search

facebookresearch / VLPart

[ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation
MIT License
348 stars 16 forks source link

How to parse image level data into part level data #3

Closed ProvenceStar closed 12 months ago

ProvenceStar commented 1 year ago

Hi, I very appreciate your work and I would like to follow your work and apply it to recent tasks, but I wonder how could I visualize these image-level data that were parsed into part-level data, I found out that in configs folder there is another folder named ann_parser which contains the config file to parse data. However, when I use the config file "find_ins_mixer.yaml" it went wrong with "FileNotFoundError: [Errno 2] No such file or directory: 'output_basedata_pascalpart' ", I would like to know that what command should I run and how should I prepare datasets for visualizing those images that were parsed into part-level data, thanks.

PeizeSun commented 1 year ago

Hi~ You need to first run python train_net.py --num-gpus 8 --config-file configs/ann_parser/build_pascalpart.yaml --eval-only to get the directory: 'output_basedata_pascalpart'. The details are in MODEL_ZOO.

ProvenceStar commented 1 year ago

I appreciate your answer, I found out that when I run the code using the command you give, an error occured "Non-existent config key: MODEL.PIXEL_NORM". After I change MODEL.PIXEL_NORM, MODEL.PIXEL_MEAN and MODEL.PIXEL_STD into DINO.PIXEL_NORM, DINO.PIXEL_MEAN and DINO.PIXEL_STD in the config file, it seems work fine. Thank you for your reply!