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

ultralytics 8.0.111 refactored model.loss() method (#2911)

Browse source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Snyk bot <snyk-bot@snyk.io>
This commit is contained in:
Glenn Jocher 2023-05-30 20:23:30 +02:00 • committed by GitHub
parent 305cde69d0
commit fd94d312da
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
14 changed files with 46 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ultralytics/nn/modules/conv.py
View file

@ -9,9 +9,8 @@ import numpy as np
import torch
import torch.nn as nn
__all__ = [
'Conv', 'LightConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus', 'GhostConv', 'ChannelAttention',
'SpatialAttention', 'CBAM', 'Concat', 'RepConv']
__all__ = ('Conv', 'LightConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus', 'GhostConv',
'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'RepConv')
def autopad(k, p=None, d=1): # kernel, padding, dilation