423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-12-14 11:26:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Enable mixed frame raysampling

Browse Source 
Summary:
Changed ray_sampler and metrics to be able to use mixed frame raysampling.

Ray_sampler now has a new member which it passes to the pytorch3d raysampler.
If the raybundle is heterogeneous metrics now samples images by padding xys first. This reduces memory consumption.

Reviewed By: bottler, kjchalup

Differential Revision: D39542221

fbshipit-source-id: a6fec23838d3049ae5c2fd2e1f641c46c7c927e3
This commit is contained in:
Darijan Gudelj
2022-10-03 08:36:47 -07:00
committed by Facebook GitHub Bot
parent ad8907d373
commit c311a4cbb9
8 changed files with 102 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
projects/implicitron_trainer/experiment.py
View File

@@ -222,6 +222,7 @@ class Experiment(Configurable): # pyre-ignore: 13
train_loader=train_loader,
val_loader=val_loader,
test_loader=test_loader,
train_dataset=datasets.train,
model=model,
optimizer=optimizer,
scheduler=scheduler,

2
projects/implicitron_trainer/tests/experiment.yaml
View File

@@ -197,6 +197,7 @@ model_factory_ImplicitronModelFactory_args:
n_pts_per_ray_training: 64
n_pts_per_ray_evaluation: 64
n_rays_per_image_sampled_from_mask: 1024
n_rays_total_training: null
stratified_point_sampling_training: true
stratified_point_sampling_evaluation: false
scene_extent: 8.0
@@ -208,6 +209,7 @@ model_factory_ImplicitronModelFactory_args:
n_pts_per_ray_training: 64
n_pts_per_ray_evaluation: 64
n_rays_per_image_sampled_from_mask: 1024
n_rays_total_training: null
stratified_point_sampling_training: true
stratified_point_sampling_evaluation: false
min_depth: 0.1