AttributeError: 'NoneType' object has no attribute 'exists'
SSXXSSXX opened this issue · comments
I have generated training partitions for each submodule and am now ready to train each submodule. My training command is as follows:
Python mega nerf/train. py -- config_file configs/mega nerf/quad. yaml -- expname exp1-- dataset_path CAMERA-POSE/quad pixsfm -- chunk_paths log1-- cluster_mask_path output/0
The following issues were encountered while running the command:
Traceback (most recent call last):
File "/home/ss/mega-nerf-main/mega_nerf/train.py", line 28, in
main(_get_train_opts())
File "/home/ss/anaconda3/envs/mega-nerf/lib/python3.9/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 345, in wrapper
return f(*args, **kwargs)
File "/home/ss/mega-nerf-main/mega_nerf/train.py", line 24, in main
Runner(hparams).train()
File "/home/ss/mega-nerf-main/mega_nerf/runner.py", line 107, in init
self.train_items, self.val_items = self._get_image_metadata()
File "/home/ss/mega-nerf-main/mega_nerf/runner.py", line 628, in _get_image_metadata
train_items = [
File "/home/ss/mega-nerf-main/mega_nerf/runner.py", line 629, in
self._get_metadata_item(x, image_indices[x.name], self.hparams.train_scale_factor, x in val_paths_set) for x
File "/home/ss/mega-nerf-main/mega_nerf/runner.py", line 645, in _get_metadata_item
assert image_path.exists()
AttributeError: 'NoneType' object has no attribute 'exists'