mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-20 06:35:36 +08:00
split scripts into 2 eval/render (#637)
* done splitting script * udpate docs * woops forgot to add function * update camera panel command
This commit is contained in:
1 parent
2de5afae0c
commit
5c3e1e8bb7
8 files changed
+250
-196
No files matched your search
@@ -47,7 +47,7 @@ ns-train nerfacto --vis viewer --viewer.zmq-port 8001 --viewer.websocket-port 80
|
||||
|
||||
## Visualizing training runs
|
||||
|
||||
If you using a fast NeRF variant (ie. Instant-NGP), we reccomend using our viewer. See our [viewer docs](viewer_quickstart.md) for more details. The viewer will allow interactive visualization of training in realtime.
|
||||
If you are using a fast NeRF variant (ie. Instant-NGP), we recommend using our viewer. See our [viewer docs](viewer_quickstart.md) for more details. The viewer will allow interactive visualization of training in realtime.
|
||||
|
||||
Additionally, if you run everything with the default configuration, by default, we use [TensorBoard](https://www.tensorflow.org/tensorboard) to log all training curves, test images, and other stats. Once the job is launched, you will be able to track training by launching the tensorboard in `outputs/blender_lego/vanilla_nerf/<timestamp>/<events.tfevents>`.
|
||||
|
||||
@@ -60,7 +60,7 @@ tensorboard --logdir outputs
|
||||
To evaluate the trained NeRF, we provide an evaluation script that allows you to do benchmarking (see our [benchmarking workflow](../developer_guides/benchmarking.md)) or to render out the scene with a custom trajectory and save the output to a video.
|
||||
|
||||
```bash
|
||||
ns-eval render-trajectory --load-config=outputs/blender_lego/instant_ngp/2022-07-07_230905/config.yml --traj=spiral --output-path=output.mp4
|
||||
ns-render --load-config=outputs/blender_lego/instant_ngp/2022-07-07_230905/config.yml --traj=spiral --output-path=output.mp4
|
||||
```
|
||||
|
||||
Please note, this quickstart allows you to preform everything in a headless manner. We also provide a web-based viewer that allows you to easily monitor training or render out trajectories. See our [viewer docs](viewer_quickstart.md) for more.
|
||||
|
||||
Reference in new issue
Block a user