update quickstart + readme (#641)

* updated quickstart and readme

* damn ctrl c on macs
This commit is contained in:
evonneng authored and GitHub committed 2022-10-03 22:38:43 -07:00
1 parent 5c3e1e8bb7
commit 5e56e7b229
7 files changed
+140 -174

No files matched your search

+2 -2
View File
@@ -1,8 +1,8 @@
# Using Custom Data
# Using custom data
Training model on existing datasets is only so fun. If you would like to train on self captured data you will need to process the data into an existing format. Specifically we need to know the camera poses for each image. [COLMAP](https://github.com/colmap/colmap) is a standard tool for extracting poses. It is possible to use other methods like [SLAM](https://en.wikipedia.org/wiki/Simultaneous_localization_and_mapping) or hardware recorded poses. We intend to add documentation for these other methods in the future.
## nerfstudio dataset
## Nerfstudio dataset
To assist running on custom data we have a script that will process a video or folder of images into a format that is compatible with nerfstudio. We use [COLMAP](https://colmap.github.io) and [FFmpeg](https://ffmpeg.org/download.html) in our data processing script, please have these installed. We have provided a quickstart to installing COLMAP below, FFmpeg can be downloaded from [here](https://ffmpeg.org/download.html)
+1 -48
View File
@@ -1,4 +1,4 @@
# Training First Model
# Training your first model
## Downloading data
@@ -64,50 +64,3 @@ ns-render --load-config=outputs/blender_lego/instant_ngp/2022-07-07_230905/confi
```
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.
## FAQ
- [TinyCUDA installation errors out with cuda mismatch](tiny-cuda-error)
- [Installation errors, File "setup.py" not found](pip-install-error)
- [Runtime errors, "len(sources) > 0".](cuda-sources-error)
(tiny-cuda-error)=
#### TinyCUDA installation errors out with cuda mismatch
While installing tiny-cuda, you run into: `The detected CUDA version mismatches the version that was used to compile PyTorch (10.2). Please make sure to use the same CUDA versions.`
**Solution**:
```
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
```
(pip-install-error)=
#### Installation errors, File "setup.py" not found
When installing dependencies and nerfstudio with `pip install -e .`, you run into: `ERROR: File "setup.py" not found. Directory cannot be installed in editable mode`
**Solution**:
This can be fixed by upgrading pip to the latest version:
```
python -m pip install --upgrade pip
```
(cuda-sources-error)=
#### Runtime errors: "len(sources) > 0", "ctype = \_C.ContractionType(type.value) ; TypeError: 'NoneType' object is not callable".
When running `train.py `, an error occurs when installing cuda files in the backend code.
**Solution**:
This is a problem with not being able to detect the correct CUDA version, and can be fixed by updating the CUDA path environment variables:
```
export CUDA_HOME=/usr/local/cuda
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64
export PATH=$PATH:$CUDA_HOME/bin
```
+54 -7
View File
@@ -1,8 +1,8 @@
# Installation
### Create environment
## Create environment
We reccomend using conda to manage dependencies. Make sure to install [Conda](https://docs.conda.io/en/latest/miniconda.html) before preceding.
We recommend using conda to manage dependencies. Make sure to install [Conda](https://docs.conda.io/en/latest/miniconda.html) before preceding.
```bash
conda create --name nerfstudio -y python=3.8.13
@@ -11,7 +11,7 @@ python -m pip install --upgrade pip
```
### Dependencies
## Dependencies
Install pytorch with CUDA (this repo has been tested with CUDA 11.3) and [tiny-cuda-nn](https://github.com/NVlabs/tiny-cuda-nn)
@@ -21,15 +21,15 @@ pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/to
```
### Installing nerfstudio
## Installing nerfstudio
Easy option:
Pip package:
```bash
pip install nerfstudio
```
If you would want the latest and greatest:
If you want the latest and greatest:
```bash
git clone git@github.com:plenoptix/nerfstudio.git
@@ -38,7 +38,7 @@ pip install -e .
```
### Optional Installs
### Optional
#### Tab completion (bash & zsh)
@@ -54,3 +54,50 @@ ns-install-cli
pip install -e.[dev]
pip install -e.[docs]
```
## Installation FAQ
- [TinyCUDA installation errors out with cuda mismatch](tiny-cuda-error)
- [Installation errors, File "setup.py" not found](pip-install-error)
- [Runtime errors, "len(sources) > 0".](cuda-sources-error)
(tiny-cuda-error)=
#### TinyCUDA installation errors out with cuda mismatch
While installing tiny-cuda, you run into: `The detected CUDA version mismatches the version that was used to compile PyTorch (10.2). Please make sure to use the same CUDA versions.`
**Solution**:
```
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
```
(pip-install-error)=
#### Installation errors, File "setup.py" not found
When installing dependencies and nerfstudio with `pip install -e .`, you run into: `ERROR: File "setup.py" not found. Directory cannot be installed in editable mode`
**Solution**:
This can be fixed by upgrading pip to the latest version:
```
python -m pip install --upgrade pip
```
(cuda-sources-error)=
#### Runtime errors: "len(sources) > 0", "ctype = \_C.ContractionType(type.value) ; TypeError: 'NoneType' object is not callable".
When running `train.py `, an error occurs when installing cuda files in the backend code.
**Solution**:
This is a problem with not being able to detect the correct CUDA version, and can be fixed by updating the CUDA path environment variables:
```
export CUDA_HOME=/usr/local/cuda
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64
export PATH=$PATH:$CUDA_HOME/bin
```
+1 -1
View File
@@ -1 +1 @@
# Setting up Viewer
# Setting up viewer