Update activations.py

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/activations.py

@@ -7,7 +7,6 @@
 
 
 class SiLU(nn.Module):
-    # SiLU activation https://arxiv.org/pdf/1606.08415.pdf
     @staticmethod
     def forward(x):
         """
@@ -19,7 +18,6 @@ def forward(x):
 
 
 class Hardswish(nn.Module):
-    # Hard-SiLU activation
     @staticmethod
     def forward(x):
         """
@@ -40,7 +38,6 @@ def forward(x):
 
 
 class MemoryEfficientMish(nn.Module):
-    # Mish activation memory-efficient
     class F(torch.autograd.Function):
         @staticmethod
         def forward(ctx, x):
@@ -78,9 +75,9 @@ def forward(self, x):
 
 
 class AconC(nn.Module):
-    r"""ACON activation (activate or not)
+    """ACON activation (activate or not) function.
     AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
-    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
+    See "Activate or Not: Learning Customized Activation" https://arxiv.org/pdf/2009.04759.pdf.
     """
 
     def __init__(self, c1):
@@ -97,9 +94,9 @@ def forward(self, x):
 
 
 class MetaAconC(nn.Module):
-    r"""ACON activation (activate or not)
-    MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
-    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
+    """ACON activation (activate or not) function.
+    AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
+    See "Activate or Not: Learning Customized Activation" https://arxiv.org/pdf/2009.04759.pdf.
     """
 
     def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r