You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
CITYSCAPES_DATASET=/path/to/abovementioned/cityscapes python cityscapesscripts/preparation/createTrainIdLabelImgs.py
These files are not needed for instance segmentation.
Note: to generate Cityscapes panoptic dataset, run cityscapesescript with:
I have successfully executed above required things. When I try to run >python train_net.py --config-file configs/coco/panoptic-segmentation/fcclip/fcclip_convnext_large_eval_cityscapes.yaml --eval-only MODEL.WEIGHTS FC-CLIP_ConvNeXt-Large/fcclip_cocopan.pth
it's giving me below issue
**backbone.clip_model.{logit_scale, positional_embedding, text_projection}
Traceback (most recent call last):
File "train_net.py", line 340, in
launch(
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/launch.py", line 84, in launch
main_func(*args)
File "train_net.py", line 325, in main
res = Trainer.test(cfg, model)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/defaults.py", line 606, in test
data_loader = cls.build_test_loader(cfg, dataset_name)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/defaults.py", line 562, in build_test_loader
return build_detection_test_loader(cfg, dataset_name)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/config/config.py", line 207, in wrapped
explicit_args = _get_args_from_config(from_config, *args, **kwargs)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/config/config.py", line 245, in _get_args_from_config
ret = from_config_func(*args, kwargs)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 594, in _test_loader_from_config
dataset = get_detection_dataset_dicts(
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 253, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 253, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/catalog.py", line 58, in get
return f()
File "/home/jovyan/shared/fc_clip_vamsi/fc-clip/fcclip/data/datasets/register_cityscapes_panoptic.py", line 186, in
key, lambda x=image_dir, y=gt_dir, z=gt_json: load_cityscapes_panoptic(x, y, z, meta)
File "/home/jovyan/shared/fc_clip_vamsi/fc-clip/fcclip/data/datasets/register_cityscapes_panoptic.py", line 88, in load_cityscapes_panoptic
assert os.path.exists(
AssertionError: Please run python cityscapesscripts/preparation/createPanopticImgs.py to generate label files.
Any help will be appreciated. Thanks!
The text was updated successfully, but these errors were encountered:
Hi @leiyu-bytedance. @cornettoyu, I have generated using below instructions
https://detectron2.readthedocs.io/en/latest/tutorials/builtin_datasets.html
Install cityscapes scripts by:
pip install git+https://github.com/mcordts/cityscapesScripts.git
Note: to create labelTrainIds.png, first prepare the above structure, then run cityscapesescript with:
CITYSCAPES_DATASET=/path/to/abovementioned/cityscapes python cityscapesscripts/preparation/createTrainIdLabelImgs.py
These files are not needed for instance segmentation.
Note: to generate Cityscapes panoptic dataset, run cityscapesescript with:
CITYSCAPES_DATASET=/path/to/abovementioned/cityscapes python cityscapesscripts/preparation/createPanopticImgs.py
I have successfully executed above required things. When I try to run
>python train_net.py --config-file configs/coco/panoptic-segmentation/fcclip/fcclip_convnext_large_eval_cityscapes.yaml --eval-only MODEL.WEIGHTS FC-CLIP_ConvNeXt-Large/fcclip_cocopan.pth
it's giving me below issue
**backbone.clip_model.{logit_scale, positional_embedding, text_projection}
Traceback (most recent call last):
File "train_net.py", line 340, in
launch(
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/launch.py", line 84, in launch
main_func(*args)
File "train_net.py", line 325, in main
res = Trainer.test(cfg, model)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/defaults.py", line 606, in test
data_loader = cls.build_test_loader(cfg, dataset_name)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/engine/defaults.py", line 562, in build_test_loader
return build_detection_test_loader(cfg, dataset_name)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/config/config.py", line 207, in wrapped
explicit_args = _get_args_from_config(from_config, *args, **kwargs)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/config/config.py", line 245, in _get_args_from_config
ret = from_config_func(*args, kwargs)
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 594, in _test_loader_from_config
dataset = get_detection_dataset_dicts(
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 253, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/build.py", line 253, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
File "/home/jovyan/shared/fc_clip_vamsi/detectron2/detectron2/data/catalog.py", line 58, in get
return f()
File "/home/jovyan/shared/fc_clip_vamsi/fc-clip/fcclip/data/datasets/register_cityscapes_panoptic.py", line 186, in
key, lambda x=image_dir, y=gt_dir, z=gt_json: load_cityscapes_panoptic(x, y, z, meta)
File "/home/jovyan/shared/fc_clip_vamsi/fc-clip/fcclip/data/datasets/register_cityscapes_panoptic.py", line 88, in load_cityscapes_panoptic
assert os.path.exists(
AssertionError: Please run
python cityscapesscripts/preparation/createPanopticImgs.py
to generate label files.Any help will be appreciated. Thanks!
The text was updated successfully, but these errors were encountered: