Issues with Visualizing Ground Truth Data in Pascal Context

[Faris468]

Run the following command:
bash
Copy code
python tools/visualize_data.py
The script uses visualize.py in the utils folder. The issue lies in the outdated numpy dtype configuration.
Detailed Issue:

The visualization assigns an incorrect class due to overflow:
Expected: train (id: 359)
Result: fly (id: 103) from the calculation 359 - 256 = 103.
The tool fails to handle datasets with more than 256 classes, such as Pascal Context with 459 classes.
Expected Behavior:
The tool should handle datasets with more than 256 classes without encountering overflow issues.

Environment:

Python Version: 3.10
Numpy Version: 1.22.4
Torch Version: 1.13.1
Fix Proposal:
Update the numpy dtype in visualize.py to support a higher class range, such as int32 or a compatible type.
Ensure compatibility with all class ranges in Pascal Context.****

[github-actions]

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template.
The following information is missing: "Instructions To Reproduce the Issue and Full Logs";

[github-actions]

Requested information was not provided in 7 days, so we're closing this issue.

Please open new issue if information becomes available. Otherwise, use github discussions for free-form discussions.