phuocphn/resnet18.py

## resnet18.py
import torch
import torch.nn as nn
from lsq import Conv2dLSQ, LinearLSQ, ActLSQ

__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
           'wide_resnet50_2', 'wide_resnet101_2']

def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return Conv2dLSQ(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation, nbits=8)


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return Conv2dLSQ(in_planes, out_planes, kernel_size=1, stride=stride, bias=False, nbits=8)


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.act1 = ActLSQ(nbits=8)

        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.act2 = ActLSQ(nbits=8)

        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.act1(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)
        out = self.act2(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.act0 = ActLSQ(nbits=8, signed=True)
        self.conv1 = Conv2dLSQ(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False, nbits=8)
        self.bn1 = norm_layer(self.inplanes)
        self.relu = nn.ReLU(inplace=True)
        self.act1 = ActLSQ(nbits=8)

        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.act2 = ActLSQ(nbits=8)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = LinearLSQ(512 * block.expansion, num_classes, nbits=8)

        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_impl(self, x):
        # See note [TorchScript super()]
        x= self.act0(x)
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.act1(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.act2(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x

    def forward(self, x):
        return self._forward_impl(x)

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',
    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
    'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
    'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
    'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
    'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}


def _resnet(arch, block, layers, pretrained, progress, **kwargs):
    model = ResNet(block, layers, **kwargs)
    from torch.utils.model_zoo import load_url as load_state_dict_from_url
    if pretrained:
        model_dict = model.state_dict()
        state_dict = load_state_dict_from_url(model_urls[arch],
                                              progress=progress)
        ignore_keys = ["act0.alpha", "act0.init_state", "conv1.alpha",
        "conv1.init_state", "act1.alpha", "act1.init_state",
         "layer1.0.conv1.alpha", "layer1.0.conv1.init_state",
          "layer1.0.act1.alpha", "layer1.0.act1.init_state",
          "layer1.0.conv2.alpha", "layer1.0.conv2.init_state",
           "layer1.0.act2.alpha", "layer1.0.act2.init_state",
           "layer1.1.conv1.alpha", "layer1.1.conv1.init_state",
           "layer1.1.act1.alpha", "layer1.1.act1.init_state",
            "layer1.1.conv2.alpha", "layer1.1.conv2.init_state",
             "layer1.1.act2.alpha", "layer1.1.act2.init_state",
              "layer2.0.conv1.alpha", "layer2.0.conv1.init_state",
              "layer2.0.act1.alpha", "layer2.0.act1.init_state",
               "layer2.0.conv2.alpha", "layer2.0.conv2.init_state",
               "layer2.0.act2.alpha", "layer2.0.act2.init_state", "layer2.0.downsample.0.alpha",
               "layer2.0.downsample.0.init_state", "layer2.1.conv1.alpha", "layer2.1.conv1.init_state",
               "layer2.1.act1.alpha", "layer2.1.act1.init_state", "layer2.1.conv2.alpha",
                "layer2.1.conv2.init_state", "layer2.1.act2.alpha", "layer2.1.act2.init_state",
                 "layer3.0.conv1.alpha", "layer3.0.conv1.init_state", "layer3.0.act1.alpha",
                 "layer3.0.act1.init_state", "layer3.0.conv2.alpha", "layer3.0.conv2.init_state",
                 "layer3.0.act2.alpha", "layer3.0.act2.init_state", "layer3.0.downsample.0.alpha",
                 "layer3.0.downsample.0.init_state", "layer3.1.conv1.alpha", "layer3.1.conv1.init_state",
                  "layer3.1.act1.alpha", "layer3.1.act1.init_state", "layer3.1.conv2.alpha",
                  "layer3.1.conv2.init_state", "layer3.1.act2.alpha", "layer3.1.act2.init_state",
                   "layer4.0.conv1.alpha", "layer4.0.conv1.init_state", "layer4.0.act1.alpha",
                    "layer4.0.act1.init_state", "layer4.0.conv2.alpha", "layer4.0.conv2.init_state",
                    "layer4.0.act2.alpha", "layer4.0.act2.init_state", "layer4.0.downsample.0.alpha",
                    "layer4.0.downsample.0.init_state", "layer4.1.conv1.alpha", "layer4.1.conv1.init_state",
                    "layer4.1.act1.alpha", "layer4.1.act1.init_state", "layer4.1.conv2.alpha",
                     "layer4.1.conv2.init_state", "layer4.1.act2.alpha", "layer4.1.act2.init_state",
                      "fc.init_state", "fc.alpha"]
        s = { k:v for k, v in state_dict.items() if k not in ignore_keys}
        model_dict.update(s)

        model.load_state_dict(model_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)
	import torch
	import torch.nn as nn
	from lsq import Conv2dLSQ, LinearLSQ, ActLSQ

	__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
	'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
	'wide_resnet50_2', 'wide_resnet101_2']

	def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
	"""3x3 convolution with padding"""
	return Conv2dLSQ(in_planes, out_planes, kernel_size=3, stride=stride,
	padding=dilation, groups=groups, bias=False, dilation=dilation, nbits=8)


	def conv1x1(in_planes, out_planes, stride=1):
	"""1x1 convolution"""
	return Conv2dLSQ(in_planes, out_planes, kernel_size=1, stride=stride, bias=False, nbits=8)


