cadop / nodeik Goto Github PK

Not appropriate to use master for branch name.

Gitlfs for all stl dae obj and checkpoints of models.

Create featured image showing visualization.

Make some example files showing how to save render and visualize in OV

There are several problems when using train script after pip installation. The version of urdpy,pycollada,numpy and so on do affect where the train script can run. Or provide an envrioemnt.yaml or docker.
And when i run train_from_panda_urdf.py, it throws:

warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
Warp CUDA error: Failed to get function cuGetProcAddress
Warp 0.10.1 initialized:
CUDA devices not available
Devices:
"cpu" | x86_64
Kernel cache: /home/junfeng/.cache/warp/0.10.1
Traceback (most recent call last):
File "/home/junfeng/.local/lib/python3.8/site-packages/collada/init.py", line 201, in init
self.xmlnode = ElementTree.ElementTree(element=None,
File "src/lxml/etree.pyx", line 3175, in lxml.etree.ElementTree
File "src/lxml/parser.pxi", line 1896, in lxml.etree._parseDocument
File "src/lxml/parser.pxi", line 1916, in lxml.etree._parseMemoryDocument
File "src/lxml/parser.pxi", line 1803, in lxml.etree._parseDoc
File "src/lxml/parser.pxi", line 1144, in lxml.etree._BaseParser._parseDoc
File "src/lxml/parser.pxi", line 618, in lxml.etree._ParserContext._handleParseResultDoc
File "src/lxml/parser.pxi", line 728, in lxml.etree._handleParseResult
File "src/lxml/parser.pxi", line 657, in lxml.etree._raiseParseError
File "", line 1
lxml.etree.XMLSyntaxError: Start tag expected, '<' not found, line 1, column 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "examples/train_from_panda_urdf.py", line 84, in
run()
File "examples/train_from_panda_urdf.py", line 60, in run
r, dataloader, val_dataloader = get_robot(filepath)
File "examples/train_from_panda_urdf.py", line 43, in get_robot
r = Robot(robot_path=filepath, ee_link_name='panda_hand')
File "/home/junfeng/nodeik/nodeik/robots/robot.py", line 18, in init
self.link_index = parse_urdf(
File "/home/junfeng/nodeik/nodeik/warp/urdf_loader.py", line 126, in parse_urdf
robot = urdfpy.URDF.load(filename)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 3729, in load
return URDF._from_xml(node, path)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 3926, in _from_xml
kwargs = cls._parse(node, path)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 161, in _parse
kwargs.update(cls._parse_simple_elements(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 137, in _parse_simple_elements
v = [t._from_xml(n, path) for n in vs]
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 137, in
v = [t._from_xml(n, path) for n in vs]
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 181, in _from_xml
return cls(**cls._parse(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 161, in _parse
kwargs.update(cls._parse_simple_elements(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 137, in _parse_simple_elements
v = [t._from_xml(n, path) for n in vs]
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 137, in
v = [t._from_xml(n, path) for n in vs]
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 1146, in _from_xml
kwargs = cls._parse(node, path)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 161, in _parse
kwargs.update(cls._parse_simple_elements(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 127, in _parse_simple_elements
v = t._from_xml(v, path)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 181, in _from_xml
return cls(**cls._parse(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 161, in _parse
kwargs.update(cls._parse_simple_elements(node, path))
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 127, in _parse_simple_elements
v = t._from_xml(v, path)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/urdf.py", line 581, in _from_xml
meshes = load_meshes(fn)
File "/home/junfeng/.local/lib/python3.8/site-packages/urdfpy/utils.py", line 225, in load_meshes
meshes = trimesh.load(filename)
File "/home/junfeng/.local/lib/python3.8/site-packages/trimesh/exchange/load.py", line 120, in load
loaded = load_mesh(file_obj, file_type=file_type, resolver=resolver, **kwargs)
File "/home/junfeng/.local/lib/python3.8/site-packages/trimesh/exchange/load.py", line 191, in load_mesh
results = loader(file_obj, file_type=file_type, resolver=resolver, **kwargs)
File "/home/junfeng/.local/lib/python3.8/site-packages/trimesh/exchange/dae.py", line 52, in load_collada
c = collada.Collada(file_obj, ignore=ignores)
File "/home/junfeng/.local/lib/python3.8/site-packages/collada/init.py", line 204, in init
raise DaeMalformedError("XML Parsing Error: %s" % e)
collada.common.DaeMalformedError: DaeMalformedError: XML Parsing Error: Start tag expected, '<' not found, line 1, column 1 (, line 1)

my pycollada version is 0.6, urdfpy version is 0.0.22, lxml version is 4.9.3

@psh117 Setup docstrings, @cadop sphinx, and github actions for doctest

Also add all requirements.

Hi, I've run evaluation script and get the inference time for get 1000 samples for 1 target pose(set num_samples to 1000, num_references to 1). The time is 1.46s and my hardware is intel i7 cpu and T1000 gpu. Even though I changed to server with RTX8000 gpu, the time cost is still 1.1s, which seems to be much higher than that in paper(85ms for 1000 samples). Is there some time reduction trick?

Setup with actions and workflow

Training with an URDF model and (base link, target link)

Would it be okay to use ROS? I'm just worry about pypi packaging if I use the ROS packages in the nodeik.

We should clearly separate the code copied/example work from our own into separate python files.

Add optional USD loader instead of the warp URDF loader.