Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ResNet-50 训练 #222

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

ResNet-50 训练 #222

wants to merge 8 commits into from

Conversation

triple-Mu
Copy link
Contributor

@triple-Mu triple-Mu commented May 10, 2022

ResNet-50 训练

参照当前 vision 下的 project 复现 resnet-50 训练和精度对齐。

参考

主要目标

  • 2022.05.11 - 2022.5.12:熟悉 vision 下的分类模型训练代码,数据集配置并跑通。
  • 2022.05.12 - 2022.05.20:对照 timm 和 pytorch 复现 reset-50 训练代码,对齐相关训练条件,测试并使用多卡训练。
  • 2022.05.21 - 2022.05.27:对比精度差异调整并复现精度,最终将训练好的权重替换为 oneflow 版本。

项目负责人:林松
预计完成时间:2022.05.27

相关 PR

罗列对应的 PR,以为一个 issue 可能会对应多个 PR,所以这里提供的是表格

PR 作者 reviewer 日期
首次上传提交代码 林松 zzzzzzz 20220510

@@ -40,7 +40,7 @@
# -----------------------------------------------------------------------------
_C.MODEL = CN()
# Model arch
_C.MODEL.ARCH = "swin_tiny_patch4_window7_224"
_C.MODEL.ARCH = "resnet50"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

可以通过外部的.yaml的config来覆盖这里的config, 我记得在/configs文件夹下有相关的参考

_C.TRAIN.OPTIMIZER.BETAS = (0.9, 0.999)
_C.TRAIN.OPTIMIZER.NAME = "sgd"
# # Optimizer Epsilon
# _C.TRAIN.OPTIMIZER.EPS = 1e-8
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这部分不用注释,可以仔细看一下optimizer.py里的build_optimizer函数, 里面会进行一些判断

@@ -110,12 +112,22 @@
_C.AUG.REPROB = 0.25
# Random erase mode
_C.AUG.REMODE = "pixel"
# Scale
_C.AUG.SCALE = [0.08, 1.0]
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这些部分建议还是用外部的.yaml进行覆盖

� Conflicts:
�	docs/source/flowvision.layers.rst
�	flowvision/layers/attention/se.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants