search

lhoyer / improving_segmentation_with_selfsupervised_depth

[CVPR21] Implementation of our work "Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation"
247 stars 30 forks source link

not able to test my images on pretrained models #12

Closed KridaCreations closed 2 years ago

KridaCreations commented 3 years ago

i am getting this error

Start inference2021-11-13_07-43-52-534157 Traceback (most recent call last): File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\inference.py", line 174, in inference_main(cfg) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\inference.py", line 128, in inference_main expand_cfg_vars(cfg) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\train.py", line 929, in expand_cfg_vars expand_cfg_vars(cfg[k]) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\train.py", line 933, in expand_cfg_vars cfg[k] = cfg[k].replace(cfg[k].split("/")[0], getattr(MachineConfig, var_name)) AttributeError: type object 'MachineConfig' has no attribute 'LOG_DIR\inference2021-11-13_07-43-52-534157'

KridaCreations commented 3 years ago

i have solved this error but now iam getting this error:

C:\Users\Abhishek\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\transforms\transforms.py:287: UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum. warnings.warn( Traceback (most recent call last): File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\inference.py", line 175, in inference_main(cfg) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\inference.py", line 138, in inference_main inference = Inference(cfg, logdir, os.path.join(name, str(run_id))) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\inference.py", line 53, in init self.val_loader = build_loader(self.cfg["data"], "val", load_labels=False, load_sequence=False) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\loader__init.py", line 45, in build_loader loader = data_loader( File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\loader\inference_loader.py", line 11, in init super(InferenceLoader, self).init__(**kwargs) File "C:\git_projects\mlproject\improving_segmentation_with_selfsupervised_depth\loader\sequence_segmentation_loader.py", line 114, in init raise RuntimeError(f"Found no segmentation files in {self.images_base}") RuntimeError: Found no segmentation files in \data

i have a folder with sequence of images from a video

lhoyer commented 2 years ago

Based on the given paths, I guess that you use Windows. The project only supports Linux. Probably, the backslashes of Windows paths mess up the path handling in the source code, which assumes that slashes are used.