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

Self weights mobilenet-yolov3 320*320 VOC2007(train_test) #36

Open
Be997398715 opened this issue Apr 1, 2019 · 2 comments
Open

Self weights mobilenet-yolov3 320*320 VOC2007(train_test) #36

Be997398715 opened this issue Apr 1, 2019 · 2 comments

Comments

@Be997398715
Copy link

I have just train a new weights for mobilenet-yolov3 320*320 VOC2007(train_test), everyone wants this could download by https://pan.baidu.com/s/1PAi_UxIcL13mkeU_0i9Pyw
passwd:x3tw . Don't forget share and give a star for me, cause I'm training a squeezenet-yolov3!
The trick I used is consine+adam, epoch=200, batchsize=8(GPU=950M).

@E12dward
Copy link

could you tell me mAP on your dataset?

@diegolitianfu
Copy link

老哥,你训练的loss是多少呀?我一直在17左右下不去,并且测试的效果也不是很好,想知道你都做了哪些改变?以及训练集只用了07的吗还是07+12呀?(consine+adam是你改了优化器吗?)非常感谢!

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