gkahn13 / badgr Goto Github PK

View Code? Open in Web Editor NEW

146.0 146.0 42.0 1.02 MB

License: MIT License

Python 100.00%

badgr's People

Contributors

Stargazers

Watchers

badgr's Issues

Anaconda for arm64

Where did you get the info on how to install Anaconda on the TX2? I'd like to build and test this on an Xavier but there no no repo for Anaconda for arm64 that I can find.

ValueError: Weights for model sequential_1 have not yet been created. Weights are created when the Model is first called on inputs or `build()` is called with an `input_shape`.

I get this when I try to run
python scripts/train.py configs/collision_position.py

I have tensorflow 1.15 and cuda 10.1

Thanks,
Jason.

Licence?

Hi!

Many thanks for sharing the code! I'm looking forward to feature it in one of the Weekly Robotics issue.

I might have missed it but I didn't find any information about the Licence for this project. Would you be able to add it at one point?

about the tfrecords

How can I generate these tfrecord files myself?
So I don't need to download it...

Hi, thank you for sharing the code and instructions. Is the script to collect/generate the dataset on the robot included in the repo? I mean the script to generate *.tfrecord files. I couldn't find anything about it in the repo.

Cheers,
Ebrahim

ModuleNotFoundError: No module named 'geometry_msgs'

I think I strictly followed the operation written in the README, and when the execution reached the Evaluation stage, when I ran python scripts/eval.py configs/bumpy_collision_position.py of code, an error was reported:

FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/lizehao/anaconda3/envs/badgr/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/lizehao/anaconda3/envs/badgr/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/lizehao/anaconda3/envs/badgr/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/lizehao/anaconda3/envs/badgr/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/lizehao/anaconda3/envs/badgr/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
  File "scripts/eval.py", line 22, in <module>
    params = import_config(config_fname)
  File "/mnt/c/Users/LZH/Desktop/badgr/src/badgr/utils/python_utils.py", line 15, in import_config
    spec.loader.exec_module(config)
  File "<frozen importlib._bootstrap_external>", line 678, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/mnt/c/users/lzh/desktop/badgr/configs/bumpy_collision_position.py", line 6, in <module>
    from badgr.jackal.envs.jackal_env import JackalEnv
  File "/mnt/c/Users/LZH/Desktop/badgr/src/badgr/jackal/envs/jackal_env.py", line 11, in <module>
    from geometry_msgs.msg import Pose2D
ModuleNotFoundError: No module named 'geometry_msgs'

How can I fix it?

Issue Accessing Dataset Download Link

Hi,

I attempted to access the dataset download link provided in the BADGR project repository, but I encountered a 404 error (page not found). Could you please verify if the link is still active or provide an alternative link to download the dataset?

Thank you for your assistance!

Some typo in the paper

By checking the source code of the badgr, I found the MPPI planner generates the actions using:

action_h = self._beta * (shifted_mean[h, :] + eps[:, h, :]) + (1. - self._beta) * actions[-1]

So I think there is a typo in the paper Eqn. 3, which is

I guess it may be

Dataset link not functional

Thank you for your amazing work. I am trying to replicate the results but the Google drive link gives a 404 error. Could you please provide an alternative link.

class YAMLObject(metaclass=YAMLObjectMetaclass): ^ SyntaxError: invalid syntax

Hi,
when I met the OpenCV problem as the author mentioned at the end of readme.md file, I did as the author told us what to do. However, after exporting PYTHONPATH, I have a new problem like this.

Traceback (most recent call last):
  File "/opt/ros/kinetic/bin/rosparam", line 34, in <module>
    import rosparam
  File "/opt/ros/kinetic/lib/python2.7/dist-packages/rosparam/__init__.py", line 63, in <module>
    import yaml
  File "/home/jio/anaconda2/envs/badgr/lib/python3.6/site-packages/yaml/__init__.py", line 374
    class YAMLObject(metaclass=YAMLObjectMetaclass):
                              ^
SyntaxError: invalid syntax

I guess there are some incompatible problems between ROS and Python3. I am stuck now. Can anyone help me?

Thanks!

gkahn13 / badgr Goto Github PK

badgr's People

Contributors

Stargazers

Watchers

Forkers

badgr's Issues

Recommend Projects

Recommend Topics

Recommend Org