Code crashes in Mapillary Vistas Semantic Segmentation Task

[johnwlambert]

Hello Codalab, I submitted an entry to the Mapillary Vistas Semantic Segmentation Task Robust Vision @ ECCV 2020, and I get the following "Failed" submission:

WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
Traceback (most recent call last):
  File "/mnt/codalab/tmpsyH6FC/run/program/raster_eval.py", line 17, in evaluate_image_pair
    c = counts.reshape(shape).astype(np.int64)
ValueError: cannot reshape array of size 4226 into shape (65,65)
multiprocessing.pool.RemoteTraceback: 
"""
Traceback (most recent call last):
  File "/usr/lib/python3.8/multiprocessing/pool.py", line 125, in worker
    result = (True, func(*args, **kwds))
  File "/mnt/codalab/tmpsyH6FC/run/program/raster_eval.py", line 17, in evaluate_image_pair
    c = counts.reshape(shape).astype(np.int64)
ValueError: cannot reshape array of size 4226 into shape (65,65)
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/mnt/codalab/tmpsyH6FC/run/program/run.py", line 87, in 
    miou, iou = evaluate(gtDir, resDir)
  File "/mnt/codalab/tmpsyH6FC/run/program/raster_eval.py", line 35, in evaluate
    for i, result in enumerate(results):
  File "/usr/lib/python3.8/multiprocessing/pool.py", line 865, in next
    raise value
ValueError: cannot reshape array of size 4226 into shape (65,65)

It appears that an array of 4225 is expected instead of 4226. All of my input images are of the correct size and have indices in [0,65], as expected. Is this a competition codebase bug?

Thanks, John

[Didayolo]

Hi,

Sorry for the late reply. It might be due to:

• Your submission (not the format required by the competition's code)
• The competition's code (a bug)

Only the competition organizers themselves can work this out. This repository is about the platform itself.

I close the issue because it's old. Feel free to re-open it if needed.