image size predicted mask on FBMS

[fyangneil]

The provided FBMS results is not consistent with the ground truth image in terms of image size. For example, the results image of the first frame of cars 10 is 384 192 but the corresponding ground truth image size is 640480.

[antonilo]

dear @fyangneil,

there are several re-shaping operations in post-processing to make sure that the image resolution is as expected. I would encourage you to check out the readme for details.

[fyangneil]

@antonilo do you have the test script for FBMS dataset?

[fyangneil]

@antonilo I use the provided model and test it on FBMS test dataset, the result is 0.498. The script I used is test_DAVIS2016_raw.sh with corresponding modification for FBMS dataset. I also tried the post processing code but the result is not good, either. I am not sure what the problem is?

[antonilo]

please follow the instructions and make sure to reproduce the same results as in here http://rpg.ifi.uzh.ch/data/detection_results.zip

[fyangneil]

By using the provided detection results, I can get the reported number on DAVIS dataset. Have not check the results on the other two datasets.

…

________________________________ From: Antonio Loquercio <notifications@github.com> Sent: Saturday, February 6, 2021 1:56 PM To: antonilo/unsupervised_detection <unsupervised_detection@noreply.github.com> Cc: Fan Yang <fyang@temple.edu>; Mention <mention@noreply.github.com> Subject: [External] Re: [antonilo/unsupervised_detection] image size predicted mask on FBMS (#18) please follow the instructions and make sure to reproduce the same results as in here http://rpg.ifi.uzh.ch/data/detection_results.zip — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#18 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ALAUWTXQ4BKWFLFIUQL5WG3S5WGFFANCNFSM4ULNDYVA>.