ovon
Open Vocabulary Object Navigation
File Explorer
Download Latest Version (.zip)- rnn_dagger.yaml
- rnn_rl.yaml
- rnn_rl_finetune.yaml
- transformer_dagger.yaml
- transformer_rl.yaml
- transformer_rl_finetune.yaml
- imagenav_stretch_hm3d.yaml
- objectnav_locobot_hm3d.yaml
- objectnav_stretch_hm3d.yaml
- ovon_task.jpg
- dagger.py
- ppo.py
- Mp3d_category_mapping.tsv
- __init__.py
- clean_episodes.py
- generate_description.py
- generate_prompts.py
- generate_viewpoints.py
- instance_objectnav_generator.py
- objectnav_dataset.py
- objectnav_generator.py
- ovon_dataset.py
- pose_sampler.py
- semantic_utils.py
- visualise_objects.py
- visualization.py
- visualize_episodes.py
- __init__.py
- collision_penalty.py
- imagenav.py
- nav.py
- sum_reward.py
- clip_encoder.py
- cma_xattn.py
- cross_attention.py
- depth_encoder.py
- dinov2_encoder.py
- habitat_resnet.py
- make_encoder.py
- resnet_gn.py
- siglip_encoder.py
- vc1_encoder.py
- visual_encoder.py
- visual_encoder_v2.py
- vit.py
- clip_policy.py
- objaverse_clip_policy.py
- ovrl_policy.py
- pointnav.py
- transformer_encoder.py
- transformer_policy.py
- transforms.py
- visual_encoders.py
- image_goal_encoder.py
- relabel_imagegoal.py
- relabel_teacher_actions.py
- resize.py
- __init__.py
- rewards.py
- sensors.py
- simulator.py
- dagger_trainer.py
- envs.py
- inference_worker_with_kv.py
- ppo_trainer_no_2d.py
- ver_rollout_storage_with_kv.py
- ver_trainer.py
- ver_transformer_trainer.py
- HM3D_ObjToRegionNameMap.csv
- HM3D_ObjToRegionNameMap_withStairs.csv
- HM3D_Semantic_Misspelling_Map.csv
- config_utils.py
- fixes_to_provided_mappings.csv
- fixes_to_provided_mappings.ods
- hm3d_annotation_preproc.py
- HM3D_ObjectTypesListing_w_Santhosh.csv
- Issues_with_provided_mappings.csv
- My_HM3D_Missing_Tags_Taxonomy.csv
- Per_Scene_Spelling_Fixes.csv
- postprocess_meta.py
- ovon_goals.py
- semantic_nav_analysis.py
- statistics.py
- viz.py
- cache_clip_embeddings.py
- create_val_split.py
- dagger_environment_worker.py
- lr_scheduler.py
- plot_tsne.py
- rollout_storage_no_2d.py
- sample_episodes.py
- shuffle_episodes.py
- test_dataset.py
- utils.py
- visualize_policy_embeddings.py
- visualize_trajectories.py
- __init__.py
- config.py
- run.py
- test.py
- clean_full_dataset.sh
- clean_scene_dataset.sh
- generate_dataset.sh
- generate_languagenav_dataset.sh
- generate_objectnav_dataset.sh
- generate_val_dataset.sh
- generate_val_episode_counts.py
- submit_data_gen_jobs.sh
- submit_language_annotation_jobs.sh
- 3-ovon-ver-eval-analysis.sh
- 4-objectnav-transformer.sh
- 1-ovon-ver.sh
- 2-imagenav-ver.sh
- 3-ovon-ver-scratch.sh
- 4-objectnav-transformer.sh
- prepare_dataset.sh
- train_ddppo.sh
- train_ver.sh
- .gitignore
- .gitmodules
- .pre-commit-config.yaml
- frontier_exploration
- pyproject.toml
- README.md
- setup.py
- setup.sh
# Installation Guide
1. Get the code
git clone https://github.com/naokiyokoyama/ovon
Downloads the entire project code from GitHub to your computer.
cd ovon
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install ftfy regex tqdm GPUtil trimesh seaborn timm scikit-learn einops transformers
Installs the package published on PyPI directly โ no need to clone the source.
pip install git+https://github.com/openai/CLIP.git
Installs the package published on PyPI directly โ no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
cd frontier_exploration && pip install -e . && cd ..
Moves into the project folder you just downloaded.
pip install -e habitat-lab
Installs the Python libraries listed in requirements.txt (or similar).
pip install -e habitat-baselines
Installs the Python libraries listed in requirements.txt (or similar).
pip install ftfy regex tqdm GPUtil trimesh seaborn timm scikit-learn einops transformers
Installs the package published on PyPI directly โ no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)