deeplabv3+及pytorch实现
deeplab系列
DeepLabV3+ 基本原理及Pytorch版注解
以下参考：【语义分割系列】deeplabv3相关知识点以及pytorch实现（ASSP模块）
class ASPP(nn.Module):
def __init__(self, num_classes):
super(ASPP, self).__init__()
self.conv_1x1_1 = nn.Conv2d(2048, 256, kernel_size=1)
self.bn_conv_1x1_1 = nn.BatchNorm2d(256)
self.conv_3x3_1 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=6, dilation=6)
self.bn_conv_3x3_1 = nn.BatchNorm2d(256)
self.conv_3x3_2 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=12, dilation=12)
self.bn_conv_3x3_2 = nn.BatchNorm2d(256)
self.conv_3x3_3 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=18, dilation=18)
self.bn_conv_3x3_3 = nn.BatchNorm2d(256)
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv_1x1_2 = nn.Conv2d(2048, 256, kernel_size=1)
self.bn_conv_1x1_2 = nn.BatchNorm2d(256)
self.conv_1x1_3 = nn.Conv2d(1280, 256, kernel_size=1) # (1280 = 5*256)
self.bn_conv_1x1_3 = nn.BatchNorm2d(256)
self.conv_1x1_4 = nn.Conv2d(256, num_classes, kernel_size=1)
def forward(self, feature_map):
# (feature_map has shape (batch_size, 2048, h/8, w/8))
feature_map_h = feature_map.size()[2] # (h/8)
feature_map_w = feature_map.size()[3] # (w/8)
out_1x1 = F.relu(self.bn_conv_1x1_1(self.conv_1x1_1(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 E
out_3x3_1 = F.relu(self.bn_conv_3x3_1(self.conv_3x3_1(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 D
out_3x3_2 = F.relu(self.bn_conv_3x3_2(self.conv_3x3_2(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 C
out_3x3_3 = F.relu(self.bn_conv_3x3_3(self.conv_3x3_3(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 B
out_img = self.avg_pool(feature_map) # (shape: (batch_size, 512, 1, 1))对应图中 ImagePooling
out_img = F.relu(self.bn_conv_1x1_2(self.conv_1x1_2(out_img))) # (shape: (batch_size, 256, 1, 1))
out_img = F.upsample(out_img, size=(feature_map_h, feature_map_w), mode="bilinear") # (shape: (batch_size, 256, h/8, w/8))对应图中 A
out = torch.cat([out_1x1, out_3x3_1, out_3x3_2, out_3x3_3, out_img], 1) # (shape: (batch_size, 1280, h/8, w/8)) cat对应图中 F
out = F.relu(self.bn_conv_1x1_3(self.conv_1x1_3(out))) # (shape: (batch_size, 256, h/8, w/8)) bn_conv_1x1_3对应图中 H out 对应图中I
out = self.conv_1x1_4(out) # (shape: (batch_size, num_classes, h/8, w/8))out 对应图中Upsample by 4
return out
感觉有用的文章：用PyTorch搞定GluonCV预训练模型，这个计算机视觉库真的很好用