기존 UNET 구조에서 skip connection 결과가 Decoder 에 추가될 때, Attention score를 적용해보기 위해 Attention Layer를 추가 Codes # 02. Attention UNET Model class ConvBlock(nn.Module): def __init__(self, in_channels, out_channels): super().__init__() self.conv = nn.Sequential( nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=True), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(..