Faster R-CNN torchvision 实现的说明

Question

我正在研究 torchvision 的 Faster R-CNN 实现的 source code，我遇到了一些我不太了解的事情。也就是说，假设我想创建一个 Faster R-CNN 模型，而不是在 COCO 上预训练，在 ImageNet 上预训练主干，然后只获得主干，我执行以下操作：

plain_backbone = fasterrcnn_resnet50_fpn(pretrained=False, pretrained_backbone=True).backbone.body

这与here 和here 所示的主干设置方式一致。但是，当我通过模型传递图像时，结果与我直接设置 resnet50 所获得的结果不对应。即：

# Regular resnet50, pretrained on ImageNet, without the classifier and the average pooling layer
resnet50_1 = torch.nn.Sequential(*(list(torchvision.models.resnet50(pretrained=True).children())[:-2]))
resnet50_1.eval()
# Resnet50, extract from the Faster R-CNN, also pre-trained on ImageNet
resnet50_2 = fasterrcnn_resnet50_fpn(pretrained=False, pretrained_backbone=True).backbone.body
resnet50_2.eval()
# Loading a random image, converted to torch.Tensor, rescalled to [0, 1] (not that it matters)
image = transforms.ToTensor()(Image.open("random_images/random.jpg")).unsqueeze(0)
# Obtaining the model outputs
with torch.no_grad():
    # Output from the regular resnet50
    output_1 = resnet50_1(image)
    # Output from the resnet50 extracted from the Faster R-CNN
    output_2 = resnet50_2(image)["3"]
    # Their outputs aren't the same, which I would assume they should be
    np.testing.assert_almost_equal(output_1.numpy(), output_2.numpy())

期待你的想法！

Answer 1

这是因为 fasterrcnn_resnet50_fpn 使用自定义规范化层 (FrozenBatchNorm2d) 而不是默认的 BatchNorm2D。它们非常相似，但我怀疑微小的数值差异会导致问题。

如果你指定与标准 resnet 使用相同的规范化层，它将通过检查：

import torch
import torchvision
from torchvision.models.detection.faster_rcnn import fasterrcnn_resnet50_fpn
import numpy as np
from torchvision.ops import misc as misc_nn_ops

# Regular resnet50, pretrained on ImageNet, without the classifier and the average pooling layer
resnet50_1 = torch.nn.Sequential(*(list(torchvision.models.resnet50(pretrained=True, norm_layer=misc_nn_ops.FrozenBatchNorm2d).children())[:-2]))
resnet50_1.eval()
# Resnet50, extract from the Faster R-CNN, also pre-trained on ImageNet
resnet50_2 = fasterrcnn_resnet50_fpn(pretrained=False, pretrained_backbone=True).backbone.body
resnet50_2.eval()
# am too lazy to get a real image
image = torch.ones((1, 3, 224, 224))
# Obtaining the model outputs
with torch.no_grad():
    # Output from the regular resnet50
    output_1 = resnet50_1(image)
    # Output from the resnet50 extracted from the Faster R-CNN
    output_2 = resnet50_2(image)["3"]
    # Passes
    np.testing.assert_almost_equal(output_1.numpy(), output_2.numpy())