zsseg.baseline icon indicating copy to clipboard operation
zsseg.baseline copied to clipboard

Zero-Shot Semantic Segmentation

Results 11 zsseg.baseline issues
Sort by recently updated
recently updated
newest added

Was there the command of Data Preparetion for Pascal VOC 11k a error? ``` python datasets/prepare_voc_sem_seg.py datasets/VOC2012 python tools/mask_cls_collect.py datasets/VOC2012/annotations_detectron2/train datasets/VOC2012/annotations_detectron2/train_base_label_count.json ``` should be ``` python datasets/prepare_voc_sem_seg.py datasets/VOC2012 python tools/mask_cls_collect.py...

I am a bit confused as to how the VOC2012 dataset should be prepared for this model. The instruction says that the file structure should be like this: ![Capture](https://user-images.githubusercontent.com/55648131/182659352-79792ba0-bb8d-4e51-bf0d-323030d31d6c.PNG) I...

Thanks for the fantastic paper and codebase! I ran the manual prompts experiment `python train_net.py --config-file configs/coco-stuff-164k-156/zero_shot_maskformer_R101c_single_prompt_bs32_60k.yaml` and wanted to know how did you guys visualize your results? It will...

Thanks for your great work and released code. I wonder if you can release the pretrained model so that we can evaluate the generalization ability on custom datasets.

Hi there, Thanks for sharing this good work! When I am trying to run learned prompt on the Pascal VOC dataset. I use the config file : voc-11k-15/zero_shot_proposal_classification_learn_prompt_bs16_10k.yaml. In this...

[03/07 13:50:19 fvcore.common.checkpoint]: [Checkpointer] Loading from detectron2://DeepLab/R-103.pkl ... R-103.pkl: 0.00B [00:00, ?B/s] This case seems keeping unchanged? How to manage it?

Thank you for your amazing work and contribution to the field. Is there an easy way to fine-tune the provided pre-weight model on Cityscapes? Do you have a config file...

`for dir_name in [ "train2017", "test2017", "train2017_base", "train2017_novel", "val2017_base", "val2017_novel", ]:` should be `for dir_name in [ "train2017", "val2017", "train2017_base", "train2017_novel", "val2017_base", "val2017_novel", ]:`

Thank you for your excellent work. But I have one question about evaluation. When I run evaluation on COCO dataset for zero-shot setting, I found that if I set the...

Hi zsseg team, I'm trying to run the experiment. I downloaded the cityscapes, ade20k and pcontext. I am stuck with coco datasets where I am unable to proceed to next...