查看efficientnet_pytorch的网络结构的输出

最新推荐文章于 2024-05-12 20:47:49 发布
最新推荐文章于 2024-05-12 20:47:49 发布
阅读量531 收藏
点赞数
分类专栏： 网络结构查看 文章标签： EfficientNet 预训练模型 卷积神经网络 MBConvBlock 特征提取
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_34974229/article/details/125340519
版权

查看使用预训练的efficientnetb0:

from efficientnet_pytorch import EfficientNet
model =EfficientNet.from_pretrained('efficientnet-b0',num_classes=2)
print(model)

输出结果：

Loaded pretrained weights for efficientnet-b0
EfficientNet(
  (_conv_stem): Conv2dStaticSamePadding(
    3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False
    (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
  )
  (_bn0): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
  (_blocks): ModuleList(
    (0): MBConvBlock(
      (_depthwise_conv): Conv2dStaticSamePadding(
        32, 32, kernel_size=(3, 3), stride=[1, 1], groups=32, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        32, 8, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        8, 32, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(16, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (1): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(96, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        96, 96, kernel_size=(3, 3), stride=[2, 2], groups=96, bias=False
        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(96, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        96, 4, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        4, 96, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (2): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        144, 144, kernel_size=(3, 3), stride=(1, 1), groups=144, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        144, 6, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        6, 144, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (3): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        144, 144, kernel_size=(5, 5), stride=[2, 2], groups=144, bias=False
        (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        144, 6, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        6, 144, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (4): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        240, 240, kernel_size=(5, 5), stride=(1, 1), groups=240, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        240, 10, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        10, 240, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (5): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        240, 240, kernel_size=(3, 3), stride=[2, 2], groups=240, bias=False
        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        240, 10, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        10, 240, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (6): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (7): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (8): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(5, 5), stride=[1, 1], groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (9): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (10): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (11): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=[2, 2], groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (12): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (13): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (14): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (15): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(3, 3), stride=[1, 1], groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(320, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
  )
  (_conv_head): Conv2dStaticSamePadding(
    320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False
    (static_padding): Identity()
  )
  (_bn1): BatchNorm2d(1280, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
  (_avg_pooling): AdaptiveAvgPool2d(output_size=1)
  (_dropout): Dropout(p=0.2, inplace=False)
  (_fc): Linear(in_features=1280, out_features=2, bias=True)
  (_swish): MemoryEfficientSwish()
)

b1:

Loaded pretrained weights for efficientnet-b1
EfficientNet(
  (_conv_stem): Conv2dStaticSamePadding(
    3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False
    (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
  )
  (_bn0): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
  (_blocks): ModuleList(
    (0): MBConvBlock(
      (_depthwise_conv): Conv2dStaticSamePadding(
        32, 32, kernel_size=(3, 3), stride=[1, 1], groups=32, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        32, 8, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        8, 32, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(16, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (1): MBConvBlock(
      (_depthwise_conv): Conv2dStaticSamePadding(
        16, 16, kernel_size=(3, 3), stride=(1, 1), groups=16, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(16, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        16, 4, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        4, 16, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(16, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (2): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(96, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        96, 96, kernel_size=(3, 3), stride=[2, 2], groups=96, bias=False
        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(96, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        96, 4, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        4, 96, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (3): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        144, 144, kernel_size=(3, 3), stride=(1, 1), groups=144, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        144, 6, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        6, 144, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (4): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        144, 144, kernel_size=(3, 3), stride=(1, 1), groups=144, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        144, 6, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        6, 144, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (5): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        144, 144, kernel_size=(5, 5), stride=[2, 2], groups=144, bias=False
        (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        144, 6, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        6, 144, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (6): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        240, 240, kernel_size=(5, 5), stride=(1, 1), groups=240, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        240, 10, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        10, 240, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (7): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        240, 240, kernel_size=(5, 5), stride=(1, 1), groups=240, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        240, 10, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        10, 240, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (8): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        240, 240, kernel_size=(3, 3), stride=[2, 2], groups=240, bias=False
        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        240, 10, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        10, 240, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (9): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (10): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (11): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (12): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        480, 480, kernel_size=(5, 5), stride=[1, 1], groups=480, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        480, 20, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        20, 480, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (13): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (14): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (15): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (16): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        672, 672, kernel_size=(5, 5), stride=[2, 2], groups=672, bias=False
        (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        672, 28, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        28, 672, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (17): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (18): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (19): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (20): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (21): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1152, 1152, kernel_size=(3, 3), stride=[1, 1], groups=1152, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1152, 48, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        48, 1152, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(320, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
    (22): MBConvBlock(
      (_expand_conv): Conv2dStaticSamePadding(
        320, 1920, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn0): BatchNorm2d(1920, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_depthwise_conv): Conv2dStaticSamePadding(
        1920, 1920, kernel_size=(3, 3), stride=(1, 1), groups=1920, bias=False
        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
      )
      (_bn1): BatchNorm2d(1920, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_se_reduce): Conv2dStaticSamePadding(
        1920, 80, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_se_expand): Conv2dStaticSamePadding(
        80, 1920, kernel_size=(1, 1), stride=(1, 1)
        (static_padding): Identity()
      )
      (_project_conv): Conv2dStaticSamePadding(
        1920, 320, kernel_size=(1, 1), stride=(1, 1), bias=False
        (static_padding): Identity()
      )
      (_bn2): BatchNorm2d(320, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
      (_swish): MemoryEfficientSwish()
    )
  )
  (_conv_head): Conv2dStaticSamePadding(
    320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False
    (static_padding): Identity()
  )
  (_bn1): BatchNorm2d(1280, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
  (_avg_pooling): AdaptiveAvgPool2d(output_size=1)
  (_dropout): Dropout(p=0.2, inplace=False)
  (_fc): Linear(in_features=1280, out_features=2, bias=True)
  (_swish): MemoryEfficientSwish()
)
佛珠散了一地
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
pytorch 实现查看网络中的参数
09-18
今天小编就为大家分享一篇pytorch 实现查看网络中的参数，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧
EfficientNet论文输出
Asura的博客
08-20 306
论文：EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 一句话总结： 这篇文章 学习内容： 提示：这里可以添加要学的内容 例如： 1、 搭建 Java 开发环境 2、 掌握 Java 基本语法 3、 掌握条件语句 4、 掌握循环语句 学习时间： 提示：这里可以添加计划学习的时间 例如： 1、 周一至周五晚上 7 点—晚上9点 2、 周六上午 9 点-上午 11 点 3、 周日下午 3 点-下午 6 点 学习
EfficientNet网络结构详细解读+SE注意力机制+pytorch框架复现
最新发布
慕溪同学的博客
05-12 2467
在前一篇博客当中已经详细解读了EfficientNet论文中的相关工作和实验，该论文是为了让调节网络的深度、宽度、输入scale达到一个合适的比例，以此让网络的特征提取部分达到最好的效果。但是在原论文当中其实是没有详细介绍网络结构搭建，这篇博客也是对EfficientNet网络结构进行深度详细剖析，详细介绍该网络中用到的SE注意力机制深度可分离卷积以及MBconv结构，并且使用pytorch框架进行复现。
利用Pytorch实现EfficientNet网络
AdjsWsgz的博客
05-13 1449
该网络的论文是Google在2019年发表的文章，作者同时探讨了输入图像分辨率和网络的深度、宽度对准确率的影响，通过网络搜索技术同时探索这三者的合理配置。
EfficientNet-PyTorch：EfficientNet的PyTorch实现
02-24
EfficientNet PyTorch 快速开始 使用pip install efficientnet_pytorch的net_pytorch并使用以下命令加载经过预训练的EfficientNet： from efficientnet_pytorch import EfficientNet model = EfficientNet . from_pretrained ( 'efficientnet-b0' ) 更新 更新（2020年8月25日） 此更新添加： 一个新的include_top （默认： True ）选项（ ） 使用连续测试 代码质量改进和修复（ ） 更新（2020年5月14日） 此更新添加了全面的注释和文档（感谢@workingcoder）。 更新（2020年1月23日） 此更新基于对抗训练添加了新类别的预训练模型，称为advprop 。 重要的是要注意，
EfficientNet-PyTorch:EfficientNet和EfficientNetV2的PyTorch实现（即将推出！）
05-10
EfficientNet PyTorch 快速开始 使用pip install efficientnet_pytorch的net_pytorch并使用以下命令加载经过预训练的EfficientNet： from efficientnet_pytorch import EfficientNet model = EfficientNet . from_pretrained ( 'efficientnet-b0' ) 更新 更新（2021年4月2日） 已发布！ 当您阅读本文时，我正在努力实现它：) 关于EfficientNetV2： EfficientNetV2是卷积网络的新家族，与以前的模型相比，它具有更快的训练速度和更好的参数效率。 为了开发该系列模型，我们将训练感知的神经体系结构搜索和缩放结合使用，以共同优化训练速度和参数效率。 从富含新操作（例如Fused-MBConv）的搜索空
Python-EfficientNet的一个PyTorch实现
08-11
EfficientNet的一个PyTorch实现
【小白学PyTorch】13 EfficientNet详解及PyTorch实现
忽逢桃林的博客
09-25 7225
参考目录： 文章目录1 EfficientNet1.1 概述1.2 把扩展问题用数学来描述1.3 实验内容1.4 compound scaling method1.5 EfficientNet的基线模型2 PyTorch实现 文章来自微信公众号【机器学习炼丹术】。我是炼丹兄，如果有疑问或者想要和炼丹兄交流的可以加微信：cyx645016617. efficientNet的论文原文链接: https://arxiv.org/pdf/1905.11946.pdf 模型扩展Model scaling一直以来都是提
EfficientNet-Pytorch:在EfficientNet上训练自己的数据集的演示
05-12
高效网式火炬 在EfficientNet上训练自己的数据集的演示 感谢> ，我只是简单地演示如何基于EfficientNet-Pytorch训练自己的数据集。 步骤1：准备自己的分类数据集 然后，数据目录应如下所示： -dataset\ -model\ -train\ -1\ -2\ ... -test\ -1\ -2\ ... 步骤2：训练和测试 （1）您可以通过修改line 169来选择是否自动下载预训练模型。 可以在> 上获得预训练的模型。 您可以在eff_weights文件夹下下载它们。 （2）更改一些设置以匹配您的数据集。 即line13-22 run efficientnet_sample.py to start train and test
Python-PyTorch实现的EfficientNet重新思考卷积神经网络的模型缩放
08-12
PyTorch实现的“EfficientNet：重新思考卷积神经网络的模型缩放”
EfficientNet网络详解并使用pytorch搭建模型
STATEABC的博客
05-04 4829
1.EfficientNet网络设计思想 在原论文中，作者通过网络搜索技术同时探索输入分辨率，网络的深度depth、channel的宽度width对准确率的影响，构建EfficientNet网络。 根据以往的经验，增加网络的深度depth能够得到更加丰富、复杂的特征，但网络的深度过深会面临梯度消失，训练困难的问题。 增加网络的width能够获得更高细粒度的特征并且也更容易训练，但对于width很大而深度较浅的网络往往很难学习到更深层次的特征。 增加输入网络的图像分辨率能够潜在得获得更高细粒度的特征模板，但对
EfficientNet网络及Pytorch实现
weixin_39750526的博客
03-31 629
2019年由Google Brain提出，论文地址：EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 论文提出了一种新的模型缩放方法，它使用一个简单而高效的复合系数来从depth, width, resolution 三个维度放大网络，不会像传统的方法那样任意缩放网络的维度，基于神经结构搜索技术可以获得最优的一组参数(复合系数)。 图43 Compound Scaling 图44 Eff
EfficientNet的pyTorch版本的使用和训练方法
热门推荐
期待黎明的博客
02-07 3万+
EfficientNet的pyTorch版本的训练和测试 1. efficientNet 的pyTorch版本的测试和使用 第三方PyTorch代码 # pytorch 的efficientNet安装 Install via pip: pip install efficientnet_pytorch Or install from source: git clone https://github...
Pytorch实现EfficientNet，2024年最新你还看不懂吗
2401_84182793的博客
04-10 494
(img-aJmjnXvd-1712714283518)]知识点，真正体系化！
图像分类】【深度学习】【轻量级网络】【Pytorch版本】EfficientNet_V2模型算法详解
yangyu0515的博客
01-24 3534
图像分类】【深度学习】【轻量级网络】【Pytorch版本】EfficientNet_V2模型算法详解
Pytorch之EfficientNetV2图像分类
风间琉璃的博客
10-09 2319
Google 在2021年4月份提出了 EfficientNet 的改进版 EfficientNet v2: Smaller Models and Faster Training。从论文题目上就可以看出 v2 版本相比 v1，模型参数量更小，训练速度更快。在 EfficientNet V1的基础上，引入了到搜索空间中，同时为渐进式学习引入了自适应正则强度调整机制。两种改进的组合使得 EfficientNet v2 在多个基准数据集上取得了 SOTA 性能，且训练速度更快。
目标检测论文：ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design及其PyTorch实现
mingo_敏
07-22 908
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design 论文链接：https://arxiv.org/pdf/1807.11164.pdf PyTorch：https://github.com/shanglianlm0525/Lightweight-network ShuffleNet V2 unit Sh...
pytorch padding_pytorch笔记：Efficientnet微调
weixin_39664010的博客
11-12 519
pytorch中有为efficientnet专门写好的网络模型，写在efficientnet_pytorch模块中。模块包含EfficientNet的op-for-op的pytorch实现，也实现了预训练模型和示例。安装Efficientnetpytorch EfficientnetInstall via pip:pip Or install from source:git clone lukem...
efficientnet_pytorch
09-13
efficientnet_pytorch是一个基于PyTorch实现的高效神经网络模型，它是由Google Brain团队开发的，采用了一种新的网络结构搜索算法，可以在保持模型精度的同时，大幅度减少模型参数和计算量。该模型在图像分类、目标...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值