假设有预定义的模型架构，请按照以下步骤，以来自 torchvision 的 ResNet18 为例，执行量化感知训练 (QAT)。完整模型定义可在此处找到。
- 检查是否存在要量化的非模块运算。ResNet18 使用
'+'来添加 2 个张量。将其替换为pytorch_nndct.nn.modules.functional.Add。 - 检查是否存在要多次调用的模块。通常，此类模块并无权重，最常见的是
torch.nn.ReLu模块。定义多个此类模块，然后在单次前传中逐一调用这些模块。修改后满足要求的定义如下：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.relu1 = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = norm_layer(planes) self.downsample = downsample self.stride = stride # Use a functional module to replace '+' self.skip_add = functional.Add() # Additional defined module self.relu2 = nn.ReLU(inplace=True) def forward(self, x): 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 function module instead of '+' # out += identity out = self.skip_add(out, identity) out = self.relu2(out) return out - 插入
QuantStub和DeQuantStub。使用
QuantStub来量化网络的输入，使用DeQuantStub来反量化网络的输出。这样就会对单次前传中从QuantStub到DeQuantStub的任意子网络进行量化。允许存在多对 QuantStub-DeQuantStub：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 iEachne: # 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) self.quant_stub = nndct_nn.QuantStub() self.dequant_stub = nndct_nn.DeQuantStub() 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 forward(self, x): x = self.quant_stub(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 = torch.flatten(x, 1) x = self.fc(x) x = self.dequant_stub(x) return x - 使用 QAT API 创建量化器并训练模型：
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) state_dict = torch.load(model_urls[arch]) 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) model = resnet18(pretrained=True) # Generate dummy inputs. input = torch.randn([batch_size, 3, 224, 224], dtype=torch.float32) # Create a quantizer from pytorch_nndct import QatProcessor qat_processor = QatProcessor(model, inputs, bitwidth=8) quantized_model = qat_processor.trainable_model()optimizer = torch.optim.Adam( quantized_model.parameters(), lr, weight_decay=weight_decay) # Use the optimizer to train del, just like a normal float model. … - 获取可部署模型并进行测试。
完成 QAT 后，将量化模型转换为可部署模型。可部署模型的精度可能与量化模型的精度略有不同：
output_dir = 'qat_result' deployable_model = qat_processor.to_deployable(quantized_model, output_dir) validate(val_loader, deployable_model, criterion, gpu) - 从可部署模型导出 XMODEL。
batch size=1是 XMODEL 编译的必备条件：# Use CPU mode to export xmodel. deployable_model.cpu() val_subset = torch.utils.data.Subset(val_dataset, list(range(1))) subset_loader = torch.utils.data.DataLoader( val_subset, batch_size=1, shuffle=False, num_workers=8, pin_memory=True) # Must forward deployable model at least 1 iteration with batch_size=1 for images, _ in subset_loader: deployable_model(images) qat_processor.export_xmodel(output_dir)