	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.act1 = ActLSQ(nbits=8)

	self.conv2 = conv3x3(planes, planes)
	self.bn2 = norm_layer(planes)
	self.act2 = ActLSQ(nbits=8)

	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.act1(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)
	out = self.act2(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.act0 = ActLSQ(nbits=8, signed=True)
	self.conv1 = Conv2dLSQ(3, self.inplanes, kernel_size=7, stride=2, padding=3,
	bias=False, nbits=8)
	self.bn1 = norm_layer(self.inplanes)
	self.relu = nn.ReLU(inplace=True)
	self.act1 = ActLSQ(nbits=8)

	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.act2 = ActLSQ(nbits=8)
	self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
	self.fc = LinearLSQ(512 * block.expansion, num_classes, nbits=8)

	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_impl(self, x):
	# See note [TorchScript super()]
	x= self.act0(x)
	x = self.conv1(x)
	x = self.bn1(x)
	x = self.relu(x)
	x = self.act1(x)
	x = self.maxpool(x)

	x = self.layer1(x)
	x = self.layer2(x)
	x = self.layer3(x)
	x = self.layer4(x)

	x = self.act2(x)
	x = self.avgpool(x)
	x = torch.flatten(x, 1)
	x = self.fc(x)

	return x

	def forward(self, x):
	return self._forward_impl(x)

	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',
	'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
	'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
	'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
	'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
	'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
	'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
	}


	def _resnet(arch, block, layers, pretrained, progress, **kwargs):
	model = ResNet(block, layers, **kwargs)
	from torch.utils.model_zoo import load_url as load_state_dict_from_url
	if pretrained:
	model_dict = model.state_dict()
	state_dict = load_state_dict_from_url(model_urls[arch],
	progress=progress)
	ignore_keys = ["act0.alpha", "act0.init_state", "conv1.alpha",
	"conv1.init_state", "act1.alpha", "act1.init_state",
	"layer1.0.conv1.alpha", "layer1.0.conv1.init_state",
	"layer1.0.act1.alpha", "layer1.0.act1.init_state",
	"layer1.0.conv2.alpha", "layer1.0.conv2.init_state",
	"layer1.0.act2.alpha", "layer1.0.act2.init_state",
	"layer1.1.conv1.alpha", "layer1.1.conv1.init_state",
	"layer1.1.act1.alpha", "layer1.1.act1.init_state",
	"layer1.1.conv2.alpha", "layer1.1.conv2.init_state",
	"layer1.1.act2.alpha", "layer1.1.act2.init_state",
	"layer2.0.conv1.alpha", "layer2.0.conv1.init_state",
	"layer2.0.act1.alpha", "layer2.0.act1.init_state",
	"layer2.0.conv2.alpha", "layer2.0.conv2.init_state",
	"layer2.0.act2.alpha", "layer2.0.act2.init_state", "layer2.0.downsample.0.alpha",
	"layer2.0.downsample.0.init_state", "layer2.1.conv1.alpha", "layer2.1.conv1.init_state",
	"layer2.1.act1.alpha", "layer2.1.act1.init_state", "layer2.1.conv2.alpha",
	"layer2.1.conv2.init_state", "layer2.1.act2.alpha", "layer2.1.act2.init_state",
	"layer3.0.conv1.alpha", "layer3.0.conv1.init_state", "layer3.0.act1.alpha",
	"layer3.0.act1.init_state", "layer3.0.conv2.alpha", "layer3.0.conv2.init_state",
	"layer3.0.act2.alpha", "layer3.0.act2.init_state", "layer3.0.downsample.0.alpha",
	"layer3.0.downsample.0.init_state", "layer3.1.conv1.alpha", "layer3.1.conv1.init_state",
	"layer3.1.act1.alpha", "layer3.1.act1.init_state", "layer3.1.conv2.alpha",
	"layer3.1.conv2.init_state", "layer3.1.act2.alpha", "layer3.1.act2.init_state",
	"layer4.0.conv1.alpha", "layer4.0.conv1.init_state", "layer4.0.act1.alpha",
	"layer4.0.act1.init_state", "layer4.0.conv2.alpha", "layer4.0.conv2.init_state",
	"layer4.0.act2.alpha", "layer4.0.act2.init_state", "layer4.0.downsample.0.alpha",
	"layer4.0.downsample.0.init_state", "layer4.1.conv1.alpha", "layer4.1.conv1.init_state",
	"layer4.1.act1.alpha", "layer4.1.act1.init_state", "layer4.1.conv2.alpha",
	"layer4.1.conv2.init_state", "layer4.1.act2.alpha", "layer4.1.act2.init_state",
	"fc.init_state", "fc.alpha"]
	s = { k:v for k, v in state_dict.items() if k not in ignore_keys}
	model_dict.update(s)

	model.load_state_dict(model_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)