qqlu / Entity

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
Other
692 stars 58 forks source link

Require help with non-existent config key error #1

Closed sharkykittens closed 3 years ago

sharkykittens commented 3 years ago

Hi there, thanks for your work! It looks very interesting and i would like to test it out, however I keep running into the same problem when testing the visualization script and wondering if you could help me out.

Steps I did:

  1. Build detectron2 from source using the same commit version and pytorch version in your README
  2. clone this repo into projects/EntitySeg
  3. Download the pretrained R50.pth model
  4. Install the panopticapi library
  5. Run python3 projects/EntitySeg/demo_result_and_vis.py --config-file projects/EntitySeg/configs/entity_swin_lw7_1x.yaml --input data/input/*.jpg --output data/output MODEL.WEIGHTS data/pretrained_model/R_50.pth MODEL.CONDINST.MASK_BRANCH.USE_MASK_RESCORE "True"

Below is my error: error

Any help is greatly appreciated. Thank you!

qqlu commented 3 years ago

Hi,

I am sorry that I missed this key in the Github code. You can add one line code "cfg.SOLVER.OPTIMIZER = "sgd"" in EntitySeg/entityseg/config.py. I also push it. Please check.

sharkykittens commented 3 years ago

Thanks for the response, you might want to add cfg.TEST.CLASS_AGNOSTIC = True to config.py as well as that was also giving me config errors.

qqlu commented 3 years ago

Thanks very much for helping us checking the code. We have updated it.

sharkykittens commented 3 years ago

visualization script works now. Thanks again for your great work! Closing this issue.