[pre-commit.ci] pre-commit suggestions (#7279)

* [pre-commit.ci] pre-commit suggestions

updates:
- [github.com/asottile/pyupgrade: v2.31.0 → v2.31.1](https://github.com/asottile/pyupgrade/compare/v2.31.0...v2.31.1)
- [github.com/pre-commit/mirrors-yapf: v0.31.0 → v0.32.0](https://github.com/pre-commit/mirrors-yapf/compare/v0.31.0...v0.32.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update yolo.py

* Update activations.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update activations.py

* Update tf.py

* Update tf.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/activations.py

@@ -8,29 +8,32 @@ import torch.nn as nn
 import torch.nn.functional as F
 
 
-# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
-class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
+class SiLU(nn.Module):
+    # SiLU activation https://arxiv.org/pdf/1606.08415.pdf
     @staticmethod
     def forward(x):
         return x * torch.sigmoid(x)
 
 
-class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
+class Hardswish(nn.Module):
+    # Hard-SiLU activation
     @staticmethod
     def forward(x):
         # return x * F.hardsigmoid(x)  # for TorchScript and CoreML
         return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0  # for TorchScript, CoreML and ONNX
 
 
-# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
 class Mish(nn.Module):
+    # Mish activation https://github.com/digantamisra98/Mish
     @staticmethod
     def forward(x):
         return x * F.softplus(x).tanh()
 
 
 class MemoryEfficientMish(nn.Module):
+    # Mish activation memory-efficient
     class F(torch.autograd.Function):
+
         @staticmethod
         def forward(ctx, x):
             ctx.save_for_backward(x)
@@ -47,8 +50,8 @@ class MemoryEfficientMish(nn.Module):
         return self.F.apply(x)
 
 
-# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
 class FReLU(nn.Module):
+    # FReLU activation https://arxiv.org/abs/2007.11824
     def __init__(self, c1, k=3):  # ch_in, kernel
         super().__init__()
         self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
@@ -58,12 +61,12 @@ class FReLU(nn.Module):
         return torch.max(x, self.bn(self.conv(x)))
 
 
-# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
 class AconC(nn.Module):
-    r""" ACON activation (activate or not).
+    r""" ACON activation (activate or not)
     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>.
     """
+
     def __init__(self, c1):
         super().__init__()
         self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
@@ -76,10 +79,11 @@ class AconC(nn.Module):
 
 
 class MetaAconC(nn.Module):
-    r""" ACON activation (activate or not).
+    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>.
     """
+
     def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
         super().__init__()
         c2 = max(r, c1 // r)