environment problem "Torch not compiled with CUDA enabled" #2
Comments
|
I solved the above problem by replacing mamba with conda. However, the following problem occurred during training: (d3il2) silencht@silencht:~/d3il$ bash scripts/sorting_4_vision/ddpm_encdec_benchmark.sh
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'sorting_4_vision_config': Defaults list is missing `_self_`. See https://hydra.cc/docs/upgrades/1.0_to_1.1/default_composition_order for more information
warnings.warn(msg, UserWarning)
[2024-05-10 09:40:56,440][HYDRA] Launching 1 jobs locally
[2024-05-10 09:40:56,440][HYDRA] #0 : seed=0 agents=ddpm_encdec_vision_agent agent_name=ddpm_encdec_vision window_size=8 group=ddpm_encdec_vision_seeds
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.
warnings.warn(msg)
[2024-05-10 09:41:06,034][agents.models.diffusion.diffusion_models][INFO] - number of parameters: 3.748500e+05
[2024-05-10 09:41:08,968][root][INFO] - Loading Sorting Dataset
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:13<00:00, 7.15it/s]
[2024-05-10 09:41:23,006][root][INFO] - Loading Sorting Dataset
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:14<00:00, 6.76it/s]
[2024-05-10 09:41:37,937][agents.utils.scaler][INFO] - Datset Info: state min: [-2.87769967 -2.62087375] and max: [2.45655452 1.81934526], action min: [-1.65338498 -1.49557176] and max: [1.68398661 1.03862885]
[2024-05-10 09:41:37,937][agents.utils.scaler][INFO] - Training dataset size: input (33685, 2) target (33685, 2)
[2024-05-10 09:41:37,938][agents.base_agent][INFO] - The model has a total amount of 22769026 parameters
[2024-05-10 09:41:44,996][OpenGL.acceleratesupport][INFO] - No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
pybullet build time: Oct 14 2023 15:48:24
[2024-05-10 09:41:50,471][environments.d3il.d3il_sim.sims.sl][INFO] - No module named 'py_at_broker'
[2024-05-10 09:41:50,471][environments.d3il.d3il_sim.sims.sl][INFO] - No SL installed. SL simulation and control is not available.
25%|██████████████████████████████▊ | 1/4 [01:17<03:53, 77.82s/it][2024-05-10 09:44:16,325][simulation.sorting_sim][INFO] - Starting trained model evaluation
there are cpus: 16
196669 {0}
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/gym/spaces/box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 0 Rollout 0
p(m|c) tensor([[0., 0., 0., 0., 0., 0.]])
Successrate 0.0
entropy nan
KL nan
[2024-05-10 09:44:56,434][__main__][INFO] - New best success rate. Stored weights have been updated!
50%|█████████████████████████████████████████████████████████████▌ | 2/4 [03:05<03:11, 95.63s/it]/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/torch/utils/data/dataloader.py:554: UserWarning: This DataLoader will create 2 worker processes in total. Our suggested max number of worker in current system is 1, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(_create_warning_msg(
75%|████████████████████████████████████████████████████████████████████████████████████████████▎ | 3/4 [04:17<01:24, 84.47s/it][2024-05-10 09:47:19,052][simulation.sorting_sim][INFO] - Starting trained model evaluation
there are cpus: 16
196669 {0}
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 0 Rollout 0
p(m|c) tensor([[0., 0., 0., 0., 0., 0.]])
Successrate 0.0
entropy nan
KL nan
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [06:00<00:00, 90.16s/it]
[2024-05-10 09:47:51,342][__main__][INFO] - Training done!
[2024-05-10 09:47:51,431][agents.ddpm_encdec_vision_agent][INFO] - Loaded pre-trained model parameters
[2024-05-10 09:47:51,445][simulation.sorting_sim][INFO] - Starting trained model evaluation
there are cpus: 16
Start 0
pybullet build time: Oct 14 2023 15:48:24
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
Start 1
197409 {0}
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/gym/spaces/box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 0 Rollout 0
pybullet build time: Oct 14 2023 15:48:24
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
Start 2
197519 {1}
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/gym/spaces/box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 12 Rollout 0
pybullet build time: Oct 14 2023 15:48:24
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
Start 3
197550 {2}
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/gym/spaces/box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 24 Rollout 0
Context 24 Rollout 1
Context 0 Rollout 1
Context 12 Rollout 1
pybullet build time: Oct 14 2023 15:48:24
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
Start 4
197581 {3}
/home/silencht/anaconda3/envs/d3il/lib/python3.9/site-packages/gym/spaces/box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(
Context 0 Rollout 2
Final IK error (74 iterations): 7.2438426746618415e-06
Final IK error (0 iterations): 7.2438426746618415e-06
Context 36 Rollout 0
Context 24 Rollout 2
Context 12 Rollout 2
Context 24 Rollout 3
Context 0 Rollout 3
Context 36 Rollout 1
Context 12 Rollout 3
Context 0 Rollout 4
Context 24 Rollout 4
Context 36 Rollout 2
Context 12 Rollout 4
pybullet build time: Oct 14 2023 15:48:24
Context 24 Rollout 5
Context 0 Rollout 5
Context 36 Rollout 3
Context 12 Rollout 5
ROBOMIMIC WARNING(
No private macro file found!
It is recommended to use a private macro file
To setup, run: python /dprl/d3il/agents/models/robomimic/scripts/setup_macros.py
)
^CProcess SpawnProcess-9:So, what happened? How can I solve it? Looking forward to your reply asap. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thanks your awesome work ! I have a problem running my code, and shell log below:
The text was updated successfully, but these errors were encountered: