Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

pretrained models #1

Closed
st2yang opened this issue Jun 17, 2020 · 5 comments
Closed

pretrained models #1

st2yang opened this issue Jun 17, 2020 · 5 comments

Comments

@st2yang
Copy link

st2yang commented Jun 17, 2020

Hi,

Thanks for your great work! And I am trying to reproduce/benchmark your results. Would you mind sharing the pre-trained models for evaluation?

Thanks,
Yang

@matwilso
Copy link
Owner

Hi, sorry, I don't have the pre-trained weights anymore. I had to clean a bunch of stuff off my hard drive awhile ago.

@st2yang
Copy link
Author

st2yang commented Jun 22, 2020

Sure, I'll try to train the models on my own.

I tried to install the environment properly but encountered one issue while running the scripts. Can you help a little? I am wondering how you set up the bashrc to run the scripts?

I can run with standard mujoco/gym environments. But when I run your scripts, it raises the following errors. It looks like the issue here mujoco issue. But I haven't properly set up my bashrc so far. I also attached my bashrc below.

Thanks,
Yang

bashrc

export LD_LIBRARY_PATH=/homes/yangyang/.mujoco/mujoco200/bin${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export MUJOCO_KEY_PATH=/homes/yangyang/.mujoco${MUJOCO_KEY_PATH}
export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libGLEW.so
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia-000

running data_collections scripts

running algorithm
Found 1 GPUs for rendering. Using device 0.
Found 1 GPUs for rendering. Using device 0.
Could not make EGL context current
Found 1 GPUs for rendering. Using device 0.
Could not make EGL context current
Exception in thread Thread-2:
RuntimeError: Failed to initialize OpenGL

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/threading.py", line 916, in _bootstrap_inner
self.run()
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/rl/trainer.py", line 548, in rollout_maker
rollouts = self.roller.rollouts()
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/rl/rollers.py", line 212, in rollouts
self.reset()
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/rl/rollers.py", line 202, in reset
self._last_obs.append(self.batched_env.reset_wait(sub_batch=i))
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/site-packages/anyrl/envs/base.py", line 207, in reset_wait
obses.append(env.reset_wait())
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/site-packages/anyrl/envs/gym.py", line 108, in reset_wait
res = self._decode_observation(self._get_response())
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/site-packages/anyrl/envs/gym.py", line 145, in _get_response
raise RuntimeError('exception on worker') from resp_obj
RuntimeError: exception on worker

Could not make EGL context current

running the evaluation script

Found 1 GPUs for rendering. Using device 0.
Could not make EGL context current
Traceback (most recent call last):
File "./eval_main.py", line 102, in
main()
File "./eval_main.py", line 99, in main
eval_policy()
File "./eval_main.py", line 48, in eval_policy
obs = env.reset()
File "/homes/yangyang/miniconda3/envs/coll/lib/python3.6/site-packages/gym/wrappers/time_limit.py", line 44, in reset
return self.env.reset()
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/envs/object_env.py", line 326, in reset
self.goal = self._sample_goal()
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/envs/object_env.py", line 469, in _sample_goal
obs = self._get_obs()
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/envs/object_env.py", line 124, in _get_obs
image = self._get_cam_frame().astype(np.float32)
File "/homes/yangyang/PycharmProjects/Collections/object_collections/object_collections/envs/base.py", line 54, in _get_cam_frame
cam_img = self.sim.render(width, height, camera_name='camera1')[::-1, :, :] # Rendered images are upside-down.
File "mujoco_py/mjsim.pyx", line 156, in mujoco_py.cymj.MjSim.render
File "mujoco_py/mjsim.pyx", line 158, in mujoco_py.cymj.MjSim.render
File "mujoco_py/mjrendercontext.pyx", line 46, in mujoco_py.cymj.MjRenderContext.init
File "mujoco_py/mjrendercontext.pyx", line 114, in mujoco_py.cymj.MjRenderContext._setup_opengl_context
File "mujoco_py/opengl_context.pyx", line 130, in mujoco_py.cymj.OffscreenOpenGLContext.init
RuntimeError: Failed to initialize OpenGL

@st2yang
Copy link
Author

st2yang commented Jun 25, 2020

I managed to set up bashrc to run the code.

@st2yang st2yang closed this as completed Jun 25, 2020
@madhan001
Copy link

@st2yang what were the exact changes you did to bashrc to fix this error?

@st2yang
Copy link
Author

st2yang commented Jul 3, 2020

@madhan001 This is my modified bashrc

export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/homes/yangyang/.mujoco/mujoco200/bin
export MUJOCO_KEY_PATH=/homes/yangyang/.mujoco${MUJOCO_KEY_PATH}
export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libGLEW.so

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants