R_50_FPN的module和各层维度

最新推荐文章于 2022-07-07 17:15:27 发布

业精于勤荒于嬉-行成于思而毁于随

最新推荐文章于 2022-07-07 17:15:27 发布

阅读量805

点赞数

CC 4.0 BY-SA版权

分类专栏： maskrcnn理解记录姿态估计逐步

本文链接：https://blog.youkuaiyun.com/m0_37644085/article/details/88884690

本文详细解析了ResNet-50网络结构中的Stem、Bottleneck层以及FPN（特征金字塔网络）的实现，包括每个模块的下采样操作和输出特征层的维度变化。对于理解深度学习中的图像特征提取和多尺度信息融合有重要作用。

(backbone): Sequential(
    (body): ResNet(
      (stem): StemWithFixedBatchNorm(
        (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
        (bn1): FrozenBatchNorm2d()
      )
      (layer1): Sequential(
        (0): BottleneckWithFixedBatchNorm(
          (downsample): Sequential(
            (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (1): FrozenBatchNorm2d()
          )
          (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d()
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d()
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d()
        )
        (1): BottleneckWithFixedBatchNorm(
          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d()
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d()
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d()
        )
        (2): BottleneckWithFixedBatchNorm(
          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d()
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d()
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d()
        )
      )
      (layer2): Sequential(
        (0): BottleneckWithFixedBatchNorm(
          (downsample): Sequential(
            (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): FrozenBatchNorm2d()
          )
          (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
          (bn1): FrozenBatchNorm2d()
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d()
          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
     &nbs