携手创作，共同成长！这是我参与「掘金日新计划 · 8 月更文挑战」的第23天,点击查看活动详情 >>
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu1(x)
x = self.layer1(x)
x = self.layer2(x)
out3 = self.layer3(x)
out4 = self.layer4(out3)
out5 = self.layer5(out4)
return out3, out4, out5
构建残差块部分
实现代码
#---------------------------------------------------------------------#
# 残差结构
# 利用一个1x1卷积下降通道数，然后利用一个3x3卷积提取特征并且上升通道数
# 最后接上一个残差边
#---------------------------------------------------------------------#
class BasicBlock(nn.Module):
def __init__(self, inplanes, planes):
super(BasicBlock, self).__init__()
# 进行卷积 下采样 标准差 俩层卷积
self.conv1 = nn.Conv2d(inplanes, planes[0], kernel_size=1, stride=1, padding=0, bias=False)
self.bn1 = nn.BatchNorm2d(planes[0])
self.relu1 = nn.LeakyReLU(0.1)
self.conv2 = nn.Conv2d(planes[0], planes[1], kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes[1])
self.relu2 = nn.LeakyReLU(0.1)
def forward(self, x):
# x为残差边
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu1(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu2(out)
# 对残差边进行叠加
out += residual
return out
获取到darknet53主干的三个输出 对三个输出再次进行卷积及上采样操作
#------------------------------------------------------------------------#
# 计算yolo_head的输出通道数，对于voc数据集而言
# final_out_filter0 = final_out_filter1 = final_out_filter2 = 75
#------------------------------------------------------------------------#
self.last_layer0 = make_last_layers([512, 1024], out_filters[-1], len(anchors_mask[0]) * (num_classes + 5))
#对应图中FPN金字塔向上再次卷积及上采样
self.last_layer1_conv = conv2d(512, 256, 1)
self.last_layer1_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.last_layer1 = make_last_layers([256, 512], out_filters[-2] + 256, len(anchors_mask[1]) * (num_classes + 5))
self.last_layer2_conv = conv2d(256, 128, 1)
self.last_layer2_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.last_layer2 = make_last_layers([128, 256], out_filters[-3] + 128, len(anchors_mask[2]) * (num_classes + 5))
make_last_layers中进行七次卷积
对应图中
def make_last_layers(filters_list, in_filters, out_filter):
m = nn.Sequential(
conv2d(in_filters, filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
conv2d(filters_list[1], filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
conv2d(filters_list[1], filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
nn.Conv2d(filters_list[1], out_filter, kernel_size=1, stride=1, padding=0, bias=True)
)
return m
最终得到三个特征层
def forward(self, x):
#---------------------------------------------------#
# 获得三个有效特征层，他们的shape分别是：
# 52,52,256；26,26,512；13,13,1024
#---------------------------------------------------#
x2, x1, x0 = self.backbone(x)
#---------------------------------------------------#
# 第一个特征层
# out0 = (batch_size,255,13,13)
#---------------------------------------------------#
# 13,13,1024 -> 13,13,512 -> 13,13,1024 -> 13,13,512 -> 13,13,1024 -> 13,13,512
out0_branch = self.last_layer0[:5](x0)
out0 = self.last_layer0[5:](out0_branch)
# 13,13,512 -> 13,13,256 -> 26,26,256
x1_in = self.last_layer1_conv(out0_branch)
x1_in = self.last_layer1_upsample(x1_in)
# 26,26,256 + 26,26,512 -> 26,26,768
x1_in = torch.cat([x1_in, x1], 1)
#---------------------------------------------------#
# 第二个特征层
# out1 = (batch_size,255,26,26)
#---------------------------------------------------#
# 26,26,768 -> 26,26,256 -> 26,26,512 -> 26,26,256 -> 26,26,512 -> 26,26,256
out1_branch = self.last_layer1[:5](x1_in)
out1 = self.last_layer1[5:](out1_branch)
# 26,26,256 -> 26,26,128 -> 52,52,128
x2_in = self.last_layer2_conv(out1_branch)
x2_in = self.last_layer2_upsample(x2_in)
# 52,52,128 + 52,52,256 -> 52,52,384
x2_in = torch.cat([x2_in, x2], 1)
#---------------------------------------------------#
# 第一个特征层
# out3 = (batch_size,255,52,52)
#---------------------------------------------------#
# 52,52,384 -> 52,52,128 -> 52,52,256 -> 52,52,128 -> 52,52,256 -> 52,52,128
out2 = self.last_layer2(x2_in)
return out0, out1, out2
