Lane_Segmentation 车道线检测

U-Net for lane segmentation in PyTorch.

Dataset & Training

total_dataset：100% train_dataset：60% val_dataset：20% test_dataset：20%

U-Net 骨干网络

下采样：
ModuleList(
  (0): UNetConvBlock(
    (block): Sequential(
      (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): ReLU()
      (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): ReLU()
    )
  )
  (1): UNetConvBlock(
    (block): Sequential(
      (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): ReLU()
      (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): ReLU()
    )
  )
  (2): UNetConvBlock(
    (block): Sequential(
      (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): ReLU()
      (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): ReLU()
    )
  )
  (3): UNetConvBlock(
    (block): Sequential(
      (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): ReLU()
      (2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): ReLU()
    )
  )
  (4): UNetConvBlock(
    (block): Sequential(
      (0): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): ReLU()
      (2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): ReLU()
    )
  )
)

上采样：
ModuleList(
  (0): UNetUpBlock(
    (up): ConvTranspose2d(1024, 512, kernel_size=(2, 2), stride=(2, 2))
    (conv_block): UNetConvBlock(
      (block): Sequential(
        (0): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU()
        (2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU()
      )
    )
  )
  (1): UNetUpBlock(
    (up): ConvTranspose2d(512, 256, kernel_size=(2, 2), stride=(2, 2))
    (conv_block): UNetConvBlock(
      (block): Sequential(
        (0): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU()
        (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU()
      )
    )
  )
  (2): UNetUpBlock(
    (up): ConvTranspose2d(256, 128, kernel_size=(2, 2), stride=(2, 2))
    (conv_block): UNetConvBlock(
      (block): Sequential(
        (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU()
        (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU()
      )
    )
  )
  (3): UNetUpBlock(
    (up): ConvTranspose2d(128, 64, kernel_size=(2, 2), stride=(2, 2))
    (conv_block): UNetConvBlock(
      (block): Sequential(
        (0): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU()
        (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU()
      )
    )
  )
)

运行

python train.py