* Model class done, pipeline class still needs more visualization stuffs
* Renaming the BaseDataContainer to DataloaderOutputs and adding documentation
* Pushing more documentation, removing some trivial functions
* Updating dict typing
* Removing config dicts for collider
* Passing tests
* Pushing shell new dataloader
* Saving work, need to fix NGP model's get_loss_dict and Pipeline
* V1 of the ngp pipeline should be done. Need train script and debugging
* Updating with latest instant-ngp code
* Syntax updates from latest ngp graph code
* Linter, removing unneeded code in new NGP graph code
* Style
* Should be good now. Linter is happy and the code is verbatum current instant-ngp
* Everything done except novel view testing code
* Fixing some nitpicks
* Debugging dataloader
* merged master
* WOP. integrating pipeline with configs and notebook demo
* removing model folder
* a lot of name changing from Graph to Model
* in progress... changing trainer to use pipeline... broken right now
* pipeline code runs
* switched to val dataset
* makes run_eval.py work
* updated configs for pipeline change
* fixing test_run_train script
* fixing black and linting
* fix docs
* small updates to trainer
Co-authored-by: Jake Austin <jake-austin@berkeley.edu>
* updated three.js version. only send camera information when it moves
* changing code back to updating camera constantly because packets seem to be lost
* interrupting function during rendering
* small linting fixes
* added logic for interrupting rendering + separted out visualizer logic from trainer
Co-authored-by: evonneng <evonne_ng@berkeley.edu>
* restructuring for webrtc integration
* some webrtc code but not working
* webrtc connects when muted
* the flag is real!
* updating camera in websocket bridge. moved webrtc to existing websocket connection instead of http request. need to change video track
* rudimentary adding real-time imaging
* added free TURN server so code works everywhere
* slow rendering works during training with the viewer
* fix tensor device and update default model save dir
* forgot to include trainer updates
* removing some code that isn't needed
* quick fix to bins. not the most accurate however
* cleaned up code and added some config logic
* black
* adding license
Co-authored-by: evonneng <evonne_ng@berkeley.edu>
Contract the scene to a sphere of radius 2. This is the same contraction used in MipNeRF 360.
Add mipnerf 360 graph and config. It currently doesn't contain the other advancements made in the paper (sample proposal network, regularizers)
* renaming dataloader to data. adding some dataloader classes
* restructuring configs
* fixed instant ngp tcnn direction rescaling
* working through test cases
* black and lint and tests
* in progress. camera_indices broken
* faster dataloader. starting on pixel sampler logic
* imagesampler and pixelsampler
* lint and black
* continuing merge
* pytest working
* fixed docs
* docs
* minor changes
* some initial cuda code as I learn. using git to save progress.
* first cuda kernel for ray sampling that mostly works
* cleaning up code. working on lr. structs for scene bounds aabb
* added scene bounds collider code
* updated setup
* setup
* setup
* black
* including some files
* exporting env variable
* new file
* git workflows
* github actions
* github actions
* github actions
* removing env var
* initial nerfw code
* nerfw should be implmented correctly now
* semantic nerf in progress. data loader is too slow and not clean right now
* added implementation of semantic nerf
* mend
* abstracted some test logic and actually using test images now
* moved logging from trainer to graph
* fixing dataset path
* refactored instant ngp code to use inheritance
* fixed my run_train
* fixed data path
* fixed data dir
* added skeleton for terminal logger
* done skeleton terminal writer logic... todo: actual calls to the write classes
* moved lambda to top function
* added logic to support timing
* prettier printing
* prettier printing
* lint
* separated out timing and other stats variables. printing in dict format
* keeping logging history and wiping rest
* updated logic to calculate total times instead of average times
* made stats tracker configurable
* moved stats tracker and profiler to own class file; implemented basic functionality for profiler
* lint removing duplicate function
* update readme; moved around config variables
* profiler prints on sig kill
* merge
* standardized all logging to global variables
Ethan Weber
Matt Tancik
Ruilong Li(李瑞龙)
evonneng
Brent Yi
Ethan Weber