Skip to content

Commit 7c66e7a

Browse files
amandleksnasiriany
andauthored
v0.4 release (#219)
* 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]>
1 parent 9273f9c commit 7c66e7a

File tree

16 files changed

+215
-60
lines changed

16 files changed

+215
-60
lines changed

.gitignore

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@ dist/
77
# local test dataset that is lazily downloaded by example scripts
88
tests/assets/test.hdf5
99
tests/assets/test_v141.hdf5
10+
tests/assets/test_v15.hdf5
1011

1112
# pycharm configs
1213
.idea/

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,7 @@
1515

1616
-------
1717
## 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
1819
- [10/11/2023] **v0.3.1**: support for extracting, training on, and visualizing depth observations for robosuite datasets
1920
- [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
2021
- [05/23/2022] **v0.2.1**: Updated website and documentation to feature more tutorials :notebook_with_decorative_cover:

docs/datasets/robomimic_v0.1.md

Lines changed: 22 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -14,9 +14,11 @@ robomimic v0.1 datasets is a large-scale, diverse collection of task demonstrati
1414
<p class="admonition-title">Warning!</p>
1515
<!-- 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. -->
1616

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).
1818

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.
2022

2123
</div>
2224

@@ -51,7 +53,14 @@ $ python download_datasets.py --download_dir /tmp/datasets
5153

5254
### Method 2: Using Direct Download Links
5355

54-
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).
57+
58+
<div class="admonition info">
59+
<p class="admonition-title">HuggingFace repository</p>
60+
61+
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).
62+
63+
</div>
5564

5665
**Proficient-Human (PH)** [**info**](robomimic_v0.1.html#proficient-human-ph)
5766

@@ -64,8 +73,8 @@ We also provide direct download links for each hdf5 dataset (the download links
6473
| **Lift<br />(PH)** | **Can<br />(PH)** | **Square<br />(PH)** | **Transport<br />(PH)** | **Tool Hang<br />(PH)** |
6574
| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
6675
| ![lift](../images/lift.png) | ![can](../images/can.png) | ![square](../images/square.png) | ![transport](../images/transport.png) | ![tool_hang](../images/tool_hang.png) |
67-
| [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/ph/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/ph/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/square/ph/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/transport/ph/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/tool_hang/ph/demo_v141.hdf5) |
68-
| [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/ph/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/ph/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/square/ph/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/transport/ph/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/tool_hang/ph/low_dim_v141.hdf5) |
76+
| [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/ph/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/ph/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/square/ph/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/transport/ph/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/tool_hang/ph/demo_v15.hdf5?download=true) |
77+
| [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/ph/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/ph/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/square/ph/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/transport/ph/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/tool_hang/ph/low_dim_v15.hdf5?download=true) |
6978

7079
| **Lift Real<br />(PH)** | **Can Real<br />(PH)** | **Tool Hang Real<br />(PH)** |
7180
| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
@@ -88,8 +97,8 @@ We also provide direct download links for each hdf5 dataset (the download links
8897
| **Lift<br />(MH)** | **Can<br />(MH)** | **Square<br />(MH)** | **Transport<br />(MH)** |
8998
| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
9099
| ![lift](../images/lift.png) | ![can](../images/can.png) | ![square](../images/square.png) | ![transport](../images/transport.png) |
91-
| [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/mh/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/mh/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/square/mh/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/transport/mh/demo_v141.hdf5) |
92-
| [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/mh/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/mh/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/square/mh/low_dim_v141.hdf5) | [low_dim](http://downloads.cs.stanford.edu/downloads/rt_benchmark/transport/mh/low_dim_v141.hdf5) |
100+
| [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/mh/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/mh/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/square/mh/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/transport/mh/demo_v15.hdf5?download=true) |
101+
| [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/mh/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/mh/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/square/mh/low_dim_v15.hdf5?download=true) | [low_dim](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/transport/mh/low_dim_v15.hdf5?download=true) |
93102
</p>
94103
</details>
95104

