smlbansal / visual-navigation-release Goto Github PK
View Code? Open in Web Editor NEWCombining Optimal-Control and Learning for Visual Navigation in Novel Environments
Home Page: https://smlbansal.github.io/LB-WayPtNav/
Combining Optimal-Control and Learning for Visual Navigation in Novel Environments
Home Page: https://smlbansal.github.io/LB-WayPtNav/
I have followed the instruction and established the environment successfully.
When I run the command PYOPENGL_PLATFORM=egl PYTHONPATH='.' python executables/rgb/resnet50/rgb_waypoint_trainer.py test --job-dir reproduce_LB_WayptNavResults --params params/rgb_trainer/reproduce_LB_WayPtNav_results/rgb_waypoint_trainer_finetune_params.py -d 0
I got an Error:
ERROR:root:Loading building from obj file: /media/omnisky/zty_Passport/Data/LB-WayPtNav/LB_WayPtNav_Data_Public/stanford_building_parser_dataset/mesh/area1/5acd38aa86ea42028a265d20947754f5.obj
ERROR:root:#Meshes: 195
WARNING:OpenGL.arrays.numpymodule:Unable to load numpy_formathandler accelerator from OpenGL_accelerate
Terminated
some times I also got results:
ERROR:root:Loading building from obj file: /media/omnisky/zty_Passport/Data/LB-WayPtNav/LB_WayPtNav_Data_Public/stanford_building_parser_dataset/mesh/area1/5acd38aa86ea42028a265d20947754f5.obj
ERROR:root:#Meshes: 195
WARNING:OpenGL.arrays.numpymodule:Unable to load numpy_formathandler accelerator from OpenGL_accelerate
Exception ignored in: <bound method SwiftshaderRenderer.del of <mp_env.render.swiftshader_renderer.SwiftshaderRenderer object at 0x7f30c01b7b38>>
Traceback (most recent call last):
File "/media/omnisky/zty_Passport/Data/LB-WayPtNav/Visual-Navigation-Release/mp_env/render/swiftshader_renderer.py", line 499, in del
File "/media/omnisky/zty_Passport/Data/LB-WayPtNav/Visual-Navigation-Release/mp_env/render/swiftshader_renderer.py", line 495, in clear_scene
File "latebind.pyx", line 32, in OpenGL_accelerate.latebind.LateBind.call (src/latebind.c:989)
File "wrapper.pyx", line 311, in OpenGL_accelerate.wrapper.Wrapper.call (src/wrapper.c:6439)
File "/home/omnisky/anaconda3/envs/venv-mpc/lib/python3.6/site-packages/OpenGL/platform/baseplatform.py", line 401, in call
File "/home/omnisky/anaconda3/envs/venv-mpc/lib/python3.6/site-packages/OpenGL/platform/baseplatform.py", line 381, in load
ImportError: sys.meta_path is None, Python is likely shutting down
environment :
I have tried running under CPU only mode, but failed.
What should I do next?
Hello everyone.
I have successfully trained the code on my computer. But I have some questions, how can I use this code's CNN for visual navigation in my robotic hardware?
I'm learning ROS and this code recently, but I can't think of a way. So I wanted to ask other researchers, how did you use this code for visual navigation on robotic hardware?
Thank you very much.
I have followed the instruction and established the environment successfully.
When I run the command“PYOPENGL_PLATFORM=egl PYTHONPATH='.' python executables/run_all_tests.py”.
I got an Error:
` File "/home/zhangmuzhi/Visual-Navigation-Release-master/mp_env/sbpd.py", line 52, in load_building_meshes
mesh_file_name = glob.glob1(dir_name, '*.obj')[1]
IndexError: list index out of range
Execution time for test test_obstacle_objective.py is 2 seconds.
Test failed: test_obstacle_objective.py`
What should I do next?
Hi,
While reproducing the model based method results, I am getting the following error:
ValueError: ('numpy.ufunc has the wrong size, try recompiling', 2, <OpenGL.platform.baseplatform.glGetShaderiv object at 0x7f6538094900>)
This is a result of running the following commands from the read me file:
PYOPENGL_PLATFORM=egl PYTHONPATH='.' python executables/rgb/resnet50/rgb_waypoint_trainer.py test --job-dir reproduce_LB_WayptNavResults --params params/rgb_trainer/reproduce_LB_WayPtNav_results/rgb_waypoint_trainer_finetune_params.py -d 0
I would appreciate your support in this regard. Thanks!
Firstly, thank you for your brilliant work!
Followed your instruction here, we successfully build the environment. When we Run the Tests, the following error occurs, albeit we have checked that the .obj files are intact. We even replaced the provided .obj files with the files download directly from here, the same error is still there.
Do you have any suggestions? Thank you.
Environment:
PYOPENGL_PLATFORM=egl PYTHONPATH='.' python executables/run_all_tests.py
======================================================================
Running test test_dynamics.py
rerun with visualize=True to visualize the test
rerun with visualize=True to visualize the test
Execution time for test test_dynamics.py is 2 seconds.
======================================================================
======================================================================
Running test test_cost_function.py
ERROR:root:Loading building from obj file: /home/developer/CodeSpace/Visual-Navigation-Release/data/LB_WayPtNav_Data/stanford_building_parser_dataset/mesh/area3/41a8012778ff4fc1800a7794bd15d81e.obj
ERROR:root:#Meshes: 90
Exception ignored in: <bound method Shape.__del__ of <mp_env.render.swiftshader_renderer.Shape object at 0x7faa3c9a0e10>>
Traceback (most recent call last):
File "/home/developer/CodeSpace/Visual-Navigation-Release/mp_env/render/swiftshader_renderer.py", line 157, in __del__
File "/home/developer/anaconda3/envs/venv-mpc/lib/python3.6/site-packages/pyassimp/core.py", line 351, in release
ImportError: sys.meta_path is None, Python is likely shutting down
Execution time for test test_cost_function.py is 12 seconds.
======================================================================
======================================================================
Running test test_coordinate_transform.py
Traceback (most recent call last):
File "/home/developer/CodeSpace/Visual-Navigation-Release/tests/test_coordinate_transform.py", line 179, in <module>
test_rotate()
File "/home/developer/CodeSpace/Visual-Navigation-Release/tests/test_coordinate_transform.py", line 44, in test_rotate
new_pos_112 = rotate_pos_nk2(pos_112, theta_111)
File "/home/developer/CodeSpace/Visual-Navigation-Release/utils/angle_utils.py", line 22, in rotate_pos_nk2
pos_rot_nk2 = tf.matmul(rot_matrix_nk22, pos_nk2[:, :, :, None])[:, :, :, 0]
File "/home/developer/anaconda3/envs/venv-mpc/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1980, in matmul
a, b, adj_x=adjoint_a, adj_y=adjoint_b, name=name)
File "/home/developer/anaconda3/envs/venv-mpc/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1261, in batch_mat_mul
_six.raise_from(_core._status_to_exception(e.code, message), None)
File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InternalError: Blas xGEMV launch failed : a.shape=[1,2,2], b.shape=[1,2,1], m=2, n=1, k=2 [Op:BatchMatMul] name: MatMul/
Execution time for test test_coordinate_transform.py is 2 seconds.
======================================================================
Test failed: test_coordinate_transform.py
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.