pytorch量化感知训练（QAT）示例---ResNet

# resnet.py # Modified from # https://github.com/pytorch/vision/blob/release/0.8.0/torchvision/models/resnet.py import torch from torch import Tensor import torch.nn as nn from torchvision.models.utils import load_state_dict_from_url from typing import Type, Any, Callable, Union, List, Optional __all__ = [ 'ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d', 'wide_resnet50_2', 'wide_resnet101_2' ] 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 conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d: """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: int, out_planes: int, stride: int = 1) -> nn.Conv2d: """1x1 convolution""" return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) class BasicBlock(nn.Module): expansion: int = 1 def __init__( self, inplanes: int, planes: int, stride: int = 1, downsample: Optional[nn.Module] = None, groups: int = 1, base_width: int = 64, dilation: int = 1, norm_layer: Optional[Callable[..., nn.Module]] = None) -> 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) # Rename relu to relu1 self.relu1 = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = norm_layer(planes) self.downsample = downsample self.stride = stride self.skip_add = nn.quantized.FloatFunctional() # Remember to use two independent ReLU for layer fusion. self.relu2 = nn.ReLU(inplace=True) def forward(self, x: Tensor) -> Tensor: identity = x out = self.conv1(x) out = self.bn1(out) out = self.relu1(out) out = self.conv2(out) out = self.bn2(out) if self.downsample is not None: identity = self.downsample(x) # Use FloatFunctional for addition for quantization compatibility # out += identity # out = torch.add(identity, out) out = self.skip_add.add(identity, out) out = self.relu2(out) return out class Bottleneck(nn.Module): # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2) # while original implementation places the stride at the first 1x1 convolution(self.conv1) # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385. # This variant is also known as ResNet V1.5 and improves accuracy according to # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch. expansion: int = 4 def __init__( self, inplanes: int, planes: int, stride: int = 1, downsample: Optional[nn.Module] = None, groups: int = 1, base_width: int = 64, dilation: int = 1, norm_layer: Optional[Callable[..., nn.Module]] = None) -> 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.relu1 = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.skip_add = nn.quantized.FloatFunctional() self.relu2 = nn.ReLU(inplace=True) def forward(self, x: Tensor) -> Tensor: identity = x out = self.conv1(x) out = self.bn1(out) out = self.relu1(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 = torch.add(identity, out) out = self.skip_add.add(identity, out) out = self.relu2(out) return out class ResNet(nn.Module): def __init__( self, block: Type[Union[BasicBlock, Bottleneck]], layers: List[int], num_classes: int = 1000, zero_init_residual: bool = False, groups: int = 1, width_per_group: int = 64, replace_stride_with_dilation: Optional[List[bool]] = None, norm_layer: Optional[Callable[..., nn.Module]] = None) -> 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,