Skip to content
Snippets Groups Projects
This project is mirrored from https://github.com/facebookresearch/habitat-lab. Pull mirroring updated .
  1. Sep 23, 2019
  2. Sep 19, 2019
  3. Sep 12, 2019
  4. Sep 08, 2019
  5. Sep 06, 2019
  6. Sep 05, 2019
  7. Sep 03, 2019
  8. Aug 29, 2019
  9. Aug 27, 2019
  10. Aug 15, 2019
    • Erik Wijmans's avatar
      Correct the naming of PointGoalNav Sensors (#180) · b5f2b00a
      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.
      b5f2b00a
    • JasonJiazhiZhang's avatar
      Fix vector env deletion (#185) · 6d76d42f
      JasonJiazhiZhang authored
      Explicitly call close for vector env to avoid issues with file writer prematurely close buffer when tensorboard enabled. See #184 for more info.
      6d76d42f
    • JasonJiazhiZhang's avatar
      Generalize performance metric for baselines (#178) · 04368cdc
      JasonJiazhiZhang authored
      Making eval() in ppo_trainer retrieve the name (sensor_uuid) of performance metric used instead of always using spl. This change is necessary for ppo_trainer to support new tasks that might have performance metric other than spl.
      04368cdc
    • JasonJiazhiZhang's avatar
      Move circle-ci experiment testing to pytest (#176) · dd75f18f
      JasonJiazhiZhang authored
      With the recent refactor/redesign of habitat_baselines, all experiment parameters can be specified through config files. Thus it makes sense to turn the python script run in circle-ci into a separate test file in our test/. This also makes it more extensible when we add more trainers in the future.
      dd75f18f
  11. Aug 07, 2019
  12. Aug 05, 2019
  13. Aug 02, 2019
  14. Jul 26, 2019
  15. Jul 25, 2019
  16. Jul 22, 2019
    • JasonJiazhiZhang's avatar
      Refactor baselines: add generic trainer and common utils (#153) · 31318f81
      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
      31318f81
  17. Jul 18, 2019
    • Oleksandr's avatar
      Added ccache to CI and fixed PyTorch caching. (#161) · 7eb3da12
      Oleksandr authored
      * fixed PyTorch caching
      * added ccache to CI
      * broke habitat api step on installation and testing to save extra 5 min on saving cache in parallel
      * testing time drops from first run to second run from 17.5 minutes to 9 minutes (2x times) for full testing.
      Unverified
      7eb3da12
  18. Jul 17, 2019
  19. Jul 16, 2019
  20. Jul 15, 2019
  21. Jul 11, 2019
  22. Jul 05, 2019
  23. Jul 04, 2019
  24. Jun 29, 2019
    • Erik Wijmans's avatar
      Fix quickstart keys commands (#147) · 43ab7241
      Erik Wijmans authored
      * Fix quickstart
      43ab7241
    • JasonJiazhiZhang's avatar
      Add tensorboard and video generation for ppo train and eval (#127) · 38be0f53
      JasonJiazhiZhang authored
      * Add checkpoint progress tracking for evalute_ppo. Now when specified with a checkpoint directory,
      * Evaluate_ppo will evaluate checkpoints in chronological order, and constantly check for new checkpoint.
      * Add tensorboard visualization to both train_ppo and evaluate_ppo
      * Add video generation for navigation episode evaluation. Generated videos can be either saved locally or visualized through tensorboard.
      * Add shortest path visualization
      38be0f53
  25. Jun 25, 2019
  26. Jun 19, 2019
Loading