* (1) if wandb/tb enabled always eval; (2) move printing of config to after all variables set
* (3) save config after everything is set
* dont change config; just disable eval with decorator
* compound model now uses compound field, passing num_images in the config, working on passing image indices through ngp sampler
* renaming cuda func, adding torch compound support
* removing unused imports
* getting num images from dataloader instead of config
* fixing pylint and adding todo
* undoing base config change
* adding cone angle and near plane to compound model config
* misc cuda improvements. added cone angle as param
* wandb as default. better organization for experiments
* turn off tensorboard
* disable eval when using viewer
* remove comment
* launch.json
* added logic to comp rays/s on train and vis
* added test and fixed vis rays/sec
* added flag to just visualize dataset
* added new script for viewing only dataset
* testing; need to merge
* fixing wrong base file in models/base
* pushed input parser into datasets class to abstract away fetching data in dataloader
* slight name chage and all
* nits
* added dataparser
* added licnese
* added tensorf, updated requirements for windows
* cleaning up imports
* tensorf changes
* initial working version of tensorf
* added callback for feature upsampling
* modifying tests to match changes
* reverting requirements changes
* reverting unnecessary changes
* reverting unnecessary changes
* no more upsampling on step 0
* removed density field, fixed error msg
* modified callbacks and upsampling, reinitializing optimzer in training loop
* deleting tensorf_field file"
* checkpointing progress on restructuring callbacks
* updated callback logic for before and after train capabilities
* fixing upsampling stepping
* merging
* adding tensorf to config, fixing some bugs with new callback
* changed the way callbacks detected steps argument in callback func
* fixing typing
* adding pylint disable no self use to get_training_callbacks
* fixing config
* changing callback in vanilla nerf to allow for no density field
* cleanup
* removing config yaml
Co-authored-by: Ethan Weber <eweb0124@gmail.com>
* starting docs for pipelines
* working on an example
* clearing output
* starting to implement config changes and add documentation
* wip: removed cicular imports; porting basic config into python; todo: get python setups workin
* circular imports again
* wip: pausing at dataloader sort of working
* break for today
* running vanilla
* wip need to get all the config docs working
* laptop about to die
* instant ngp working
* added all configs for all methods; not tested yet: [mipnerf360, nerfw, semantic_nerf]
* unpacking later
* done with pylinting
* mostly done. just need to do docs and one test
* added import order to docs
* fixing near/far plane and other config things
* making loggers also instantiable via configs
* docs
* lint
* making --help work with dcargs
* moving configs back into flat
* convert list to tuples; fixed post init function with mutable params
* lint
* made run_eval and benchmarking scripts compatible with new config/dcargs
* lint
* added option to load configs from presaved config
Co-authored-by: evonneng <evonne_ng@berkeley.edu>
evonneng
Ethan Weber
Jake Austin
Matthew Tancik
Terrance Wang
Alexander Kristoffersen
Brent Yi
