Algorithm/deepHeadPose.git

			@@ -4,44 +4,10 @@
			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(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

			class Hopenet(nn.Module):
			# This is just Hopenet with 3 output layers for yaw, pitch and roll.
			def __init__(self, block, layers, num_bins, iter_ref):
			# 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,
			@@ -58,12 +24,8 @@
			self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
			self.fc_roll = nn.Linear(512 * block.expansion, num_bins)

			self.softmax = nn.Softmax()
			# Vestigial layer from previous experiments
			self.fc_finetune = nn.Linear(512 * block.expansion + 3, 3)

			self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda()

			self.iter_ref = iter_ref

			for m in self.modules():
			if isinstance(m, nn.Conv2d):
			@@ -107,30 +69,13 @@
			pre_pitch = self.fc_pitch(x)
			pre_roll = self.fc_roll(x)

			yaw = self.softmax(pre_yaw)
			yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True)
			pitch = self.softmax(pre_pitch)
			pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True)
			roll = self.softmax(pre_roll)
			roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True)
			yaw = yaw.view(yaw.size(0), 1)
			pitch = pitch.view(pitch.size(0), 1)
			roll = roll.view(roll.size(0), 1)
			angles = []
			preangles = torch.cat([yaw, pitch, roll], 1)
			angles.append(preangles)
			return pre_yaw, pre_pitch, pre_roll

			# angles predicts the residual
			for idx in xrange(self.iter_ref):
			angles.append(self.fc_finetune(torch.cat((preangles, x), 1)))

			return pre_yaw, pre_pitch, pre_roll, angles

			class Hopenet_shape(nn.Module):
			# This is just Hopenet with 3 output layers for yaw, pitch and roll.
			def __init__(self, block, layers, num_bins, shape_bins):
			class ResNet(nn.Module):
			# ResNet for regression of 3 Euler angles.
			def __init__(self, block, layers, num_classes=1000):
			self.inplanes = 64
			super(Hopenet_shape, self).__init__()
			super(ResNet, self).__init__()
			self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
			bias=False)
			self.bn1 = nn.BatchNorm2d(64)
			@@ -141,19 +86,7 @@
			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)
			self.fc_shape_0 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_1 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_2 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_3 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_4 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_5 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_6 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_7 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_8 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_shape_9 = nn.Linear(512 * block.expansion, shape_bins)
			self.fc_angles = nn.Linear(512 * block.expansion, num_classes)

			for m in self.modules():
			if isinstance(m, nn.Conv2d):
			@@ -193,20 +126,46 @@

			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)

			shape = []
			shape.append(self.fc_shape_0(x))
			shape.append(self.fc_shape_1(x))
			shape.append(self.fc_shape_2(x))
			shape.append(self.fc_shape_3(x))
			shape.append(self.fc_shape_4(x))
			shape.append(self.fc_shape_5(x))
			shape.append(self.fc_shape_6(x))
			shape.append(self.fc_shape_7(x))
			shape.append(self.fc_shape_8(x))
			shape.append(self.fc_shape_9(x))

			return yaw, pitch, roll, shape
			return yaw, pitch, roll