Skip to content
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

FileNotFoundError: [Errno 2] No such file or directory: 'tmp_result_0.pkl' and IndexError: list index out of range #53

Open
metehkaya opened this issue Apr 24, 2022 · 3 comments

Comments

@metehkaya
Copy link

metehkaya commented Apr 24, 2022

I am facing 2 errors like here and here when I want to test the pre-trained model on name_of_input_pose.json you provided.

I put the trained model under output/model_dump/COCO, images from 2017 Test images under data/COCO/images/test2017, COCO annotation 2017 Testing Image info under data/COCO/annotations. Also, made the changes in data/COCO/dataset.py regarding input_pose_path and main/config.py about testset and dataset as you explained at this issue.

The tensorflow version is not stated in requirements.txt, therefore I tried with tf 1.9, 1.10 and 1.11. Also tried both python test.py --gpu 0-1 --test_epoch 140 and python test.py --gpu 0 --test_epoch 140. Unfortunately, I could not make it work.

Any suggestions?

@mks0601
Copy link
Owner

mks0601 commented Apr 25, 2022

Did you prepare bbox correctly?

@metehkaya
Copy link
Author

metehkaya commented Apr 25, 2022

No, I did not touch bbox attributes.

Btw, I switched to another data you mentioned here and which does not have bbox attribute. Since the name contains 256x192, I also changed input_shape at main/config.py but I faced the same errors.

@mks0601
Copy link
Owner

mks0601 commented Apr 26, 2022

Sorry it has been few years since I wrote this code, so it is hard for me to get the reason quickly. Please make sure at here whether you load the annot and input_pose correctly.

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

No branches or pull requests

2 participants