Hi, thanks for this interesting challenge.
When i try to submit a prediction i get the following trace stack, which doesn't really help me figuring things out:
Traceback (most recent call last):
File "/tmp/codalab/tmpnwPwoH/run/program/evaluate.py", line 122, in
pred = png.read_png_int(predict_path)
TypeError: Object does not appear to be a 8-bit string path or a Python file-like object
I submit a zip file, which contains masks for all images with the name xxxx.png and one file "image_classes.json"
Is there any way to get more information what goes wrong with the submission?
Thanks!
Posted by: petillmann @ April 6, 2021, 5:34 p.m.So far I understand, the code did not find the predicted masks there. One reason could be, when you zipped the file it created another layer of folder. For example, if you unzipped the "submit.zip", it should have create only one folder named "submit", not "submit\submit" which is often happened.
Please make sure that the zipping process does not create any extra layer of folder.
Thank you!
Posted by: binalab @ April 6, 2021, 6:17 p.m.I am getting this error
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 "/tmp/codalab/tmp8Z_aZP/run/program/evaluate.py", line 122, in
pred = png.read_png_int(predict_path)
TypeError: Object does not appear to be a 8-bit string path or a Python file-like object
No extra layer of folder present in zip file. Kindly suggest the solution
Posted by: avinash_nesac @ April 26, 2021, 6:14 a.m.Hi Avinash,
i don't really know what the my original issue was but under the following link you can find the code snippet i use to generate my submission of the segmentation part:
https://gist.github.com/P-Tillmann/aa177ea76dd04b1ed2a5eef4e7dc67dc
The model is a pytorch model and i use Nvidia Dali as dataloader which makes for a little weird looking code. I hope this helps you.
Best,
Peter