Making TrainerConfig an InstantiateConfig so it can be swapped in and out with different methods. Also made the TrainerConfig a subclass of ExperimentConfig (which was changed from a printableconfig to an instantiateconfig), since we were already instantiating the Trainer class with the ExperimentConfig
Removed the "config" field from the TrainerCallbackAttributes struct to eliminate circular dependencies when types are checked.
Minor scripts and docs changes to accommodate the update to the config struct, meaning the flags that were associated with the TrainerConfig were moved up to the top level of the config.
* Added Dockerfile to build docker image including all dependencies and nerfstudio, added description on how to user docker.
* Move docker description to Installation.md.
* Fix mask_filename indices after splitting train set.
* Rebase DOckerfile to newer image for updated libraries.
* Update docker container documentation.
Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
* basic support for hloc (includes netvlad, super point, superglue in colmap), just a first test, not ready yet
* add exhaustive match option for hloc
* add command line option to choose the type of feature, matcher,...
* make hloc an optional dependency, update doc, and small bug fixes
* fix missing imports
* fix warnings, pylint,...
* fix overwrite previous commits
* fix import order from isort
* move find_tool_feature_matcher_combination to process_data_utils, add type hints and Args/Returns doc
* error message when no valid combination of sfm tool, feature type, and matcher
Co-authored-by: RandomPrototypes <delmotte_ar@yahoo.fr>
* start of mesh PR
* point cloud export mvp
* start of mesh PR
* point cloud export mvp
* Save out mesh. Poor quality atm
* reorganized mesh algorithms and specified CLI
* CLI reorg
* tsdf algorithm in progress
* debugging
* tsdf functional but camera distortion params not in
* playing with distortion params
* TSDF works but texture looks bad
* added trimesh
* moved to exporter
* removed files
* saving progress
* save texture image
* seems to work w/o barycentric
* barycentric start
* gap between triangles
* blocking out diagonal
* new barcentric and scaling
* meshing working. need to remove extra rows
* fixed triangle packing
* gitignore changes
* removed package
* fix Literal import
* comments
* update .mtl file
* poisson mesh with model output normals & resolved some PR comments on git
* starting docs. breaking up big function. todo: add xatlas
* xatlas and nvdiffrast working
* triangle_id
* progress on expensive texture coordinates method
* pytorch meshing works
* removing nvdiffrast
* remove trimesh
* cleanup
* few changes
* pred normals by default and add minimum additions to viewer
* fix cli in viewer
* add xatlas as dependency
* make point cloud more dense
* reverted viewer changes
* turn off normals by default
* fix docs
* finished todos on github
* remove xatlas
* xatlas
* black
Co-authored-by: Matt Tancik <tancik@berkeley.edu>
* launch_eval_blender.sh: fix script
- add shebang
- add -s option to launch a single job per GPU
- last GPU was ignored
- kill all subprocesses when script is terminated
* launch_train_blender.sh: fix script
- add -s option to launch a single job per GPU
- add -v option to use tensorboard instead of wandb
- set nerfacto options according to https://github.com/nerfstudio-project/nerfstudio/issues/806#issuecomment-1284327844
- use a single timestamp for all training jobs
- last GPU was ignored
- kill all subprocesses when script is terminated
- print the eval script command-line
* launch_eval_blender.sh: fix script
* Update benchmarking.md
* launch_train_blender.sh: add -s to eval command-line
* Update launch_train_blender.sh
* Update benchmarking.md
* Added Dockerfile to build docker image including all dependencies and nerfstudio, added description on how to user docker.
* Move docker description to Installation.md.
Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
* Updating the script for downloading data
* Making update to config structure
* Updating documentation and colab
* Adding back the save directory
* Pushing an all flag for nerfstudio
* forgot to save some previous edits
* Add support for polycam
* Modify blur score
* Support processing zip and add undistort fallback
* Created using Colaboratory
* Update docs
* Update demo.ipynb
* Address comments
* fix lint
* documented coordinate conventions without a figure for now
* another sentence
* update frames docs
* explain intrinsics and extrinsics
* more comments
* fix build
* Update custom_dataset.md
Train with the given websocket-port:
```shell
ns-train nerfacto record3d-data --data {RECORD3D_CAPTURE_DIR/EXR_RGBD} --viewer.websocket-port 7007
```
Then I get `ns-train: error: unrecognized arguments: --viewer.websocket-port 7007`.
It is recommended to put `record3d-data` at the end of all arguments.
```shell
ns-train nerfacto --data {RECORD3D_CAPTURE_DIR/EXR_RGBD} --viewer.websocket-port 7007 record3d-data
```
* Update custom_dataset.md
Update
```
ns-train nerfacto nerfstudio-data --data {PROCESSED_DATA_DIR}
```
to
```
ns-train nerfacto --data {PROCESSED_DATA_DIR} nerfstudio-data
```
* alex/record3d_docs_add
* alex/record3d_docs_add
* link from dataparsers to custom_dataset added.
* images are now appearing
Co-authored-by: evonneng <evonne_ng@berkeley.edu>
