SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND 0.5MB MODEL SIZE

最新推荐文章于 2024-05-23 09:37:52 发布

seamanj

最新推荐文章于 2024-05-23 09:37:52 发布

阅读量336

点赞数

分类专栏： deep learning pytorch paper

本文链接：https://blog.youkuaiyun.com/seamanj/article/details/90677637

版权

paper 同时被 3 个专栏收录

106 篇文章

订阅专栏

deep learning

40 篇文章

订阅专栏

pytorch

29 篇文章

订阅专栏

博客介绍了SqueezeNet，它能达到AlexNet级别的准确率，却拥有少50倍的参数，且模型大小仅0.5MB，在信息技术领域展现出高效的性能特点。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在这里插入图片描述

/home/seamanj/Software/anaconda3/bin/python3.7 /home/seamanj/Workspace/AlexNet/main.py
Downloading: "https://download.pytorch.org/models/squeezenet1_0-a815701f.pth" to /home/seamanj/.cache/torch/checkpoints/squeezenet1_0-a815701f.pth
100%|██████████| 5017600/5017600 [00:00<00:00, 7892750.24it/s]
SqueezeNet(
  (features): Sequential(
    (0): Conv2d(3, 96, kernel_size=(7, 7), stride=(2, 2))
    (1): ReLU(inplace)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)
    (3): Fire(
      (squeeze): Conv2d(96, 16, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (4): Fire(
      (squeeze): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (5): Fire(
      (squeeze): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (6): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)
    (7): Fire(
      (squeeze): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (8): Fire(
      (squeeze): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (9): Fire(
      (squeeze): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (10): Fire(
      (squeeze): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
    (11): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)
    (12): Fire(
      (squeeze): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
      (squeeze_activation): ReLU(inplace)
      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
      (expand1x1_activation): ReLU(inplace)
      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (expand3x3_activation): ReLU(inplace)
    )
  )
  (classifier): Sequential(
    (0): Dropout(p=0.5)
    (1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))
    (2): ReLU(inplace)
    (3): AdaptiveAvgPool2d(output_size=(1, 1))
  )
)

Process finished with exit code 0