@@ -107,9 +116,9 @@ We also provide direct download links for each hdf5 dataset (the download links
107116
| **Lift<br />(MG)** | **Can<br />(MG)** |
108117
| :----------------------------------------------------------: | :----------------------------------------------------------: |
109118
| ![lift](../images/lift.png) | ![can](../images/can.png) |
110-
| [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/mg/demo_v141.hdf5) | [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/mg/demo_v141.hdf5) |
111-
| [low_dim (sparse)](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/mg/low_dim_sparse_v141.hdf5) | [low_dim (sparse)](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/mg/low_dim_sparse_v141.hdf5) |
112-
| [low_dim (dense)](http://downloads.cs.stanford.edu/downloads/rt_benchmark/lift/mg/low_dim_dense_v141.hdf5) | [low_dim (dense)](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/mg/low_dim_dense_v141.hdf5) |
119+
| [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/mg/demo_v15.hdf5?download=true) | [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/mg/demo_v15.hdf5?download=true) |
120+
| [low_dim (sparse)](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/mg/low_dim_sparse_v15.hdf5?download=true) | [low_dim (sparse)](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/mg/low_dim_sparse_v15.hdf5?download=true) |
121+
| [low_dim (dense)](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/lift/mg/low_dim_dense_v15.hdf5?download=true) | [low_dim (dense)](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/mg/low_dim_dense_v15.hdf5?download=true) |
113122

114123
</p>
115124
</details>
@@ -126,8 +135,8 @@ We also provide direct download links for each hdf5 dataset (the download links
126135
| **Can Paired** |
127136
| :----------------------------------------------------------: |
128137
| <img src="../images/can_paired.png" alt="can_paired" style="zoom:12%;" /> |
129-
| [raw](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/paired/demo_v141.hdf5) |
130-
| [low_dim (sparse)](http://downloads.cs.stanford.edu/downloads/rt_benchmark/can/paired/low_dim_v141.hdf5) |
138+
| [raw](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/paired/demo_v15.hdf5?download=true) |
139+
| [low_dim (sparse)](https://huggingface.co/datasets/amandlek/robomimic/resolve/main/v1.5/can/paired/low_dim_v15.hdf5?download=true) |
131140

132141
</p>
133142
</details>
@@ -188,7 +197,7 @@ python /path/to/robomimic/scripts/train.py --config /path/to/robomimic/exps/pape
188197
<div class="admonition info">
189198
<p class="admonition-title">Want to Run Experiments on Custom Observations?</p>
190199

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).
192201

193202
**NOTE**: To compare against how our paper's released datasets were generated, please see the `extract_obs_from_raw_datasets.sh` script.
194203

docs/index.rst

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,7 @@ Welcome to robomimic's documentation!
8181
:maxdepth: 1
8282
:caption: Previous Versions
8383

84+
versions/v0.3
8485
versions/v0.2
8586

8687

docs/tutorials/configs.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ Please see the [Config documentation](../modules/configs.html) for more informat
1919
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.**
2020

2121
```sh
22-
$ python train.py --config ../exps/templates/bc.json --dataset ../../tests/assets/test_v141.hdf5
22+
$ python train.py --config ../exps/templates/bc.json --dataset ../../tests/assets/test_v15.hdf5
2323
```
2424

2525
Please see the [hyperparameter helper tutorial](../tutorials/hyperparam_scan.html) to see how to easily generate json configs for launching training runs.

docs/tutorials/dataset_contents.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -18,10 +18,10 @@ The repository offers a simple utility script (`get_dataset_info.py`) to view th
1818
- 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
1919
- the dataset structure for the first demonstration
2020

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.
2222

2323
```sh
24-
$ python get_dataset_info.py --dataset ../../tests/assets/test_v141.hdf5
24+
$ python get_dataset_info.py --dataset ../../tests/assets/test_v15.hdf5
2525
```
2626

2727
<div class="admonition tip">
@@ -36,25 +36,25 @@ Any user wishing to write custom code that works with robomimic datasets should
3636
<div class="admonition note">
3737
<p class="admonition-title">Note: These examples are compatible with any robomimic dataset.</p>
3838

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.
4040

4141
</div>
4242

4343
Use the `playback_dataset.py` script to easily view dataset trajectories.
4444

4545
```sh
4646
# 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
47-
$ python playback_dataset.py --dataset ../../tests/assets/test_v141.hdf5 --render_image_names agentview robot0_eye_in_hand --video_path /tmp/playback_dataset.mp4 --n 5
47+
$ python playback_dataset.py --dataset ../../tests/assets/test_v15.hdf5 --render_image_names agentview robot0_eye_in_hand --video_path /tmp/playback_dataset.mp4 --n 5
4848

4949
# 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.
50-
$ python playback_dataset.py --dataset ../../tests/assets/test_v141.hdf5 --use-obs --render_image_names agentview_image --video_path /tmp/obs_trajectory.mp4
50+
$ python playback_dataset.py --dataset ../../tests/assets/test_v15.hdf5 --use-obs --render_image_names agentview_image --video_path /tmp/obs_trajectory.mp4
5151

5252
# Visualize depth observations as well.
5353
$ python playback_dataset.py --dataset /path/to/dataset.hdf5 --use-obs --render_image_names agentview_image --render_depth_names agentview_depth --video_path /tmp/obs_trajectory.mp4
5454

5555
# Play the dataset actions in the environment to verify that the recorded actions are reasonable.
56-
$ python playback_dataset.py --dataset ../../tests/assets/test_v141.hdf5 --use-actions --render_image_names agentview --video_path /tmp/playback_dataset_with_actions.mp4
56+
$ python playback_dataset.py --dataset ../../tests/assets/test_v15.hdf5 --use-actions --render_image_names agentview --video_path /tmp/playback_dataset_with_actions.mp4
5757

5858
# Visualize only the initial demonstration frames.
59-
$ python playback_dataset.py --dataset ../../tests/assets/test_v141.hdf5 --first --render_image_names agentview --video_path /tmp/dataset_task_inits.mp4
59+
$ python playback_dataset.py --dataset ../../tests/assets/test_v15.hdf5 --first --render_image_names agentview --video_path /tmp/dataset_task_inits.mp4
6060
```

docs/tutorials/hyperparam_scan.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ Sections of the config that are not involved in the scan and that do not differ
2222

2323
</div>
2424

25-
We modify `/tmp/gen_configs/base.json`, adding a base experiment name (`"bc_rnn_hyper"`) and specified the dataset path (`"/tmp/test_v141.hdf5"`).
25+
We modify `/tmp/gen_configs/base.json`, adding a base experiment name (`"bc_rnn_hyper"`) and specified the dataset path (`"/tmp/test_v15.hdf5"`).
2626

2727
```sh
2828
$ cat /tmp/gen_configs/base.json
@@ -59,7 +59,7 @@ $ cat /tmp/gen_configs/base.json
5959
}
6060
},
6161
"train": {
62-
"data": "/tmp/test_v141.hdf5",
62+
"data": "/tmp/test_v15.hdf5",
6363
"output_dir": "../bc_trained_models",
6464
"num_data_workers": 0,
6565
"hdf5_cache_mode": "all",

docs/versions/v0.3.md

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
# v0.3
2+
3+
Redirecting...
4+
5+
<html lang="en-US">
6+
<head>
7+
<meta charset="UTF-8">
8+
<meta http-equiv="refresh" content="0; url=https://robomimic.github.io/docs/v0.3/introduction/overview.html">
9+
<script type="text/javascript">
10+
window.location.href = "https://robomimic.github.io/docs/v0.3/introduction/overview.html"
11+
</script>
12+
<title>Page Redirection</title>
13+
</head>
14+
<body>
15+
<!-- Note: don't tell people to `click` the link, just tell them that it is a link. -->
16+
If you are not redirected automatically, follow this <a href='https://robomimic.github.io/docs/v0.3/introduction/overview.html'>link</a>.
17+
</body>
18+
</html>

0 commit comments

Comments
 (0)