-
Notifications
You must be signed in to change notification settings - Fork 48
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
Would you like to ask why the training result is nan #26
Comments
Hi, I tested the code again but wasn't able to reproduce this issue. Are all the package requirements satisfied? |
Indeed, the package versions are the same as the ones I tested the code with. Could it be that this issue is relevant for you? |
Well, I don't know. I'll try again. Thank you. |
I had the same problem with RTX4090 and this helps a lot! |
Hi there! |
same nan. using cpu with the same speed with gpu. |
same nun problem. Just delete the model you trained first. And It will be solve. |
What do you mean by deleting the model I trained first? |
nan |
seams like still bugs |
I use only 100 pictures in this three:1.415068 Then I delete all the .result and weight and start the traning again and here is the output: Epoch 01/20 [====================] 100/100 (ETA: 0:00:00) |
No code changes have been made, and the version of the library is compliant
![image](https://user-images.githubusercontent.com/54981416/199186495-9932bce3-0a8f-4976-a09a-ab0ac0aa89be.png)
![image](https://user-images.githubusercontent.com/54981416/199186949-6ce94312-b8bc-4ee9-a224-f9881c45e8f7.png)
This is the result of my training
Only the first picture was correct when the 10 pictures were tested
Thanks to reassure!
The text was updated successfully, but these errors were encountered: