You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* add robocasa import and ep_meta support
* update logic for robosuite v1.5 check
* bump version
* Hf v15 (#214)
* some minor changes
* release robomimic datasets compatible with robosuite v1.5 on huggingface
* some fixes for visualization with robosuite v1.5
* potential fix for video render when using depth images during training
* minor fix
* new paths for test hdf5 based on robosuite version and HF
* update docs
---------
Co-authored-by: snasiriany <[email protected]>
Co-authored-by: Soroush Nasiriany <[email protected]>
Copy file name to clipboardExpand all lines: README.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,6 +15,7 @@
15
15
16
16
-------
17
17
## Latest Updates
18
+
-[3/11/2025]**v0.4.0**: support for [robosuite v1.5](https://github.com/ARISE-Initiative/robosuite/tree/v1.5.1) and migrate robomimic datasets to HuggingFace
18
19
-[10/11/2023]**v0.3.1**: support for extracting, training on, and visualizing depth observations for robosuite datasets
19
20
-[07/03/2023]**v0.3.0**: BC-Transformer and IQL :brain:, support for DeepMind MuJoCo bindings :robot:, pre-trained image reps :eye:, wandb logging :chart_with_upwards_trend:, and more
20
21
-[05/23/2022]**v0.2.1**: Updated website and documentation to feature more tutorials :notebook_with_decorative_cover:
Copy file name to clipboardExpand all lines: docs/datasets/robomimic_v0.1.md
+22-13Lines changed: 22 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,9 +14,11 @@ robomimic v0.1 datasets is a large-scale, diverse collection of task demonstrati
14
14
<pclass="admonition-title">Warning!</p>
15
15
<!-- When working with these datasets, please make sure that you have installed [robosuite](https://robosuite.ai/) from source and are on the `v1.4.1` branch. -->
16
16
17
-
Since the release of robomimic v0.3, we recommend that users install [robosuite](https://robosuite.ai/) from source and are on the `v1.4.1` branch. The `v1.4.1` branch of robosuite uses Google DeepMind's [mujoco python bindings](https://github.com/deepmind/mujoco) which replaces the now deprecated [mujoco-py](https://github.com/openai/mujoco-py).
17
+
Since the release of robomimic v0.4, we recommend that users install [robosuite](https://robosuite.ai/) from source and are on the `v1.5.1` branch. The `v1.5.1` branch of robosuite uses Google DeepMind's [mujoco python bindings](https://github.com/deepmind/mujoco) which replaces the now deprecated [mujoco-py](https://github.com/openai/mujoco-py).
18
18
19
-
Note that the CoRL 2021 datasets relied on the mujoco-py based `offline_study` branch of robosuite. In this version of robomimic we provide users with datasets based on `v1.4.1`, which we found produce similar results to the original `offline_study` datasets. However if you would like to download the `offline_study` datasets, please use the `v0.2.0` branch of robomimic and consult the [v0.2 docs](https://robomimic.github.io/docs/v0.2/datasets/robomimic_v0.1.html) for instructions.
19
+
Note that the CoRL 2021 datasets relied on the mujoco-py based `offline_study` branch of robosuite. In this version of robomimic we provide users with datasets based on `v1.5.1`, which allows users to use new robosuite features. However, it is possible that learning results may not match exactly with the original `offline_study` datasets. If you would like to download the `offline_study` datasets, please use the `v0.2.0` branch of robomimic and consult the [v0.2 docs](https://robomimic.github.io/docs/v0.2/datasets/robomimic_v0.1.html) for instructions.
20
+
21
+
Previously, we also had datasets based on the `v1.4.1` branch of robosuite, packaged with robomimic v0.3. If you would like to use those, please switch to robomimic v0.3 and consult the [v0.3 docs](https://robomimic.github.io/docs/v0.3/datasets/robomimic_v0.1.html) for instructions.
We also provide direct download links for each hdf5 dataset (the download links for the raw datasets are also included – they allow flexibility in extracting different kinds of observations and rewards during postprocessing):
56
+
We also provide direct download links for each hdf5 dataset (the download links for the raw datasets are also included – they allow flexibility in extracting different kinds of observations and rewards during postprocessing).
You can also find all of the datasets at the Hugging Face link [here](https://huggingface.co/datasets/amandlek/robomimic/tree/main/v1.5) (except for the real robot datasets, which are not hosted there).
<pclass="admonition-title">Want to Run Experiments on Custom Observations?</p>
190
199
191
-
We provide the raw (observation-free) `demo_v141.hdf5` datasets so that you can generate your own custom set of observations, such as additional camera viewpoints. For information, see [Extracting Observations from Datasets](robosuite.md#extracting-observations-from-mujoco-states).
200
+
We provide the raw (observation-free) `demo_v15.hdf5` datasets so that you can generate your own custom set of observations, such as additional camera viewpoints. For information, see [Extracting Observations from Datasets](robosuite.md#extracting-observations-from-mujoco-states).
192
201
193
202
**NOTE**: To compare against how our paper's released datasets were generated, please see the `extract_obs_from_raw_datasets.sh` script.
Copy file name to clipboardExpand all lines: docs/tutorials/configs.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,7 +19,7 @@ Please see the [Config documentation](../modules/configs.html) for more informat
19
19
The preferred way to specify training parameters is to pass a config json to the main training script `train.py` via the `--config` argument. The dataset can be specified by setting the `data` attribute of the `train` section of the config json, or specified via the `--dataset` argument. The example below runs a default template json for the BC algorithm. **This is the preferred way to launch training runs.**
Please see the [hyperparameter helper tutorial](../tutorials/hyperparam_scan.html) to see how to easily generate json configs for launching training runs.
Copy file name to clipboardExpand all lines: docs/tutorials/dataset_contents.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,10 +18,10 @@ The repository offers a simple utility script (`get_dataset_info.py`) to view th
18
18
- the [environment metadata](../modules/environments.html#initialize-an-environment-from-a-dataset) in the dataset, which is used to construct the same simulator environment that the data was collected on
19
19
- the dataset structure for the first demonstration
20
20
21
-
Pass the `--verbose` argument to print the list of demonstration keys under each filter key, and the dataset structure for all demonstrations. An example, using the small hdf5 dataset packaged with the repository in `tests/assets/test_v141.hdf5` is shown below.
21
+
Pass the `--verbose` argument to print the list of demonstration keys under each filter key, and the dataset structure for all demonstrations. An example, using the small hdf5 dataset packaged with the repository in `tests/assets/test_v15.hdf5` is shown below.
@@ -36,25 +36,25 @@ Any user wishing to write custom code that works with robomimic datasets should
36
36
<divclass="admonition note">
37
37
<pclass="admonition-title">Note: These examples are compatible with any robomimic dataset.</p>
38
38
39
-
The examples in this section use the small hdf5 dataset packaged with the repository in `tests/assets/test_v141.hdf5` (which requires robosuite v1.4.1), but you can run these examples with any robomimic hdf5 dataset.
39
+
The examples in this section use the small hdf5 dataset packaged with the repository in `tests/assets/test_v15.hdf5` (which requires robosuite v1.4.1), but you can run these examples with any robomimic hdf5 dataset.
40
40
41
41
</div>
42
42
43
43
Use the `playback_dataset.py` script to easily view dataset trajectories.
44
44
45
45
```sh
46
46
# For the first 5 trajectories, load environment simulator states one-by-one, and render "agentview" and "robot0_eye_in_hand" cameras to video at /tmp/playback_dataset.mp4
# Directly visualize the image observations in the dataset. This is especially useful for real robot datasets where there is no simulator to use for rendering.
0 commit comments