- Enable verbose output in your training options to get more detailed information about each training step.
- Verify that your MATLAB installation is correctly configured to use the GPU. You can use the following command to check the status of your GPU.
trainnet gives training loss is NaN
조회 수: 39 (최근 30일)
이전 댓글 표시
Hello, I'm currently working on semantic segmentation with Unet architecture on matlab. As version R2024a, I tried to train my model with the trainnet command. But after I ran my script, it gives me this result in Command Window.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1732118/image.png)
I tried to change the MiniBatchSize and MaxEpoch but none seem to be working, it seemed like the training never happened because my GPU doesn't seem to have any activity. Does anyone know how to resolve this? Is Matlab R2024a still buggy so this happens?
댓글 수: 0
답변 (4개)
Maneet Kaur Bagga
2024년 7월 11일
Hi Aliya,
I understand that you are encountering an issue where the training loss is "NaN", causing the training to stop.To debug the issue please refer to the following steps:
gpuDevice
Please refer to the the following code snippet to set your training options:
options = trainingOptions('adam', ...
'InitialLearnRate', 1e-4, ...
'MaxEpochs', 50, ...
'MiniBatchSize', 16, ...
'Plots', 'training-progress', ...
'Verbose', true, ...
'ExecutionEnvironment', 'gpu'); % Ensure you specify 'gpu' if you have a compatible GPU
I hope this helps!
댓글 수: 0
Shreeya
2024년 7월 11일
Hey Aliya
I see that you are not able to train your UNET model due to Nan loss. There are a few troubleshooting methods you can try:
- Try to fiddle around with the learning rate on a smaller dataset to ensure if this is or isnt the root cause.
- If the image size is huge, you may need a bigger network to converge the model.
- I also came across an interesting take on teh usage of PNG images for model training. Essentially, PNG image have layers. During training, only the last layer maybe used, and thus the model learns nothing related to the features of rest of the images.
I'm also linking a few threads which you can refer to, apart from these suggestions:
댓글 수: 0
Joss Knight
2024년 7월 11일
편집: Joss Knight
2024년 7월 11일
Do your network weights contain NaNs? Try this
nansInMyNetwork = ~(all(cellfun(@allfinite, net.Learnables.Value)) && all(cellfun(@allfinite, net.State.Value)))
You might also want to check the Variance on any batch normalization layers to make sure none of the values are negative.
댓글 수: 0
Matt J
2024년 8월 6일 2:58
You need to provide more information about what you did, e.g., the training code. However, I can hazard a guess. I imagine problem occurs when you use the 'sgd' training algorithm, but it might not occur if you instead use 'adam'.
댓글 수: 0
참고 항목
카테고리
Help Center 및 File Exchange에서 Image Data Workflows에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!