ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

class ShuffleNetV2(nn.Module):
    def __init__(self, net_size):
        super(ShuffleNetV2, self).__init__()
        out_channels = configs[net_size]['out_channels']
        num_blocks = configs[net_size]['num_blocks']

        self.conv1 = nn.Conv2d(3, 24, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(24)
        self.in_channels = 24
        self.layer1 = self._make_layer(out_channels[0], num_blocks[0])
        self.layer2 = self._make_layer(out_channels[1], num_blocks[1])
        self.layer3 = self._make_layer(out_channels[2], num_blocks[2])
        self.conv2 = nn.Conv2d(out_channels[2], out_channels[3],
                               kernel_size=1, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels[3])
        self.linear = nn.Linear(out_channels[3], 10)

    def _make_layer(self, out_channels, num_blocks):
        layers = [DownBlock(self.in_channels, out_channels)]
        for i in range(num_blocks):
            layers.append(BasicBlock(out_channels))
            self.in_channels = out_channels
        return nn.Sequential(*layers)

class BasicBlock(nn.Module):
    def __init__(self, in_channels, split_ratio=0.5):
        super(BasicBlock, self).__init__()
        self.split = SplitBlock(split_ratio)
        in_channels = int(in_channels * split_ratio)
        self.conv1 = nn.Conv2d(in_channels, in_channels,
                               kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(in_channels)
        self.conv2 = nn.Conv2d(in_channels, in_channels,
                               kernel_size=3, stride=1, padding=1, groups=in_channels, bias=False)
        self.bn2 = nn.BatchNorm2d(in_channels)
        self.conv3 = nn.Conv2d(in_channels, in_channels,
                               kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(in_channels)
        self.shuffle = ShuffleBlock()

class DownBlock(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(DownBlock, self).__init__()
        mid_channels = out_channels // 2
        # left
        self.conv1 = nn.Conv2d(in_channels, in_channels,
                               kernel_size=3, stride=2, padding=1, groups=in_channels, bias=False)
        self.bn1 = nn.BatchNorm2d(in_channels)
        self.conv2 = nn.Conv2d(in_channels, mid_channels,
                               kernel_size=1, bias=False)
        self.bn2 = nn.BatchNorm2d(mid_channels)
        # right
        self.conv3 = nn.Conv2d(in_channels, mid_channels,
                               kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(mid_channels)
        self.conv4 = nn.Conv2d(mid_channels, mid_channels,
                               kernel_size=3, stride=2, padding=1, groups=mid_channels, bias=False)
        self.bn4 = nn.BatchNorm2d(mid_channels)
        self.conv5 = nn.Conv2d(mid_channels, mid_channels,
                               kernel_size=1, bias=False)
        self.bn5 = nn.BatchNorm2d(mid_channels)

        self.shuffle = ShuffleBlock()

shufflenet_v2_x0_5 in torchvisionmodels output

/home/seamanj/Software/anaconda3/bin/python3.7 /home/seamanj/Workspace/AlexNet/main.py
Downloading: "https://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth" to /home/seamanj/.cache/torch/checkpoints/shufflenetv2_x0.5-f707e7126e.pth
100%|██████████| 5538128/5538128 [00:00<00:00, 8747872.18it/s]
ShuffleNetV2(
  (conv1): Sequential(
    (0): Conv2d(3, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU(inplace)
  )
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (stage2): Sequential(
    (0): InvertedResidual(
      (branch1): Sequential(
        (0): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)
        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (4): ReLU(inplace)
      )
      (branch2): Sequential(
        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)
        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (1): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (2): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (3): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
  )
  (stage3): Sequential(
    (0): InvertedResidual(
      (branch1): Sequential(
        (0): Conv2d(48, 48, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=48, bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (3): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (4): ReLU(inplace)
      )
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (1): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (2): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (3): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (4): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (5): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (6): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (7): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)
        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
  )
  (stage4): Sequential(
    (0): InvertedResidual(
      (branch1): Sequential(
        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (4): ReLU(inplace)
      )
      (branch2): Sequential(
        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (1): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)
        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (2): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)
        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
    (3): InvertedResidual(
      (branch2): Sequential(
        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace)
        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)
        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (7): ReLU(inplace)
      )
    )
  )
  (conv5): Sequential(
    (0): Conv2d(192, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU(inplace)
  )
  (fc): Linear(in_features=1024, out_features=1000, bias=True)
)

Process finished with exit code 0