Validation after inference: integrate to dev branch and fix

[remtav]

Validation script in production is failing

[�[36m2023-01-18 14:32:59,997�[0m][�[34mroot�[0m][�[32mINFO�[0m] - 
Overwritten parameters in the config: 
inference.checkpoint_dir=[...]/operationalization/checkpoints/,inference.input_stac_item=https://datacube-stage.services.geo.ca/api/collections/worldview-2-ortho-pansharp/items/ON17-052934190130_01_P001-WV02,inference.output_name=ON17-052934190130_01_P001-WV02_ROAI,inference.state_dict_path=https://datacube-[...]/models/pl_VA_95imgs_RGBN_ROAI_20220925.pth.tar,mode=validate,postprocess.output_name=ON17-052934190130_01_P001-WV02,postprocess.reg_cont.cont_image=[...]/singularity_images/gdl-cuda11_v2.3.3-prod.sif,postprocess.root_dir=[...]operationalization/inferences/�[0m
[�[36m2023-01-18 14:32:59,998�[0m][�[34mroot�[0m][�[32mINFO�[0m] - 
-----------------------------------------
Let's start validate for segmentation !!!
-----------------------------------------�[0m
[�[36m2023-01-18 14:33:00,812�[0m][�[34mroot�[0m][�[32mINFO�[0m] - 
Provided path is url. Cannot validate it's existence nor convert to Path object. Got:
https://datacube-[...]/models/pl_VA_95imgs_RGBN_ROAI_20220925.pth.tar�[0m
[�[36m2023-01-18 14:33:00,825�[0m][�[34mroot�[0m][�[32mINFO�[0m] - 
=> checking model compatibility...�[0m
Error executing job with overrides: ['mode=validate', 'inference.input_stac_item=https://datacube-stage[...]/worldview-2-ortho-pansharp/items/ON17-052934190130_01_P001-WV02', 'inference.state_dict_path=https://datacube-stage-[...]/models/pl_VA_95imgs_RGBN_ROAI_20220925.pth.tar', 'postprocess.output_name=ON17-052934190130_01_P001-WV02', 'inference.output_name=ON17-052934190130_01_P001-WV02_ROAI', 'inference.checkpoint_dir=[...]operationalization/checkpoints/', 'postprocess.root_dir=[...]operationalization/inferences/', 'postprocess.reg_cont.cont_image=[...]singularity_images/gdl-cuda11_v2.3.3-prod.sif']
Traceback (most recent call last):
  File "[...]/operationalization/geo-deep-learning/GDL.py", line 71, in run_gdl
    task(cfg)
  File "[...]/operationalization/geo-deep-learning/validate_segmentation.py", line 53, in main
    if not ckpt_is_compatible(checkpoint):
  File "[...]/operationalization/geo-deep-learning/utils/utils.py", line 718, in ckpt_is_compatible
    checkpoint = load_state_dict_from_url(url=in_ckpt_path, map_location='cpu', model_dir=to_absolute_path(download_dir))
  File "[...]geo_deep_env_prod_submitit/lib/python3.9/site-packages/hydra/utils.py", line 68, in to_absolute_path
    p = Path(path)
  File "[...]geo_deep_env_prod_submitit/lib/python3.9/pathlib.py", line 1082, in __new__
    self = cls._from_parts(args, init=False)
  File "[...]geo_deep_env_prod_submitit/lib/python3.9/pathlib.py", line 707, in _from_parts
    drv, root, parts = self._parse_args(args)
  File "[...]geo_deep_env_prod_submitit/lib/python3.9/pathlib.py", line 691, in _parse_args
    a = os.fspath(a)
TypeError: expected str, bytes or os.PathLike object, not NoneType

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.