mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-18 22:04:02 +08:00
Update docs.
This commit is contained in:
1 parent
bed39763a1
commit
35deb34515
17 files changed
+86
-26
No files matched your search
@@ -2,12 +2,12 @@
|
||||
|
||||
We make it easy to benchmark your new NeRF against the standard Blender dataset.
|
||||
|
||||
#### Launching training on Blender
|
||||
#### Launching training on Blender dataset
|
||||
|
||||
To start, you will need to train your NeRF on each of the blender objects.
|
||||
To launch training jobs automatically on each of these items, you can call:
|
||||
|
||||
```
|
||||
```bash
|
||||
./scripts/benchmarking/launch_train_blender.sh <config-name> <list_of_gpus>
|
||||
```
|
||||
|
||||
@@ -17,7 +17,7 @@ Simply replace the arguments in brackets with the correct arguments.
|
||||
|
||||
A full example would be:
|
||||
|
||||
```
|
||||
```bash
|
||||
./scripts/benchmarking/launch_train_blender.sh graph_vanilla_nerf 0 1 2 3
|
||||
```
|
||||
|
||||
@@ -29,7 +29,7 @@ Once you have launched training, and training converges, you can test your metho
|
||||
|
||||
Modify the `BENCH` variable to specify which jobs you want benchmarked.
|
||||
|
||||
```
|
||||
```python
|
||||
BENCH = {
|
||||
"method": "graph_vanilla_nerf", # change this to whatever you want
|
||||
"hydra_base_dir": "outputs/", # change this to wherever hydra's default output directory is
|
||||
@@ -40,7 +40,7 @@ BENCH = {
|
||||
|
||||
Then you can simply run
|
||||
|
||||
```
|
||||
```bash
|
||||
python scripts/benchmarking/run_benchmark.py
|
||||
|
||||
```
|
||||
|
||||
@@ -4,7 +4,7 @@ We provide a few visualization tools with Jupyter that can be found in `notebook
|
||||
|
||||
To install and run any of the notebooks, simply run the following commands:
|
||||
|
||||
```
|
||||
```bash
|
||||
python -m jupyter lab build
|
||||
bash environments/run_jupyter.sh
|
||||
```
|
||||
@@ -3,7 +3,7 @@
|
||||
We provide integration with multiple logging interfaces to log images and statistics during training.
|
||||
All of these loggers are configurable via the config:
|
||||
|
||||
```
|
||||
```yaml
|
||||
# e.g. configs/graphs_default.yaml
|
||||
|
||||
logging:
|
||||
|
||||
@@ -4,7 +4,7 @@ If you are looking to test out other existing repo's with our data, the pyRad st
|
||||
|
||||
For instance, you can run nerf-pytorch and jaxnerf with the following commands:
|
||||
|
||||
```
|
||||
```bash
|
||||
# nerf-pytorch
|
||||
cd external
|
||||
python run_nerf.py --config configs/chair.txt --datadir /path/to/pyrad/data/blender/chair
|
||||
|
||||
@@ -6,7 +6,7 @@ We provide built-in performance profiling capabilities to make it easier for you
|
||||
#### In-house profiler
|
||||
You can use our built-in profiler by enabling the profiler in the config:
|
||||
|
||||
```
|
||||
```yaml
|
||||
# e.g. configs/graphs_default.yaml
|
||||
|
||||
logging:
|
||||
@@ -17,7 +17,7 @@ The profiler computes the average total time of execution for any function with
|
||||
For instance, if you wanted to profile the total time it takes to generate rays given pixel and camera indices via the `RayGenerator` class, you would want to evaluate its `forward()` function. In that class, you would need to add the decorator to the function.
|
||||
|
||||
|
||||
```
|
||||
```python
|
||||
class RayGenerator(nn.Module):
|
||||
|
||||
...
|
||||
@@ -38,13 +38,13 @@ If you want to profile the entire codebase, we provide functionality to generate
|
||||
|
||||
Install PySpy
|
||||
|
||||
```
|
||||
```bash
|
||||
pip install py-spy
|
||||
```
|
||||
|
||||
To perform the profiling, you can either specify that you want to generate a flame graph or generate a live-view of the profiler.
|
||||
|
||||
```
|
||||
```bash
|
||||
## for flame graph
|
||||
|
||||
./scripts/debugging/profile.sh -t flame -o flame.svg -p <python_command>
|
||||
@@ -56,7 +56,7 @@ To perform the profiling, you can either specify that you want to generate a fla
|
||||
|
||||
In both cases, `<python_command>` can be replaced with any command you would normally run in the terminal. For instance, you can replace `<python_function>` with `scripts/run_train.py data/dataset=blender_lego`. Then the full command would be e.g.:
|
||||
|
||||
```
|
||||
```bash
|
||||
./scripts/debugging/profile.sh -t flame -o flame.svg -p scripts/run_train.py data/dataset=blender_lego
|
||||
```
|
||||
|
||||
|
||||
@@ -3,12 +3,12 @@
|
||||
Documentation for running the code with CUDA.
|
||||
Please see https://github.com/NVlabs/tiny-cuda-nn for how to install tiny-cuda-nn.
|
||||
|
||||
```
|
||||
```bash
|
||||
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
|
||||
```
|
||||
|
||||
To run instant-ngp with tcnn, you can do the following. This is with the fox dataset.
|
||||
|
||||
```
|
||||
```bash
|
||||
python scripts/run_train.py --config-name=instant_ngp_tcnn.yaml data/dataset=instant_ngp_fox
|
||||
```
|
||||
Reference in new issue
Block a user