New model.yaml activation: field (#9371)

* New model.yaml `activation:` field

Add optional model yaml activation field to define model-wide activations, i.e.:

```yaml
activation: nn.LeakyReLU(0.1)  # activation with arguments
activation: nn.SiLU()  # activation with no arguments
```

Signed-off-by: Glenn Jocher <[email protected]>

* Update yolo.py

Signed-off-by: Glenn Jocher <[email protected]>

* Add example models

* l to m models

* update

* Add yolov5s-LeakyReLU.yaml

* Update yolov5s-LeakyReLU.yaml

Signed-off-by: Glenn Jocher <[email protected]>

Signed-off-by: Glenn Jocher <[email protected]>

Author: glenn-jocher

models/common.py

@@ -39,11 +39,13 @@ def autopad(k, p=None, d=1):  # kernel, padding, dilation
 
 class Conv(nn.Module):
     # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
+    act = nn.SiLU()  # default activation
+
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
         super().__init__()
         self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
         self.bn = nn.BatchNorm2d(c2)
-        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+        self.act = self.act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
 
     def forward(self, x):
         return self.act(self.bn(self.conv(x)))
@@ -54,8 +56,8 @@ def forward_fuse(self, x):
 
 class DWConv(Conv):
     # Depth-wise convolution
-    def __init__(self, c1, c2, k=1, s=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
 
 
 class DWConvTranspose2d(nn.ConvTranspose2d):

models/hub/yolov5s-LeakyReLU.yaml

@@ -0,0 +1,49 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+activation: nn.LeakyReLU(0.1)  # <----- Conv() activation used throughout entire YOLOv5 model
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+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 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolo.py

@@ -297,8 +297,12 @@ def _from_yaml(self, cfg):
 
 
 def parse_model(d, ch):  # model_dict, input_channels(3)
+    # Parse a YOLOv5 model.yaml dictionary
     LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
-    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
+    if act:
+        Conv.act = eval(act)  # redefine default activation, i.e. Conv.act = nn.SiLU()
+        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
     na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
     no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)