-
Notifications
You must be signed in to change notification settings - Fork 8
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
Getting very low mIoU using pre-trained weights for DMN #21
Comments
Thanks to the help from @andfoy, I am now able to get the same mIoU numbers as mentioned in Readme using the pre-trained weights. The issue was that I was using the latest version of SRU. On suggestion from @andfoy, I switched to the version of SRU as of this commit. Once I switched to this version, running the below mentioned command gave me the following results. Command Used for evaluating the model
Result of Evaluation(using above command)
As one can see that the above numbers are similar to that provided in the readme file. So using the version of SRU provided in the ReadMe file instead of using the latest version fixed the issue that I was facing and enables me to reproduce the results mentioned in ReadMe. |
…of DMN. BCV-Uniandes/DMS#21 Hence switching to the latest compatiable verison of SRU. However the issue with older version of SRU is that it becomes incompatiable with latest version of pynvtrc. The new version of pynvrtc assumes bytes objects instead of str objects as input to Program(), hence removing the encode calls in cuda_functional to have this older version of SRU also be compatiable with latest version of pynvtrc
@andfoy Great thanks for your timely reply. I followed the instruction to update the SRU to 2.1.3 which already support Prnvrtc 9.2. But my problem is still there. python -u -m dmn_pytorch.train_gai --data referit_data --dataset referit --val val --backend dpn92 --num-filters 10 --lang-layers 3 --mix-we --save-folder weights --snapshot dmn_referit_weights.pth --epochs 0 --eval-first Evaluation done. Elapsed time: 1035.489 (s) I couldn't add --high-res because of out of memory problem, I had nvidia 2080 with 8G memory. I don't know the reason why it's so easy to leak. |
P.S: Dependency: |
Actually, you need to install the SRU version from this commit: pip install -U git+https://github.com/taolei87/sru.git@43c85ed --no-deps
Try reducing the image size of your inputs, using |
Followed your instruction and reinstall sru-0.0.1, remove encode() with 348 line. python -u -m dmn_pytorch.train_gai --data referit_data --dataset referit --val val --backend dpn92 --num-filters 10 --lang-layers 3 --mix-we --save-folder weights --snapshot dmn_referit_weights.pth --epochs 0 --eval-first --high-res Still mIoU around 0.15. @andfoy |
I resize from 512 to 384, it works well. |
Hi,
I am attempting to use the DMN model with the pre-trained weights provided. However, whenever I evaluate the model using the below-mentioned command for UNC dataset using the pre-trained weights downloaded from the link provided in the ReadMe, I get a very low mIoU(close to 0.11).
Pre-trained weights( for unc dataset)
Command Used for evaluating the model
Result of Evaluation(using above command)
I have tried with other datasets also but I am unable to get anywhere close to the performance numbers mentioned in the ReadMe using the pre-trained weights. I am not sure what the issue is here. Below I provide the different versions of packages/libraries I am using.
Dependency Versions
Please note that I am getting low numbers for all datasets and have only provided UNC dataset(and numbers) as an example.
The text was updated successfully, but these errors were encountered: