search

facebookresearch / CutLER

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"
Other
913 stars 90 forks source link

maskcut.py; the meaning of arguments #44

Closed lemonbuilder closed 12 months ago

lemonbuilder commented 1 year ago

Thanks for sharing your model. I'm going to train my custom dataset, and make psuedo-masks with MaskCut. Could I know the meaning of each argument that goes into 'maskcut.py'?

cd maskcut

python maskcut.py --vit-arch base #01. --patch-size 8 #02. --tau 0.15 #03. --fixed_size 480 #04. --N 3 #05. --num-folder-per-job 1000 #06. --job-index 0 #07. --dataset-path /path/to/dataset/traindir --out-dir /path/to/save/annotations

01. what is '--vit-arch' ? Are there any options other than 'base'?

02. Is '--patch-size' the correct number of segments for the input-image?

03. what is '--tau' ?

04. what is '--fixed_size' ?

05. '--N' is the number of objects that must be masked in that image, right? Is it a Maximum number??

06. Is 'num-folder-per-job' the number of folders that make up the input-data?

07. what is '--job-index' ?

If you could answer this questions, it would be really helpful to use the CutLer :)

lemonbuilder commented 1 year ago

@frank-xwang

frank-xwang commented 1 year ago

Hi, please refer to this link for explanations pertaining to each argument.