Merge pull request #8 from KeplerC/main

update readme with pip
BerkeleyAutomation · Apr 28, 2024 · 58e30f8 · 58e30f8
2 parents 80f10e3 + 6935d37
commit 58e30f8
Show file tree

Hide file tree

Showing 11 changed files with 38 additions and 78 deletions.
diff --git a/README.md b/README.md
@@ -2,24 +2,27 @@
 
 🦊 Fog-RT-X: An Efficient and Scalable Data Collection and Management Framework For Robotics Learning. Support [Open-X-Embodiment](https://robotics-transformer-x.github.io/), 🤗[HuggingFace](https://huggingface.co/). 
 
-🦊 Fog-RT-X considers both speed 🚀 and memory efficiency 📈 with active metadata and lazily-loaded trajectory data. It supports flexible and distributed dataset partitioning. 
+🦊 Fog-RT-X considers both speed 🚀 and memory efficiency 📈 with active metadata and lazily-loaded trajectory data. It supports flexible and distributed dataset partitioning. It provides native support to cloud storage. 
 
 [Design Doc](https://docs.google.com/document/d/1woLQVLWsySGjFuz8aCsaLoc74dXQgIccnWRemjlNDws/edit#heading=h.irrfcedesnvr) | [Dataset Visualization](https://keplerc.github.io/openxvisualizer/)
 
 ## Install 
 
 ```bash
-pip install fogx
+pip install fog_x
 ```
 
 ## Usage
 
 ```py
-import fogx as fox 
+import fog_x
 
 # 🦊 Dataset Creation 
 # from distributed dataset storage 
-dataset = fox.Dataset(load_from = ["/tmp/rtx", "s3://fox_storage/"])  
+dataset = fog_x.Dataset(
+    name="demo_ds",
+    path="~/test_dataset", # can be AWS S3, Google Bucket! 
+)  
 
 # 🦊 Data collection: 
 # create a new trajectory
@@ -43,6 +46,7 @@ desired_episodes = episode_info.filter(episode_info["collector"] == "User 2")
 
 # 🦊 Data Sharing and Usage:
 # Export and share the dataset as standard Open-X-Embodiment format
+# it also supports hugging face, and more!
 dataset.export(desired_episodes, format="rtx")
 # Load with pytorch dataloader
 torch.utils.data.DataLoader(dataset.as_pytorch_dataset(desired_episodes))

diff --git a/design_doc/data_layout.md → docs/design_doc/data_layout.md b/design_doc/data_layout.md → docs/design_doc/data_layout.md
diff --git a/design_doc/planning_doc.md → docs/design_doc/planning_doc.md b/design_doc/planning_doc.md → docs/design_doc/planning_doc.md
diff --git a/design_doc/sql_table_design.md → docs/design_doc/sql_table_design.md b/design_doc/sql_table_design.md → docs/design_doc/sql_table_design.md
diff --git a/design_doc/system_assumptions.md → docs/design_doc/system_assumptions.md b/design_doc/system_assumptions.md → docs/design_doc/system_assumptions.md
diff --git a/design_doc/timestamp_join.md → docs/design_doc/timestamp_join.md b/design_doc/timestamp_join.md → docs/design_doc/timestamp_join.md
diff --git a/fog_x/VERSION b/fog_x/VERSION
diff --git a/pyproject.toml b/pyproject.toml
@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "fog_x"
+version = "0.1.0.beta.3"
+dependencies = [
+    "pandas", 
+    "numpy",
+    "polars",
+    "pillow",
+    "pyarrow",
+    "opencv-python",
+    "sqlalchemy==1.4.51",
+]
+description = "An Efficient and Scalable Data Collection and Management Framework For Robotics Learning"
+readme = {file = "README.md", content-type = "text/markdown"}
+license = {file = "LICENSE"}
+keywords = ["robotics", "data", "management", "collection", "framework", "learning"]
+
+[project.optional-dependencies]
+hf = ["datasets"]
+rtx = ["tensorflow", "tensorflow_datasets", "envlogger"]
+aws = ["boto3", "smart_open"]
+torch = ["torch"]
+all = ["datasets", "tensorflow", "tensorflow_datasets", "envlogger", "boto3", "smart_open", "torch", "torchvision"]
+
+[project.urls]
+homepage = "https://github.com/BerkeleyAutomation/fog_x/"
diff --git a/requirements-full.txt b/requirements-full.txt
diff --git a/requirements.txt b/requirements.txt
diff --git a/setup.py b/setup.py