Low training accuracy

Open abhinavkaul95 opened this issue 4 years ago • 3 comments

Hi @rowanz,

I was trying to replicate the training of R2C model at my end. But the training fetches the accuracy of around 24.9% only as opposed to upwards of 60% that we get after training on the best checkpoint available in the README.md file.

The model running is being replicated on 2 GPUs with all the settings set to default. The standard output file is attached as train.txt. Could you please help explain what the issue could be and what can be done to try and get a comparable accuracy? Please let me know if you need any details from my side.

Apr 05 '21 02:04 abhinavkaul95

have you fix it yet,I got the same issue

May 07 '21 01:05 Rita313

Hi @abhinavkaul95, have you solved this problem, please. Can you add a contact information?

Aug 16 '21 02:08 vicky-abr

Hi @abhinavkaul95 @vicky-abr @Rita313 , facing the same problem. Have any of you resolved the issue?

Oct 07 '22 14:10 codefreakSubham