HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.1.35 simplify network modules (#9321)

Browse source 
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Laughing 2024-03-28 04:28:23 +08:00 • committed by GitHub
parent e84e11724b
commit 3aeb058e82
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

28
ultralytics/nn/modules/block.py
View file

@ -171,10 +171,9 @@ class SPPF(nn.Module):
def forward(self, x):
"""Forward pass through Ghost Convolution block."""
x = self.cv1(x)
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
y = [self.cv1(x)]
y.extend(self.m(y[-1]) for _ in range(3))
return self.cv2(torch.cat(y, 1))
class C1(nn.Module):
@ -555,40 +554,27 @@ class BNContrastiveHead(nn.Module):
return x * self.logit_scale.exp() + self.bias
class RepBottleneck(nn.Module):
class RepBottleneck(Bottleneck):
"""Rep bottleneck."""
def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
"""Initializes a RepBottleneck module with customizable in/out channels, shortcut option, groups and expansion
ratio.
"""
super().__init__()
super().__init__(c1, c2, shortcut, g, k, e)
c_ = int(c2 * e) # hidden channels
self.cv1 = RepConv(c1, c_, k[0], 1)
self.cv2 = Conv(c_, c2, k[1], 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
"""Forward pass through RepBottleneck layer."""
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class RepCSP(nn.Module):
class RepCSP(C3):
"""Rep CSP Bottleneck with 3 convolutions."""
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
"""Initializes RepCSP layer with given channels, repetitions, shortcut, groups and expansion ratio."""
super().__init__()
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)
self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
"""Forward pass through RepCSP layer."""
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
class RepNCSPELAN4(nn.Module):
"""CSP-ELAN."""