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

mAP #28

Open
yyx1107 opened this issue Jul 23, 2019 · 3 comments
Open

mAP #28

yyx1107 opened this issue Jul 23, 2019 · 3 comments

Comments

@yyx1107
Copy link

yyx1107 commented Jul 23, 2019

请问大家有测过剪枝之后的map吗,还是只看得precision和recall呀

@liaoyunkun
Copy link

剪枝后的map会下降特别大,从0.4->0.005,只剪枝了20%,有人遇到过吗?

@yyx1107
Copy link
Author

yyx1107 commented Jul 25, 2019

@liaoyunkun 你是按他说的稀疏化训练然后剪枝的吗,你可以再训练一下,提升精度。 我之前在别的上面也剪过一次,边剪边训练map会变好一些,但是没达到之前的精度(你也是做剪枝吗,可以加我交流一下下∩_∩1017176539

@PearlDzzz
Copy link

PearlDzzz commented Jul 26, 2019

@talebolano @yyx1107
我用自己的数据集 训练yolov3模型, 普通训练100epoch的MAP能达到0.9.
利用sparse_train.py训练yolov3模型, 100epoch的MAP只有0.2.
指令: python sparsity_train.py -sr --s 0.0001
alpha用的 是默认值1.

0-20%:0.000020, 20-40%:0.000123, 40-60%:0.008983, 60-80%: 0.032746, 80-100%:0.540597

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

No branches or pull requests

3 participants