tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-14 20:03:49 +08:00
Code Activity

Account for num_gpus rename in docs + test configs (#2332)

Browse Source 
* fix: num-gpus to num-devices

* fix: Update test_config1.yml

* fix: Update test_config2.yml
This commit is contained in:
Kate Yurkova authored and GitHub committed 2023-08-12 11:09:44 +00:00
1 parent 4fe8e657d2
commit 5eb83e8acd
3 files changed
+4 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/quickstart/first_nerf.md
+2 -2
View File
@@ -123,7 +123,7 @@ ns-download-data nerfstudio --capture-name=aspen
```python
# 1 GPU (8192 rays per GPU per batch)
export CUDA_VISIBLE_DEVICES=0
ns-train nerfacto-big --vis viewer+wandb --machine.num-gpus 1 --pipeline.datamanager.train-num-rays-per-batch 4096 --data data/nerfstudio/aspen
ns-train nerfacto-big --vis viewer+wandb --machine.num-devices 1 --pipeline.datamanager.train-num-rays-per-batch 4096 --data data/nerfstudio/aspen
```
You would observe about ~70k rays / sec on NVIDIA V100.
@@ -148,7 +148,7 @@ By having more GPUs in the training, you can allocate batch size to multiple GPU
```python
# 2 GPUs (4096 rays per GPU per batch, effectively 8192 rays per batch)
export CUDA_VISIBLE_DEVICES=0,1
ns-train nerfacto --vis viewer+wandb --machine.num-gpus 2 --pipeline.datamanager.train-num-rays-per-batch 4096 --data data/nerfstudio/aspen
ns-train nerfacto --vis viewer+wandb --machine.num-devices 2 --pipeline.datamanager.train-num-rays-per-batch 4096 --data data/nerfstudio/aspen
```
You would get improved throughput (~100k rays / sec on two NVIDIA V100).