YOLOv5 6.0/6.1结合ASFF(yolov5 教程)

YOLOv5 6.0/6.1结合ASFF

推荐整理分享YOLOv5 6.0/6.1结合ASFF(yolov5 教程)，希望有所帮助，仅作参考，欢迎阅读内容。

文章相关热门搜索词:yolov2结构,yolov2结构,yolov5结构解析,yolov5结构解析,yolov5结构解析,yolov3.cfg,yolov5搭建,yolov5 教程,内容如对您有帮助，希望把文章链接给更多的朋友！

YOLOv5 6.0/6.1结合ASFF

前言

YOLO小白纯干货分享！！！

一、主要修改代码

二、使用步骤1. models/common.py：加入要修改的代码, 类ASFFV5 class ASFFV5(nn.Module): class ASFFV5(nn.Module): def __init__(self, level, multiplier=1, rfb=False, vis=False, act_cfg=True): """ ASFF version for YoloV5 only. Since YoloV5 outputs 3 layer of feature maps with different channels which is different than YoloV3 normally, multiplier should be 1, 0.5 which means, the channel of ASFF can be 512, 256, 128 -> multiplier=1 256, 128, 64 -> multiplier=0.5 For even smaller, you gonna need change code manually. """ super(ASFFV5, self).__init__() self.level = level self.dim = [int(1024*multiplier), int(512*multiplier), int(256*multiplier)] #print("dim:",self.dim) self.inter_dim = self.dim[self.level] if level == 0: self.stride_level_1 = Conv(int(512*multiplier), self.inter_dim, 3, 2) #print(self.dim) self.stride_level_2 = Conv(int(256*multiplier), self.inter_dim, 3, 2) self.expand = Conv(self.inter_dim, int( 1024*multiplier), 3, 1) elif level == 1: self.compress_level_0 = Conv( int(1024*multiplier), self.inter_dim, 1, 1) self.stride_level_2 = Conv( int(256*multiplier), self.inter_dim, 3, 2) self.expand = Conv(self.inter_dim, int(512*multiplier), 3, 1) elif level == 2: self.compress_level_0 = Conv( int(1024*multiplier), self.inter_dim, 1, 1) self.compress_level_1 = Conv( int(512*multiplier), self.inter_dim, 1, 1) self.expand = Conv(self.inter_dim, int( 256*multiplier), 3, 1) # when adding rfb, we use half number of channels to save memory compress_c = 8 if rfb else 16 self.weight_level_0 = Conv( self.inter_dim, compress_c, 1, 1) self.weight_level_1 = Conv( self.inter_dim, compress_c, 1, 1) self.weight_level_2 = Conv( self.inter_dim, compress_c, 1, 1) self.weight_levels = Conv( compress_c*3, 3, 1, 1) self.vis = vis def forward(self, x_level_0, x_level_1, x_level_2): #s,m,l """ # 128, 256, 512 512, 256, 128 from small -> large """ # print('x_level_0: ', x_level_0.shape) # print('x_level_1: ', x_level_1.shape) # print('x_level_2: ', x_level_2.shape) x_level_0=x[2] x_level_1=x[1] x_level_2=x[0] if self.level == 0: level_0_resized = x_level_0 level_1_resized = self.stride_level_1(x_level_1) level_2_downsampled_inter = F.max_pool2d( x_level_2, 3, stride=2, padding=1) level_2_resized = self.stride_level_2(level_2_downsampled_inter) #print('X——level_0: ', level_2_downsampled_inter.shape) elif self.level == 1: level_0_compressed = self.compress_level_0(x_level_0) level_0_resized = F.interpolate( level_0_compressed, scale_factor=2, mode='nearest') level_1_resized = x_level_1 level_2_resized = self.stride_level_2(x_level_2) elif self.level == 2: level_0_compressed = self.compress_level_0(x_level_0) level_0_resized = F.interpolate( level_0_compressed, scale_factor=4, mode='nearest') x_level_1_compressed = self.compress_level_1(x_level_1) level_1_resized = F.interpolate( x_level_1_compressed, scale_factor=2, mode='nearest') level_2_resized = x_level_2 # print('level: {}, l1_resized: {}, l2_resized: {}'.format(self.level, # level_1_resized.shape, level_2_resized.shape)) level_0_weight_v = self.weight_level_0(level_0_resized) level_1_weight_v = self.weight_level_1(level_1_resized) level_2_weight_v = self.weight_level_2(level_2_resized) # print('level_0_weight_v: ', level_0_weight_v.shape) # print('level_1_weight_v: ', level_1_weight_v.shape) # print('level_2_weight_v: ', level_2_weight_v.shape) levels_weight_v = torch.cat( (level_0_weight_v, level_1_weight_v, level_2_weight_v), 1) levels_weight = self.weight_levels(levels_weight_v) levels_weight = F.softmax(levels_weight, dim=1) fused_out_reduced = level_0_resized * levels_weight[:, 0:1, :, :] +\ level_1_resized * levels_weight[:, 1:2, :, :] +\ level_2_resized * levels_weight[:, 2:, :, :] out = self.expand(fused_out_reduced) if self.vis: return out, levels_weight, fused_out_reduced.sum(dim=1) else: return out2. models/yolo.py：添加 类ASFF_Detect

