visualize_reconstruction fixes

Summary: Various fixes to get visualize_reconstruction running, and an interactive test for it.

Reviewed By: kjchalup

Differential Revision: D39286691

fbshipit-source-id: 88735034cc01736b24735bcb024577e6ab7ed336
This commit is contained in:
Jeremy Reizenstein
2022-09-07 20:10:07 -07:00
committed by Facebook GitHub Bot
parent 34ad77b841
commit 6e25fe8cb3
8 changed files with 125 additions and 58 deletions

View File

@@ -66,7 +66,7 @@ If you have a custom `experiment.py` script (as in the Option 2 above), replace
To run training, pass a yaml config file, followed by a list of overridden arguments.
For example, to train NeRF on the first skateboard sequence from CO3D dataset, you can run:
```shell
dataset_args=data_source_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
dataset_args=data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
pytorch3d_implicitron_runner --config-path ./configs/ --config-name repro_singleseq_nerf \
$dataset_args.dataset_root=<DATASET_ROOT> $dataset_args.category='skateboard' \
$dataset_args.test_restrict_sequence_id=0 test_when_finished=True exp_dir=<CHECKPOINT_DIR>
@@ -87,7 +87,7 @@ To run evaluation on the latest checkpoint after (or during) training, simply ad
E.g. for executing the evaluation on the NeRF skateboard sequence, you can run:
```shell
dataset_args=data_source_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
dataset_args=data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
pytorch3d_implicitron_runner --config-path ./configs/ --config-name repro_singleseq_nerf \
$dataset_args.dataset_root=<CO3D_DATASET_ROOT> $dataset_args.category='skateboard' \
$dataset_args.test_restrict_sequence_id=0 exp_dir=<CHECKPOINT_DIR> eval_only=True