Skip to content
This repository has been archived by the owner on Jan 25, 2024. It is now read-only.

Can you tell me the reason for randomness? #30

Open
noparkee opened this issue Jul 3, 2022 · 4 comments
Open

Can you tell me the reason for randomness? #30

noparkee opened this issue Jul 3, 2022 · 4 comments

Comments

@noparkee
Copy link

noparkee commented Jul 3, 2022

Hello, Thanks for your nice project.

I tried to train the model several times without code editing, then I found that the difference in performance of each trial was quite large.
There is no big difference when testing multiple times with one checkpoint, so randomness seems to occur during the learning process.
Do you have any idea what could be the reason?

Thank you!

@FUTUREEEEEE
Copy link

i think the randomness is caused by the usage of nondeterministic-algorithms , which means even you set all the random seed ,the result will still have some randomness. check it out by add torch.use_deterministic_algorithms(True) into the main function .

@FUTUREEEEEE
Copy link

Hello, Thanks for your nice project.

I tried to train the model several times without code editing, then I found that the difference in performance of each trial was quite large. There is no big difference when testing multiple times with one checkpoint, so randomness seems to occur during the learning process. Do you have any idea what could be the reason?

Thank you!

btw,have you try to submit the test result to eval AI ? how is the outcome? i try to submit it result using the pretrained model provided by the author and my own training result , it turns out very bad....

@noparkee
Copy link
Author

Thank you for you answer. I'll check it later.
I didn't submit the evaluation, just checked the validation result. I am sorry for not being helpful 😅

@huanmanlou
Copy link

Hello, Thanks for your nice project.
I tried to train the model several times without code editing, then I found that the difference in performance of each trial was quite large. There is no big difference when testing multiple times with one checkpoint, so randomness seems to occur during the learning process. Do you have any idea what could be the reason?
Thank you!

btw,have you try to submit the test result to eval AI ? how is the outcome? i try to submit it result using the pretrained model provided by the author and my own training result , it turns out very bad....

I recently obtained the h5 file using the pretrained model provided by the author, but the results are much worse than what the author described in the paper. Do you know the reason? Thank you

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants