* Update pixel_samplers.py
Now uses the specified batch_size param in sample_method()
* black
---------
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
* Use torch_compile with Zoe for compatibility
torch_compile module support
Previously the compatibility utility torch.compile worked for functions, but not for modules as torch.compile was originally employed here.
* torch_compile -> Any
* 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>
* Fix pixel sampler cpu bottleneck
cpu usage reduced 1700% -> 100%, and even more if using multi-gpu training
* Convert to config option
* Change optional to bool
* Implement nerfacto alpha transparency training
* Stop adding all ones alpha channel and clean up blend_background
* Make background_color a required argument in blend_background
* Enable alpha transparent training by default
* Improve background_color typing
* Blend uniform background color for metric computation
* Fix typing error
* Clean up typing
* Fix background_color to outputs assignment
* Model outputs returns unblended RGB (black bg) for random bg
* Update renderers
* Fix comments
* Add support for transparent BG for other methods
* Minor refac
* Fix get_background_color
* Fix typing error for blend_background
* Fix comments
* Export utils support transparency
* Pylint fix
* Fix pcd export masking
* Filter pcd view directions based on opacity
* Clean up get_rgba_image
---------
Co-authored-by: Jonas Kulhanek <jonas.kulhanek@live.com>
* starting the framework for dreamfusion
* Removed view direction from RGB to calculate albedo
* Started diffusion
* Added dreamfusion to CLI, removed direction embeddings
* Normals in dreamfusion
* Lambertian shading added
* Train normals in Dreamfusion
* Stable diffusion from Stable Dreamfusion
* Fix normal orientation loss
* Configurable light direction sampling
* adding density initalization at origin
* V1 datamanager
* Don't train normals for first 1k iters
* SDS loss added to dreamfusion
* Dreamfusion pipeline
* Background MLP and SphereCollider
* Normals prediction training fixed
* Sigmoid on background, prompt in config
* Shading hyperparameter adjustements
* Shading hyperparameter tuning
* Location based prompting, density initialization fades, LR change
* Cleaned imports, more config options
* Tuning, more config changes
* remove unused sampler, normalize predicted normals from network
* change position encoding to direction encoding for background color mlp
* Updating dreamfusion to use custom trainer, fixed bug, multi-gpu support (put diffusion on one specific device), merged with main
* Hard coding less, offloading to config
* Appeasing the linter
* First pass opacity / sparsity losses
* Small patches and configs
* Accidentally pushed logs
* Removing logs for real this time
* Transmittance loss bug fix
* 12 GB Dreamfusion!
* Lint
* Remove unecissary collider changes
* Start SD cleanup
* Cleanup SD code
* adding overhead location prompting
* Use lambertian renderer
* turn grad accum off by default, decrease background mlp size, add overhead text embedding
* Cleanup
* Fix normals vis
* change uniform sampler to prediction network, add option to jit unet for faster sds_loss
* Use shaders
* cleaning up jit code
* add warning if using non jit unet
* add proposal network optimizer to config
* speed up render and cleanup code
* Clean up datamanager
* Add distortion loss
* fix wanb
* adding interpolated location sampling
* Update configs
* interpolated location prompting option, lowering init density, transmittance loss interpolation flipped
* rename alphas mult to alphas loss mult
* Mess around with normals
* add option to use random bg color + bg mlp
* Remove Dreamfusion Trainer (#1423)
* Dreamfusion trainer no longer needed
* Added typing for grad scaler
* SDS return loss
* Fix CFG
* Cleanup
* Update configs
* Fix opacity loss, use unform sampling first round of prop
* add prompt edditing to viewer
* Choose your own diffusion
* remove dreamfusion pipeline file
* merging + remove dreamfusion pipeline file
* Update configs
* add stable diff utils
* cleanup
* cleanup
* Fix test
* positional prompting bugfix
* Warmups
* tune
* lint
* Remove dataparser
* merging + text embedding bugfix
* Set data path to launch viewer for DreamFusion (#1776)
* Set data path to launch viewer for DreamFusion
* Apply formatter
* Fallback to 'base_dir' if data manager has no path
* Make if statement non-inline
* Reformat
---------
Co-authored-by: Matthew Tancik <mattt4001@gmail.com>
* add deepfloyd option first try
* merging
* merging from main
* merging
* removing comments, cleaning code, making stable diff utils usable for deepfloyd, remove deepfloyd text encoder after use
* undo chagnes in data folder
* cleaning code, removing unneccesary changes from main, removed normals prediction network
* remove old scripts files, rename generative pipeline flag to no_input_data, revert to default histogram padding in proposal sampler
* changing pipeline flag
* move no input data flag from pipeline to datamanager
* undo config and merge in deepfloyd from main
* merging grad scaler pipeline addition
* merging + setting proposal net scheduler
* revert nerfacto config change
* typing + linting
* rename dreamfusion datamanager to random camras datamanager, check datamanager typing in pipeline and trainer
* fix test import
* fix test import
* changing datamanager check in trainer, add typing in random cameras datamanager
* add Tensor to randomcamerasdatamanager
* remove old comments
* resolve tyro warning
* update fields to use tcnn
* lint
* add packages for deepfloyd
* add versions
* docs first draft
* rename to generfacto, clean docs
* fix import error
* minor changes
* fix orientation loss bug, retune params
* cleanup
* typing
* trying docs fix
* fixing generative package imports
* fix pyright
* docs fix
* merge w main
* docs minor change
* tuning + bugfixes
* remove torch.backends
---------
Co-authored-by: Abhik Ahuja <ahujaabhik@berkeley.edu>
Co-authored-by: David McAllister <davidrmc2@gmail.com>
Co-authored-by: Jake Austin <jake-austin@berkeley.edu>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
Co-authored-by: Matt Tancik <mattt4001@gmail.com>
Co-authored-by: SeungWoo Yoo <dreamy1534@gmail.com>
Co-authored-by: ayaanzhaque <ayaanzhaque@gmail.com>
Co-authored-by: Ayaan Haque <ayaanzhaque@berkeley.edu>
Also remove the image skipping logic, which seems to be a remnant of some old code (all images should exist)
Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
* Fix model loading collate_fn non-static
* Fix serialization
* Add tests to reproduce the error
* Comment the change to let the tests fail
* Finish changes
* knocking out a couple
* Fix more errors
* Add pyright
* Remove some unnecessary cv2 type ignores, warning on missing imports
(for missing tinycudann)
* Minor annotation fixes
* Update docs
* Drop `None` from temporal distortion output
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* `isort` -> `ruff`
* `pylint` -> `ruff`
* Remove line
* More minor cleanup
* Better documentation for rules we are enabling
* Fix gitignore, run black
* vscode settings
---------
Co-authored-by: Matt Tancik <mattt4001@gmail.com>