然后在yolo.py 中 Detect 类下面，添加一个ASFF_Detect类

class ASFF_Detect(nn.Module): #add ASFFV5 layer and Rfb stride = None # strides computed during build export = False # onnx export def __init__(self, nc=80, anchors=(), multiplier=0.5,rfb=False,ch=()): # detection layer super(ASFF_Detect, self).__init__() self.nc = nc # number of classes self.no = nc + 5 # number of outputs per anchor self.nl = len(anchors) # number of detection layers self.na = len(anchors[0]) // 2 # number of anchors self.grid = [torch.zeros(1)] * self.nl # init grid self.l0_fusion = ASFFV5(level=0, multiplier=multiplier,rfb=rfb) self.l1_fusion = ASFFV5(level=1, multiplier=multiplier,rfb=rfb) self.l2_fusion = ASFFV5(level=2, multiplier=multiplier,rfb=rfb) a = torch.tensor(anchors).float().view(self.nl, -1, 2) self.register_buffer('anchors', a) # shape(nl,na,2) self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2) self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv

接着在 yolo.py的parse_model 中把函数放到模型的代码里： （大概在283行左右）

if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,CBAM,ResBlock_CBAM, C3]: c1, c2 = ch[f], args[0] if c2 != no: # if not output c2 = make_divisible(c2 * gw, 8) args = [c1, c2, *args[1:]] if m in [BottleneckCSP, C3]: args.insert(2, n) # number of repeats n = 1 elif m is nn.BatchNorm2d: args = [ch[f]] elif m is Concat: c2 = sum([ch[x] for x in f]) elif m is ASFF_Detect: args.append([ch[x] for x in f]) if isinstance(args[1], int): # number of anchors args[1] = [list(range(args[1] * 2))] * len(f) elif m is Contract: c2 = ch[f] * args[0] ** 2 elif m is Expand: c2 = ch[f] // args[0] ** 2 elif m is ASFFV5: c2=args[1] else: c2 = ch[f]3.models/yolov5s-asff.yaml

在models文件夹下新建对应的yolov5s-asff.yaml 文件 然后将yolov5s.yaml的内容复制过来，将 head 部分的最后一行进行修改； 将[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ] 修改成下面：

[[17, 20, 23], 1, ASFF_Detect, [nc, anchors]], # Detect(P3, P4, P5) ]4.查看网络结构

修改 models/yolo.py --cfg models/yolov5s-asff.yaml 接下来run yolo.py 即可查看网络结构

5.将train.py 中 --cfg中的 yaml 文件修改成本文文件即可，开始训练总结

本人在多个数据集上做了大量实验，针对不同的数据集效果不同，需要大家进行实验。有效果有提升的情况占大多数。

最后，希望能互粉一下，做个朋友，一起学习交流。