This project is mirrored from https://github.com/facebookresearch/habitat-lab.
Pull mirroring updated .
- Aug 15, 2019
-
-
Erik Wijmans authored
This PR seeks to bring habitat-API inline with this. StaticPointGoalSensor is now just a PointGoalSensor and the old PointGoalSensor is now a PointGoalWithGPSCompassSensor. There are also now explicit GPS and Compass sensors, such that you can fairly easily compute PointGoalWithGPSCompassSensor given [PointGoalSensor, GPSSensor, CompassSensor]. The PointGoal* sensors now also include {2d, 3d} x {Cartesian, Polar} support.
-
- Jul 25, 2019
-
-
Erik Wijmans authored
* Refactor baselines to allow for extension * Make clip an after-backward * Loop over rollout step instead of function for full rollout
-
- Jul 22, 2019
-
-
JasonJiazhiZhang authored
* refactor and add generic trainer class * fix to pass tests * change BaseModel to BaseTrainer * fix tensorboard import causing CI failure * modify circle-ci test script accordingly * doc, typing and other changes * rename BASELINE to TRAINER * merge from upstream master * Update Habitat-API to allow for no rendering sensors (#139) Update Habitat-API to allow for no rendering sensors * Added installation requirements step for sim installation in CI setup. (#159) Added installation requirements step for sim installation in CI setup * move RolloutStorage to utils * add environments.py * make ckpt dir if not exist * small fixes according to comments * changes according to comments * update readme * fix old config compatibility * fix missed isort lint
-
- Jun 14, 2019
-
-
JasonJiazhiZhang authored
* Generalize PPO with both PointNav goal sensors * generalize simple agents and fix lint * Removed dataset specific nodes
-
- Jun 06, 2019
-
-
Oleksandr authored
* Builds and installs habitat-sim with python setup.py install * Added pytorch installation and running habitat baseline test in prediction mode. That maybe too much of testing, but decided to keep it for now. * Have ideas how to speed up and parallelize jobs. Will follow up in next PRs. * Run isort and black on whole code to make it happy. * Includes parallelization of installation steps and use files as flags that step is finished. CircleCI has no good way to parallelize steps and have dependencies one the same machine. * Cache is used to save conda dependencies installed and build simulator based on commit SHA.
-
- May 05, 2019
-
-
Oleksandr authored
Renamed baselines folder to habitat_baselines
-
- Apr 30, 2019
-
-
Oleksandr authored
Config system improvements: compositional config, added scenes_dir, removed config_dir, fixed eqa test (#77) * Added scenes_dir parameter to Config to have no requirement of data symlink or data directory in working directory. scenes_dir will be used as prefix for scene_id during episodes dataset loading. * Added overwriting options argument to get_config that unblocks parameter sweeping and experimentation capabilities from command line * config_file path can be comma separated list of configs that will be merged in exact order. That will help to use separate configs for dataset specification and sensors setups. String with commas was chosen because that make it easy to pass list of configs as script argument. * To make habitat-api easier to as package we decided to get rid of forcing loading of configs from config_dir param * fixed unit test caused by latest habitat-sim update * Added support of config list, corrected scene_path, added overwriting options, added EQA dataset changes, adopted quaternion suggestion * Fixed headers
-
- Apr 18, 2019
-
-
Erik Wijmans authored
* Made simple agents suitable for challenge submissions. * Addressed the comments, chaned flag names, switched to benchmark * Removed .swp file, added swp to gitignore. * Compatability with habitat-sim#6 * Fix formatting * Just use the quats to rotate thing * Burn in looks good * Fixup newly merged code wrt. this PR * Nits * Fixup quaternion usage * Add TODO
-
- Apr 13, 2019
-
-
Oleksandr Maksymets authored
-
- Apr 03, 2019
-
-
Facebook Community Bot authored
Benchmark and challenge implementations; PPO agents, Random, ForwardOnly, GoalFollower agents; High resolution top down map and bird-eye visualizations; Collisions measure introduced; SPL success criteria fix; Added deleter that closes subprocesses
-