From f111cb002b9c6065fdf6bb274ce5857a9e875e8c Mon Sep 17 00:00:00 2001
From: chenshijun <csj_sky@126.com>
Date: 星期三, 05 六月 2019 15:38:49 +0800
Subject: [PATCH] face rectangle
---
code/hopenet.py | 198 +++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 165 insertions(+), 33 deletions(-)
diff --git a/code/hopenet.py b/code/hopenet.py
index e6f8f50..c9e0b74 100644
--- a/code/hopenet.py
+++ b/code/hopenet.py
@@ -1,39 +1,171 @@
import torch
import torch.nn as nn
-import torchvision.datasets as dsets
from torch.autograd import Variable
+import math
+import torch.nn.functional as F
-# CNN Model (2 conv layer)
-class Simple_CNN(nn.Module):
- def __init__(self):
- super(Simple_CNN, self).__init__()
- self.layer1 = nn.Sequential(
- nn.Conv2d(3, 64, kernel_size=3, padding=0),
- nn.BatchNorm2d(64),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.layer2 = nn.Sequential(
- nn.Conv2d(64, 128, kernel_size=3, padding=0),
- nn.BatchNorm2d(128),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.layer3 = nn.Sequential(
- nn.Conv2d(128, 256, kernel_size=3, padding=0),
- nn.BatchNorm2d(256),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.layer4 = nn.Sequential(
- nn.Conv2d(256, 512, kernel_size=3, padding=0),
- nn.BatchNorm2d(512),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.fc = nn.Linear(17*17*512, 3)
+class Hopenet(nn.Module):
+ # Hopenet with 3 output layers for yaw, pitch and roll
+ # Predicts Euler angles by binning and regression with the expected value
+ def __init__(self, block, layers, num_bins):
+ self.inplanes = 64
+ super(Hopenet, self).__init__()
+ 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=2)
+ self.avgpool = nn.AvgPool2d(7)
+ self.fc_yaw = nn.Linear(512 * block.expansion, num_bins)
+ self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
+ self.fc_roll = nn.Linear(512 * block.expansion, num_bins)
+
+ # Vestigial layer from previous experiments
+ self.fc_finetune = nn.Linear(512 * block.expansion + 3, 3)
+
+ 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):
- out = self.layer1(x)
- out = self.layer2(out)
- out = self.layer3(out)
- out = self.layer4(out)
- out = out.view(out.size(0), -1)
- out = self.fc(out)
- return out
+ 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)
+ pre_yaw = self.fc_yaw(x)
+ pre_pitch = self.fc_pitch(x)
+ pre_roll = self.fc_roll(x)
+
+ return pre_yaw, pre_pitch, pre_roll
+
+class ResNet(nn.Module):
+ # ResNet for regression of 3 Euler angles.
+ def __init__(self, block, layers, num_classes=1000):
+ self.inplanes = 64
+ super(ResNet, self).__init__()
+ 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=2)
+ self.avgpool = nn.AvgPool2d(7)
+ self.fc_angles = 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_angles(x)
+ return x
+
+class AlexNet(nn.Module):
+ # AlexNet laid out as a Hopenet - classify Euler angles in bins and
+ # regress the expected value.
+ def __init__(self, num_bins):
+ super(AlexNet, self).__init__()
+ self.features = nn.Sequential(
+ nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
+ nn.ReLU(inplace=True),
+ nn.MaxPool2d(kernel_size=3, stride=2),
+ nn.Conv2d(64, 192, kernel_size=5, padding=2),
+ nn.ReLU(inplace=True),
+ nn.MaxPool2d(kernel_size=3, stride=2),
+ nn.Conv2d(192, 384, kernel_size=3, padding=1),
+ nn.ReLU(inplace=True),
+ nn.Conv2d(384, 256, kernel_size=3, padding=1),
+ nn.ReLU(inplace=True),
+ nn.Conv2d(256, 256, kernel_size=3, padding=1),
+ nn.ReLU(inplace=True),
+ nn.MaxPool2d(kernel_size=3, stride=2),
+ )
+ self.classifier = nn.Sequential(
+ nn.Dropout(),
+ nn.Linear(256 * 6 * 6, 4096),
+ nn.ReLU(inplace=True),
+ nn.Dropout(),
+ nn.Linear(4096, 4096),
+ nn.ReLU(inplace=True),
+ )
+ self.fc_yaw = nn.Linear(4096, num_bins)
+ self.fc_pitch = nn.Linear(4096, num_bins)
+ self.fc_roll = nn.Linear(4096, num_bins)
+
+ def forward(self, x):
+ x = self.features(x)
+ x = x.view(x.size(0), 256 * 6 * 6)
+ x = self.classifier(x)
+ yaw = self.fc_yaw(x)
+ pitch = self.fc_pitch(x)
+ roll = self.fc_roll(x)
+ return yaw, pitch, roll
--
Gitblit v1.8.0