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

HI! is there a pretrained model ? #2

Open
wqz960 opened this issue Apr 1, 2019 · 5 comments
Open

HI! is there a pretrained model ? #2

wqz960 opened this issue Apr 1, 2019 · 5 comments

Comments

@wqz960
Copy link

wqz960 commented Apr 1, 2019

Thank you for your code, do you test it, can you provide me the pretrained model?

@wqz960
Copy link
Author

wqz960 commented Apr 1, 2019

or can you tell me the training loss in different stage, i just run it and the loss seems to be very low , about 0.03 in the beginning, and drop rapidly to 0.005, is there some bug? i trained on 300WLP. Looking forward for your kind respond!

@xsacha
Copy link

xsacha commented May 20, 2019

Loss values in general don't mean much as long as they go down.

You will also notice accuracy on validation hits 100% in a few epochs.

Probably needs better test set really. I've no idea which epoch is best.

@EdwardChCriollo
Copy link

I have the same doubt, training loss drop to 0.004 and so on, but mi training accuracy stay in 0.0000 on 700 epoch of 8971, what is the reason to obtain these values?, is there any problem?, thanks in advance...

@sxs4337
Copy link

sxs4337 commented Feb 8, 2021

Ping! Any possibility of a pre-trained model?

@AmitSharma1127
Copy link

A pre-trained model would be of huge help

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

5 participants