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

Error when running python main_fast_single_object.py #1

Open
angelsb008 opened this issue Jul 25, 2024 · 1 comment
Open

Error when running python main_fast_single_object.py #1

angelsb008 opened this issue Jul 25, 2024 · 1 comment

Comments

@angelsb008
Copy link

Hello! I have a trouble, when I tried run python main_fast_single_object.py with the default config, appear the next issue:

Generating masks for input video 100%|███████████████████████████████████████████████████████████████████████████████████| 53/53 [00:02<00:00, 19.18it/s] Running test-time adaptation to enhance flow-predicted masks Traceback (most recent call last): File "/home/angel/ev_deep_motion_segmentation/dino/eval_adaptation.py", line 31, in <module> import vision_transformer as vits File "/home/angel/ev_deep_motion_segmentation/dino/vision_transformer.py", line 24, in <module> from .utils import trunc_normal_ ImportError: attempted relative import with no known parent package Execution time for DMR: 1048.8221645355225 ms Overlay test-time adaptation masks on original images 98%|█████████████████████████████████████████████████████████████████████████████████▍ | 52/53 [00:02<00:00, 19.68it/s] Traceback (most recent call last): File "/home/angel/ev_deep_motion_segmentation/main_fast_single_object.py", line 279, in <module> input_image = Image.open(input_image_path) File "/home/angel/miniconda3/envs/ev_motion_segmentation/lib/python3.9/site-packages/PIL/Image.py", line 3431, in open fp = builtins.open(filename, "rb") FileNotFoundError: [Errno 2] No such file or directory: '/home/angel/ev_deep_motion_segmentation/output/EED_what_is_background/input_frames/EED_what_is_background_test_time_adapt.gif'

I tried fixed it, but I can't. This issue only happens with the default dataset: EED_what_is_background_events.es, because I can't run the main.py with another dataset.
Also, how can I see the content of '.es' file?

I hope you can help me.

Thanks!

@samiarja
Copy link
Owner

Apologies for the late response. I just saw your issue.

I tested the script, and it runs smoothly on my end without any errors. It appears that your code is trying to access the file "input_frames/EED_what_is_background_test_time_adapt.gif" from the wrong directory, which shouldn't happen. This GIF file should be saved in the "tt_adapt" folder instead of "input_frames".

If you have moved any files within "output/EED_what_is_background", the simplest fix is to delete this folder and re-run the code. Alternatively, if you have modified any directories within the code, please refer back to the original implementation.

To view the contents of a .es file, you can access the event coordinates, polarities, and timestamps using the read_es_file function as follows:
width, height, events = event_warping.read_es_file(f"./Dataset/{data}/{data}_{seq}_events.es")

Hope this helps

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