReLU(True),
|
||||
nn.Conv2d(in_planes, out_planes,
|
||||
kernel_size=1, stride=1, bias=False),
|
||||
)
|
||||
else:
|
||||
self.downsample = None
|
||||
|
||||
def forward(self, x):
|
||||
residual = x
|
||||
|
||||
out1 = self.bn1(x)
|
||||
out1 = F.relu(out1, True)
|
||||
out1 = self.conv1(out1)
|
||||
|
||||
out2 = self.bn2(out1)
|
||||
out2 = F.relu(out2, True)
|
||||
out2 = self.conv2(out2)
|
||||
|
||||
out3 = self.bn3(out2)
|
||||
out3 = F.relu(out3, True)
|
||||
out3 = self.conv3(out3)
|
||||
|
||||
out3 = torch.cat((out1, out2, out3), 1)
|
||||
|
||||
if self.downsample is not None:
|
||||
residual = self.downsample(residual)
|
||||
|
||||
out3 += residual
|
||||
|
||||
return out3
|
||||
|
||||
|
||||
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 * 4, kernel_size=1, bias=False)
|
||||
self.bn3 = nn.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 HourGlass(nn.Module):
|
||||
def __init__(self, num_modules, depth, num_features):
|
||||
super(HourGlass, self).__init__()
|
||||
self.num_modules = num_modules
|
||||
self.depth = depth
|
||||
self.features = num_features
|
||||
|
||||
self._generate_network(self.depth)
|
||||
|
||||
def _generate_network(self, level):
|
||||
self.add_module('b1_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
self.add_module('b2_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
if level > 1:
|
||||
self._generate_network(level - 1)
|
||||
else:
|
||||
self.add_module('b2_plus_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
self.add_module('b3_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
def _forward(self, level, inp):
|
||||
# Upper branch
|
||||
up1 = inp
|
||||
up1 = self._modules['b1_' + str(level)](up1)
|
||||
|
||||
# Lower branch
|
||||
low1 = F.avg_pool2d(inp, 2, stride=2)
|
||||
low1 = self._modules['b2_' + str(level)](low1)
|
||||
|
||||
if level > 1:
|
||||
low2 = self._forward(level - 1, low1)
|
||||
else:
|
||||
low2 = low1
|
||||
low2 = self._modules['b2_plus_' + str(level)](low2)
|
||||
|
||||
low3 = low2
|
||||
low3 = self._modules['b3_' + str(level)](low3)
|
||||
|
||||
up2 = F.interpolate(low3, scale_factor=2, mode='nearest')
|
||||
|
||||
return up1 + up2
|
||||
|
||||
def forward(self, x):
|
||||
return self._forward(self.depth, x)
|
||||
|
||||
|
||||
class FAN(nn.Module):
|
||||
|
||||
def __init__(self, num_modules=1):
|
||||
super(FAN, self).__init__()
|
||||
self.num_modules = num_modules
|
||||
|
||||
# Base part
|
||||
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
|
||||
self.bn1 = nn.BatchNorm2d(64)
|
||||
self.conv2 = ConvBlock(64, 128)
|
||||
self.conv3 = ConvBlock(128, 128)
|
||||
self.conv4 = ConvBlock(128, 256)
|
||||
|
||||
# Stacking part
|
||||
for hg_module in range(self.num_modules):
|
||||
self.add_module('m' + str(hg_module), HourGlass(1, 4, 256))
|
||||
self.add_module('top_m_' + str(hg_module), ConvBlock(256, 256))
|
||||
self.add_module('conv_last' + str(hg_module),
|
||||
nn.Conv2d(256, 256, kernel_size=1, stride=1, padding=0))
|
||||
self.add_module('bn_end' + str(hg_module), nn.BatchNorm2d(256))
|
||||
self.add_module('l' + str(hg_module), nn.Conv2d(256,
|
||||
68, kernel_size=1, stride=1, padding=0))
|
||||
|
||||
if hg_module < self.num_modules - 1:
|
||||
self.add_module(
|
||||
'bl' + str(hg_module), nn.Conv2d(256, 256, kernel_size=1, stride=1, padding=0))
|
||||
self.add_module('al' + str(hg_module), nn.Conv2d(68,
|
||||
256, kernel_size=1, stride=1, padding=0))
|
||||
|
||||
def forward(self, x):
|
||||
x = F.relu(self.bn1(self.conv1(x)), True)
|
||||
x = F.avg_pool2d(self.conv2(x), 2, stride=2)
|
||||
x = self.conv3(x)
|
||||
x = self.conv4(x)
|
||||
|
||||
previous = x
|
||||
|
||||
outputs = []
|
||||
for i in range(self.num_modules):
|
||||
hg = self._modules['m' + str(i)](previous)
|
||||
|
||||
ll = hg
|
||||
ll = self._modules['top_m_' + str(i)](ll)
|
||||
|
||||
ll = F.relu(self._modules['bn_end' + str(i)]
|
||||
(self._modules['conv_last' + str(i)](ll)), True)
|
||||
|
||||
# Predict heatmaps
|
||||
tmp_out = self._modules['l' + str(i)](ll)
|
||||
outputs.append(tmp_out)
|
||||
|
||||
if i < self.num_modules - 1:
|
||||
ll = self._modules['bl' + str(i)](ll)
|
||||
tmp_out_ = self._modules['al' + str(i)](tmp_out)
|
||||
previous = previous + ll + tmp_out_
|
||||
|
||||
return outputs
|
||||
|
||||
|
||||
class ResNetDepth(nn.Module):
|
||||
|
||||
def __init__(self, block=Bottleneck, layers=[3, 8, 36, 3], num_classes=68):
|
||||
self.inplanes = 64
|
||||
super(ResNetDepth, self).__init__()
|
||||
self.conv1 = nn.Conv2d(3 + 68, 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=2)
|
||||
self.avgpool = nn.AvgPool2d(7)
|
||||
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, nn.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),
|
||||
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 forward(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)
|
||||
|
||||
x = self.avgpool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
x = self.fc(x)
|
||||
|
||||
return x
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import math
|
||||
|
||||
def conv3x3(in_planes, out_planes, strd=1, padding=1, bias=False):
|
||||
"3x3 convolution with padding"
|
||||
return nn.Conv2d(in_planes, out_planes, kernel_size=3,
|
||||
stride=strd, padding=padding, bias=bias)
|
||||
|
||||
|
||||
class ConvBlock(nn.Module):
|
||||
def __init__(self, in_planes, out_planes):
|
||||
super(ConvBlock, self).__init__()
|
||||
self.bn1 = nn.BatchNorm2d(in_planes)
|
||||
self.conv1 = conv3x3(in_planes, int(out_planes / 2))
|
||||
self.bn2 = nn.BatchNorm2d(int(out_planes / 2))
|
||||
self.conv2 = conv3x3(int(out_planes / 2), int(out_planes / 4))
|
||||
self.bn3 = nn.BatchNorm2d(int(out_planes / 4))
|
||||
self.conv3 = conv3x3(int(out_planes / 4), int(out_planes / 4))
|
||||
|
||||
if in_planes != out_planes:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.BatchNorm2d(in_planes),
|
||||
nn.ReLU(True),
|
||||
nn.Conv2d(in_planes, out_planes,
|
||||
kernel_size=1, stride=1, bias=False),
|
||||
)
|
||||
else:
|
||||
self.downsample = None
|
||||
|
||||
def forward(self, x):
|
||||
residual = x
|
||||
|
||||
out1 = self.bn1(x)
|
||||
out1 = F.relu(out1, True)
|
||||
out1 = self.conv1(out1)
|
||||
|
||||
out2 = self.bn2(out1)
|
||||
out2 = F.relu(out2, True)
|
||||
out2 = self.conv2(out2)
|
||||
|
||||
out3 = self.bn3(out2)
|
||||
out3 = F.relu(out3, True)
|
||||
out3 = self.conv3(out3)
|
||||
|
||||
out3 = torch.cat((out1, out2, out3), 1)
|
||||
|
||||
if self.downsample is not None:
|
||||
residual = self.downsample(residual)
|
||||
|
||||
out3 += residual
|
||||
|
||||
return out3
|
||||
|
||||
|
||||
class HourGlass(nn.Module):
|
||||
def __init__(self, num_modules, depth, num_features):
|
||||
super(HourGlass, self).__init__()
|
||||
self.num_modules = num_modules
|
||||
self.depth = depth
|
||||
self.features = num_features
|
||||
|
||||
self._generate_network(self.depth)
|
||||
|
||||
def _generate_network(self, level):
|
||||
self.add_module('b1_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
self.add_module('b2_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
if level > 1:
|
||||
self._generate_network(level - 1)
|
||||
else:
|
||||
self.add_module('b2_plus_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
self.add_module('b3_' + str(level), ConvBlock(self.features, self.features))
|
||||
|
||||
def _forward(self, level, inp):
|
||||
# Upper branch
|
||||
up1 = inp
|
||||
up1 = self._modules['b1_' + str(level)](up1)
|
||||
|
||||
# Lower branch
|
||||
low1 = F.avg_pool2d(inp, 2, stride=2)
|
||||
low1 = self._modules['b2_' + str(level)](low1)
|
||||
|
||||
if level > 1:
|
||||
low2 = self._forward(level - 1, low1)
|
||||
else:
|
||||
low2 = low1
|
||||
low2 = self._modules['b2_plus_' + str(level)](low2)
|
||||
|
||||
low3 = low2
|
||||
low3 = self._modules['b3_' + str(level)](low3)
|
||||
|
||||
up2 = F.interpolate(low3, scale_factor=2, mode='nearest')
|
||||
|
||||
return up1 + up2
|
||||
|
||||
def forward(self, x):
|
||||
return self._forward(self.depth, x)
|
||||
|
||||
|
||||
class FAN(nn.Module):
|
||||
|
||||
def __init__(self, num_modules=1):
|
||||
super(FAN, self).__init__()
|
||||
self.num_modules = num_modules
|
||||
|
||||
# Base part
|
||||
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
|
||||
self.bn1 = nn.BatchNorm2d(64)
|
||||
self.conv2 = ConvBlock(64, 128)
|
||||
self.conv3 = ConvBlock(128, 128)
|
||||
self.conv4 = ConvBlock(128, 256)
|
||||
|
||||
# Stacking part
|
||||
for hg_module in range(self.num_modules):
|
||||
self.add_module('m' + str(hg_module), HourGlass(1, 4, 256))
|
||||
self.add_module('top_m_' + str(hg_module), ConvBlock(256, 256))
|
||||
self.add_module('conv_last' + str(hg_module),
|
||||
nn.Conv2d(256, 256, kernel_size=1, stride=1, padding=0))
|
||||
self.add_module('bn_end' + str(hg_module), nn.BatchNorm2d(256))
|
||||
self.add_module('l' + str(hg_module), nn.Conv2d(256,
|
||||
68, kernel_size=1, stride=1, padding=0))
|
||||
|
||||
if hg_module < self.num_modules - 1:
|
||||
self.add_module(
|
||||
'bl' + str(hg_module), nn.Conv2d(256, 256, kernel_size=1, stride=1, padding=0))
|
||||
self.add_module('al' + str(hg_module), nn.Conv2d(68,
|
||||
256, kernel_size=1, stride=1, padding=0))
|
||||
|
||||
def forward(self, x):
|
||||
x = F.relu(self.bn1(self.conv1(x)), True)
|
||||
x = F.avg_pool2d(self.conv2(x), 2, stride=2)
|
||||
x = self.conv3(x)
|
||||
x = self.conv4(x)
|
||||
|
||||
previous = x
|
||||
|
||||
outputs = []
|
||||
for i in range(self.num_modules):
|
||||
hg = self._modules['m' + str(i)](previous)
|
||||
|
||||
ll = hg
|
||||
ll = self._modules['top_m_' + str(i)](ll)
|
||||
|
||||
ll = F.relu(self._modules['bn_end' + str(i)]
|
||||
(self._modules['conv_last' + str(i)](ll)), True)
|
||||
|
||||
# Predict heatmaps
|
||||
tmp_out = self._modules['l' + str(i)](ll)
|
||||
outputs.append(tmp_out)
|
||||
|
||||
if i < self.num_modules - 1:
|
||||
ll = self._modules['bl' + str(i)](ll)
|
||||
tmp_out_ = self._modules['al' + str(i)](tmp_out)
|
||||
previous = previous + ll + tmp_out_
|
||||
|
||||
return outputs
|
||||
@@ -0,0 +1,100 @@
|
||||
import math
|
||||
import torch.nn as nn
|
||||
|
||||
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 * 4, kernel_size=1, bias=False)
|
||||
self.bn3 = nn.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 ResNetDepth(nn.Module):
|
||||
|
||||
def __init__(self, block=Bottleneck, layers=[3, 8, 36, 3], num_classes=68):
|
||||
self.inplanes = 64
|
||||
super(ResNetDepth, self).__init__()
|
||||
self.conv1 = nn.Conv2d(3 + 68, 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=2)
|
||||
self.avgpool = nn.AvgPool2d(7)
|
||||
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, nn.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),
|
||||
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 forward(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)
|
||||
|
||||
x = self.avgpool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
x = self.fc(x)
|
||||
|
||||
return x
|
||||
@@ -249,7 +249,7 @@ def flip(tensor, is_label=False):
|
||||
|
||||
|
||||
# Pytorch load supports only pytorch models
|
||||
def load_file_from_url(url, model_dir=None, map_location=None, progress=True, check_hash=False, file_name=None):
|
||||
def load_file_from_url(url, model_dir=None, progress=True, check_hash=False, file_name=None):
|
||||
if model_dir is None:
|
||||
hub_dir = get_dir()
|
||||
model_dir = os.path.join(hub_dir, 'checkpoints')
|
||||
|
||||
Referência em uma Nova Issue
Bloquear um usuário