Simpler code for DWConvClass (#4310)

* more simpler code for DWConvClass

more simpler code for DWConvClass

* remove DWConv function

* Replace DWConvClass with DWConv

models/common.py

@@ -29,11 +29,6 @@ def autopad(k, p=None):  # kernel, padding
     return p
 
 
-def DWConv(c1, c2, k=1, s=1, act=True):
-    # Depth-wise convolution function
-    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
-
-
 class Conv(nn.Module):
     # Standard convolution
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
@@ -49,11 +44,10 @@ class Conv(nn.Module):
         return self.act(self.conv(x))
 
 
-class DWConvClass(Conv):
+class DWConv(Conv):
     # Depth-wise convolution class
     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, act)
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
-        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k), groups=math.gcd(c1, c2), bias=False)
 
 
 class TransformerLayer(nn.Module):

models/yolo.py

@@ -202,7 +202,7 @@ class Model(nn.Module):
     def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
         LOGGER.info('Fusing layers... ')
         for m in self.model.modules():
-            if isinstance(m, (Conv, DWConvClass)) and hasattr(m, 'bn'):
+            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
                 m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                 delattr(m, 'bn')  # remove batchnorm
                 m.forward = m.forward_fuse  # update forward