You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Exact command run:
I executed tools/visualize_data and noticed that visualize.py in the utils folder uses an outdated numpy dtype.
Logs or relevant observations:
The image should correspond to train(id: 359), but there is an overflow issue, referencing fly(id: 359-256 = 103) instead.
Expected Behavior:
It should handle classes greater than 256, but Pascal Context 459 results in an overflow.
Environment:
Python 3.10
NumPy 1.22.4
PyTorch 1.13.1
The text was updated successfully, but these errors were encountered:
Steps to Reproduce the Bug:
Full runnable code or changes made:
Refer to the failed pull request: visualizer's sem_seg function dtype uint8 cannot handle classes more than 256! #5391
Exact command run:
I executed
tools/visualize_data
and noticed thatvisualize.py
in theutils
folder uses an outdated numpy dtype.Logs or relevant observations:
The image should correspond to train(id: 359), but there is an overflow issue, referencing fly(id: 359-256 = 103) instead.
Expected Behavior:
It should handle classes greater than 256, but Pascal Context 459 results in an overflow.
Environment:
The text was updated successfully, but these errors were encountered: