models/resnet.py

import torch
import torch.nn as nn
from torch.utils.model_zoo import load_url as load_state_dict_from_url
import torch.nn.functional as F


model_urls = {
	'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
	'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
	'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
	'resnet152': 'https://download.pytorch.org/models/resnet152-394f9c45.pth'
}


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)


def conv1x1(in_planes, out_planes, stride=1):
	"""1x1 convolution"""
	return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
	expansion = 1

	def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
				 base_width=64, dilation=1, norm_layer=None):
		super(BasicBlock, self).__init__()
		if norm_layer is None:
			norm_layer = nn.BatchNorm2d
		if groups != 1 or 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")
		# Both self.conv1 and self.downsample layers downsample the input when stride != 1
		self.conv1 = conv3x3(inplanes, planes, stride)
		self.bn1 = norm_layer(planes)
		self.relu = nn.ReLU(inplace=True)
		self.conv2 = conv3x3(planes, planes)
		self.bn2 = norm_layer(planes)
		self.downsample = downsample
		self.stride = stride

	def forward(self, x):
		identity = x

		out = self.conv1(x)
		out = self.bn1(out)
		out = self.relu(out)

		out = self.conv2(out)
		out = self.bn2(out)

		if self.downsample is not None:
			identity = self.downsample(x)

		out += identity
		out = self.relu(out)

		return out


class Bottleneck(nn.Module):
	expansion = 4

	def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
				 base_width=64, dilation=1, norm_layer=None):
		super(Bottleneck, self).__init__()
		if norm_layer is None:
			norm_layer = nn.BatchNorm2d
		width = int(planes * (base_width / 64.)) * groups
		# Both self.conv2 and self.downsample layers downsample the input when stride != 1
		self.conv1 = conv1x1(inplanes, width)
		self.bn1 = norm_layer(width)
		self.conv2 = conv3x3(width, width, stride, groups, dilation)
		self.bn2 = norm_layer(width)
		self.conv3 = conv1x1(width, planes * self.expansion)
		self.bn3 = norm_layer(planes * self.expansion)
		self.relu = nn.ReLU(inplace=True)
		self.downsample = downsample
		self.stride = stride

	def forward(self, x):
		identity = 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:
			identity = self.downsample(x)

		out += identity
		out = self.relu(out)

		return out

class DeconvBasicBlock(nn.Module):
	def __init__(self, in_planes, stride=1, norm_layer=None):
		super(DeconvBasicBlock, self).__init__()
		
		if norm_layer is None:
			norm_layer = nn.BatchNorm2d
		planes = int(in_planes/stride)

		self.conv2 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=1, padding=1, bias=False)
		self.bn2 = norm_layer(in_planes)

		self.bn1 = norm_layer(planes)

		if stride == 1:
			self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
			self.bn1 = norm_layer(planes)
			self.shortcut = nn.Sequential()
		else:
			self.conv1 = nn.ConvTranspose2d(in_planes, planes, kernel_size=3, stride=stride, bias=False, padding=1, output_padding=1)
			self.bn1 = norm_layer(planes)
			self.shortcut = nn.Sequential(
				nn.ConvTranspose2d(in_planes, planes, kernel_size=3, stride=stride, bias=False, padding=1, output_padding=1),
				norm_layer(planes)
			)

	def forward(self, x):
		out = torch.relu(self.bn2(self.conv2(x)))
		out = self.bn1(self.conv1(out))
		out += self.shortcut(x)
		out = torch.relu(out)
		return out

class DeconvBottleneck(nn.Module):
	def __init__(self, in_channels, out_channels, expansion=2, stride=1, upsample=None, norm_layer=None):
		super(DeconvBottleneck, self).__init__()
		if norm_layer is None:
			norm_layer = nn.BatchNorm2d
		self.expansion = expansion
		self.conv1 = nn.Conv2d(in_channels, out_channels,
							   kernel_size=1, bias=False)
		self.bn1 = norm_layer(out_channels)
		if stride == 1:
			self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3,
								   stride=stride, bias=False, padding=1)
		else:
			self.conv2 = nn.ConvTranspose2d(out_channels, out_channels,
											kernel_size=3,
											stride=stride, bias=False,
											padding=1,
											output_padding=1)
		self.bn2 = norm_layer(out_channels)
		self.conv3 = nn.Conv2d(out_channels, out_channels * self.expansion,
							   kernel_size=1, bias=False)
		self.bn3 = norm_layer(out_channels * self.expansion)
		self.relu = nn.ReLU()
		self.upsample = upsample

	def forward(self, x):
		shortcut = 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)
		out = self.relu(out)

		if self.upsample is not None:
			shortcut = self.upsample(x)

		out += shortcut
		out = self.relu(out)

		return out


class ResNet(nn.Module):

	def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
				 groups=1, width_per_group=64, replace_stride_with_dilation=None,
				 norm_layer=None):
		super(ResNet, self).__init__()
		if norm_layer is None:
			norm_layer = nn.BatchNorm2d
		self._norm_layer = norm_layer

		self.inplanes = 64
		self.dilation = 1
		if replace_stride_with_dilation is None:
			# each element in the tuple indicates if we should replace
			# the 2x2 stride with a dilated convolution instead
			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))
		self.groups = groups
		self.base_width = width_per_group
		self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
							   bias=False)
		self.bn1 = norm_layer(self.inplanes)
		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,
									   dilate=replace_stride_with_dilation[0])
		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,
									   dilate=replace_stride_with_dilation[2])

		self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
		self.fc = nn.Linear(512 * block.expansion, num_classes)

		for m in self.modules():
			if isinstance(m, nn.Conv2d):
				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)

		# Zero-initialize the last BN in each residual branch,
		# so that the residual branch starts with zeros, and each residual block behaves like an identity.
		# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
		if zero_init_residual:
			for m in self.modules():
				if isinstance(m, Bottleneck):
					nn.init.constant_(m.bn3.weight, 0)
				elif isinstance(m, BasicBlock):
					nn.init.constant_(m.bn2.weight, 0)

	def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
		norm_layer = self._norm_layer
		downsample = None
		previous_dilation = self.dilation
		if dilate:
			self.dilation *= stride
			stride = 1
		if stride != 1 or self.inplanes != planes * block.expansion:
			downsample = nn.Sequential(
				conv1x1(self.inplanes, planes * block.expansion, stride),
				norm_layer(planes * block.expansion),
			)

		layers = []
		layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
							self.base_width, previous_dilation, norm_layer))
		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,
								norm_layer=norm_layer))

		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) 

		return x
	

def _resnet(arch, block, layers, pretrained, progress, **kwargs):
	model = ResNet(block, layers, **kwargs)
	if pretrained:
		state_dict = load_state_dict_from_url(model_urls[arch],
											  progress=progress)

		model.load_state_dict(state_dict)
	return model

def resnet18(pretrained=False, progress=True, **kwargs):
	r"""ResNet-18 model from
	`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>'_
	Args:
		pretrained (bool): If True, returns a model pre-trained on ImageNet
		progress (bool): If True, displays a progress bar of the download to stderr
	"""
	return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
				   **kwargs)

def resnet34(pretrained=False, progress=True, **kwargs):
	r"""ResNet-34 model from
	`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>'_
	Args:
		pretrained (bool): If True, returns a model pre-trained on ImageNet
		progress (bool): If True, displays a progress bar of the download to stderr
	"""
	return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
				   **kwargs)

def resnet50(pretrained=False, progress=True, **kwargs):
	r"""ResNet-50 model from
	`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>'_
	Args:
		pretrained (bool): If True, returns a model pre-trained on ImageNet
		progress (bool): If True, displays a progress bar of the download to stderr
	"""
	return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
				   **kwargs)

def resnet152(pretrained=False, progress=True, **kwargs):
	r"""ResNet-152 model from
	`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>'_
	Args:
		pretrained (bool): If True, returns a model pre-trained on ImageNet
		progress (bool): If True, displays a progress bar of the download to stderr
	"""
	return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
				   **kwargs)


class ResNetGaze(nn.Module):
	def __init__(self):
		raise NotImplementedError
		
	def forward(self, x_in):
		output_dict = {}
		features = self.feature(x_in)
		z = self.avgpool(features)
		z = z.view(z.size(0), -1) ## (batch, dim)
		pred_gaze = self.fc(z)
		output_dict['pred_gaze'] = pred_gaze
		return output_dict

class Res18(ResNetGaze, nn.Module):
	def __init__(self,  resnet_pretrained=True):
		nn.Module.__init__(self)
		self.feature = resnet18(pretrained=resnet_pretrained)
		self.avgpool = nn.AdaptiveAvgPool2d((1,1))

		self.fc = nn.Linear(512, 2)
		

class Res50(ResNetGaze, nn.Module):
	def __init__(self, resnet_pretrained=True):
		nn.Module.__init__(self)
		self.feature = resnet50(pretrained=resnet_pretrained)
		self.avgpool = nn.AdaptiveAvgPool2d((1,1))
		self.fc = nn.Linear(2048, 2)
			
		
class Res152(ResNetGaze, nn.Module):
	def __init__(self, resnet_pretrained=True):
		nn.Module.__init__(self)
		self.feature = resnet152(pretrained=resnet_pretrained)
		self.avgpool = nn.AdaptiveAvgPool2d((1,1))
		self.fc = nn.Linear(2048, 2)