423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2026-02-26 08:06:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Move load_stats to TrainingLoop

Browse Source 
Summary:
Stats are logically connected to the training loop, not to the model. Hence, moving to the training loop.

Also removing resume_epoch from OptimizerFactory in favor of a single place - ModelFactory. This removes the need for config consistency checks etc.

Reviewed By: kjchalup

Differential Revision: D38313475

fbshipit-source-id: a1d188a63e28459df381ff98ad8acdcdb14887b7
This commit is contained in:
David Novotny
2022-08-02 15:40:53 -07:00
committed by Facebook GitHub Bot
parent 760305e044
commit c3f8dad55c
11 changed files with 259 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
projects/implicitron_trainer/visualize_reconstruction.py
View File

@@ -344,7 +344,7 @@ def export_scenes(
# Load the previously trained model
experiment = Experiment(config)
model = experiment.model_factory(force_load=True, load_model_only=True)
model = experiment.model_factory(force_resume=True)
model.cuda()
model.eval()