updates

models/common.py

@@ -65,24 +65,6 @@ class BottleneckCSP(nn.Module):
         return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
 
 
-class BottleneckCSPF(nn.Module):
-    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
-        super(BottleneckCSPF, self).__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
-        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
-        self.cv4 = Conv(c2, c2, 1, 1)
-        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
-        self.act = nn.LeakyReLU(0.1, inplace=True)
-        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
-
-    def forward(self, x):
-        y1 = self.cv3(self.m(self.cv1(x)))
-        y2 = self.cv2(x)
-        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
-
-
 class Narrow(nn.Module):
     def __init__(self, c1, c2, shortcut=True, g=1):  # ch_in, ch_out, shortcut, groups
         super(Narrow, self).__init__()

models/yolo.py

@@ -122,7 +122,7 @@ def parse_model(md, ch):  # model_dict, input_channels(3)
                 pass
 
         n = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [nn.Conv2d, Conv, Bottleneck, SPP, DWConv, MixConv2d, Focus, ConvPlus, BottleneckCSP, BottleneckCSPF, BottleneckLight]:
+        if m in [nn.Conv2d, Conv, Bottleneck, SPP, DWConv, MixConv2d, Focus, ConvPlus, BottleneckCSP, BottleneckLight]:
             c1, c2 = ch[f], args[0]
 
             # Normal
@@ -143,8 +143,8 @@ def parse_model(md, ch):  # model_dict, input_channels(3)
             #     c2 = make_divisible(c2, 8) if c2 != no else c2
 
             args = [c1, c2, *args[1:]]
-            if m in [BottleneckCSP, BottleneckCSPF]:
-                args += [n]
+            if m is BottleneckCSP:
+                args.insert(2, n)
                 n = 1
         elif m is nn.BatchNorm2d:
             args = [ch[f]]
@@ -170,7 +170,7 @@ def parse_model(md, ch):  # model_dict, input_channels(3)
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--cfg', type=str, default='yolov5s_csp.yaml', help='model.yaml')
     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
     opt = parser.parse_args()
     opt.cfg = glob.glob('./**/' + opt.cfg, recursive=True)[0]  # find file

models/yolov5s_csp.yaml

@@ -1,46 +0,0 @@
-# parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-
-# anchors
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# yolov5 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Focus, [64, 3]],  # 1-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
-   [-1, 3, BottleneckCSP, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
-   [-1, 9, BottleneckCSP, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
-   [-1, 9, BottleneckCSP, [512]],
-   [-1, 1, Conv, [1024, 3, 2]], # 8-P5/32
-   [-1, 1, SPP, [1024, [5, 9, 13]]],
-   [-1, 3, BottleneckCSP, [1024]],  # 10
-  ]
-
-# yolov5 head
-head:
-  [[-1, 3, Bottleneck, [1024, False]],  # 11
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 12 (P5/32-large)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 3, Bottleneck, [512, False]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 17 (P4/16-medium)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 3, Bottleneck, [256, False]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 22 (P3/8-small)
-
-   [[], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]
-

models/yolov5s_csp1.yaml

@@ -1,46 +0,0 @@
-# parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-
-# anchors
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# yolov5 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Focus, [64, 3]],  # 1-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
-   [-1, 3, BottleneckCSP, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
-   [-1, 9, BottleneckCSP, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
-   [-1, 9, BottleneckCSP, [512]],
-   [-1, 1, Conv, [1024, 3, 2]], # 8-P5/32
-   [-1, 1, SPP, [1024, [5, 9, 13]]],
-   [-1, 6, BottleneckCSP, [1024]],  # 10
-  ]
-
-# yolov5 head
-head:
-  [[-1, 3, Bottleneck, [1024, False]],  # 11
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 12 (P5/32-large)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 3, Bottleneck, [512, False]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 17 (P4/16-medium)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 3, Bottleneck, [256, False]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 22 (P3/8-small)
-
-   [[], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]
-

models/yolov5s_csp2.yaml

@@ -1,46 +0,0 @@
-# parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-
-# anchors
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# yolov5 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Focus, [64, 3]],  # 1-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
-   [-1, 3, BottleneckCSP, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
-   [-1, 9, BottleneckCSP, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
-   [-1, 9, BottleneckCSP, [512]],
-   [-1, 1, Conv, [1024, 3, 2]], # 8-P5/32
-   [-1, 1, SPP, [1024, [5, 9, 13]]],
-   [-1, 6, BottleneckCSP, [1024]],  # 10
-  ]
-
-# yolov5 head
-head:
-  [[-1, 3, BottleneckCSPF, [1024]],  # 11
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 12 (P5/32-large)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 3, BottleneckCSPF, [512]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 17 (P4/16-medium)
-
-   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 3, BottleneckCSPF, [256]],
-   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 22 (P3/8-small)
-
-   [[], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]
-