Algorithm/deepHeadPose.git

			@@ -1,46 +1,12 @@
			import torch
			import torch.nn as nn
			import torchvision.datasets as dsets
			from torch.autograd import Variable
			import math

			# 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(1717512, 3)

			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
			import torch.nn.functional as F

			class Hopenet(nn.Module):
			# This is just Hopenet with 3 output layers for yaw, pitch and roll.
			# 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__()
			@@ -57,6 +23,9 @@
			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):
			@@ -96,8 +65,107 @@

			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