Train and eval data splits (Nerfbusters) (#2207)

* nerfbusters dataparser

* nerfbuster dataparser and visualization of eval views

* resolved some errors from  pyright

* enable ns-process-data to take two videos as input and use one for eval and the other for train

* resolve some pyright issues

* instead of data being a tuple, I added eval_data as another argument

* implemented train eval split for all cases

* implemented train eval split for all cases

* reverting equi changes

* reverting reality capture changes

* raise valueerror

* revert comment

* added split override code back to dataparser

* reverted one change

* using image border now

* adding docs

---------

Co-authored-by: Ethan Weber <eweb0124@gmail.com>
This commit is contained in:
Frederik WarburgandEthan Weber authored and GitHub committed 2023-08-04 10:11:55 -04:00
1 parent 388fcb09e1
commit 9b03299d40
14 files changed
+288 -83

No files matched your search

+4
View File
@@ -46,6 +46,10 @@ ns-process-data {images, video} --data {DATA_PATH} --output-dir {PROCESSED_DATA_
ns-train nerfacto --data {PROCESSED_DATA_DIR}
```
### Training and evaluation on separate data
For `ns-process-data {images, video}`, you can optionally use a separate image directory or video for training and evaluation, as suggested in [Nerfbusters](https://ethanweber.me/nerfbusters/). To do this, run `ns-process-data {images, video} --data {DATA_PATH} --eval-data {EVAL_DATA_PATH} --output-dir {PROCESSED_DATA_DIR}`. Then when running nerfacto, run `ns-train nerfacto --data {PROCESSED_DATA_DIR} nerfstudio-data --eval-mode filename`.
### Installing COLMAP
There are many ways to install COLMAP, unfortunately it can sometimes be a bit finicky. If the following commands do not work, please refer to the [COLMAP installation guide](https://colmap.github.io/install.html) for additional installation methods. COLMAP install issues are common! Feel free to ask for help in on our [Discord](https://discord.gg/uMbNqcraFc).