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

How to get the file "saved_meshes/robot_state_kinematic_val.json" #3

Open
p1ckpep opened this issue May 29, 2023 · 3 comments
Open

Comments

@p1ckpep
Copy link

p1ckpep commented May 29, 2023

Hello, I am learning your significant repo, I succeeded to train your visual self-model and get the robot_state.json, but I have a problem when I run your command in "Training" part of "To use our pre-trained self-model to train a small network to predict end-effector position", it seems that there's no file named "robot_state_kinematic_val.json", and I'm new to learn Deep Learing, so could you help me how to generate that file?
logs:
(env-visual-selmodeling) $ CUDA_VISIBLE_DEVICES=0 python ../main.py ../configs/state_condition_kinematic/config1.yaml kinematic ./logs_state-condition_new-global-siren-sdf_1/lightning_logs/version_0/checkpoints/
{'coord_system': 'cartesian',
'data_filepath': '../saved_meshes',
'dof': 4,
'epochs': 1000,
'gamma': 0.5,
'if_cuda': True,
'log_dir': 'logs',
'loss_type': 'siren_sdf_kinematic',
'lr': 0.0009,
'lr_schedule': [10000000],
'model_name': 'state-condition-kinematic',
'num_gpus': 1,
'num_workers': 8,
'seed': 1,
'tag': 'new-global-siren-sdf',
'task_batch': 9600,
'test_batch': 4500,
'train_batch': 4500,
'val_batch': 4500}
Global seed set to 1
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
Traceback (most recent call last):
File "../main.py", line 173, in
main_kinematic()
File "../main.py", line 118, in main_kinematic
trainer.fit(model)
File "/data/lwh22/anaconda3/envs/env-visual-selmodeling/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 458, in fit
self.call_setup_hook(model)
File "/data/lwh22/anaconda3/envs/env-visual-selmodeling/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 1066, in call_setup_hook
model.setup(stage_name)
File "/data/lwh22/hust_pj/visual-selfmodeling/models.py", line 204, in setup
pointcloud_folder=self.hparams.data_filepath)
File "/data/lwh22/hust_pj/visual-selfmodeling/dataset.py", line 97, in init
self.robot_state_dict = self.load_robot_state()
File "/data/lwh22/hust_pj/visual-selfmodeling/dataset.py", line 134, in load_robot_state
with open(robot_state_filepath, 'r') as file:
FileNotFoundError: [Errno 2] No such file or directory: '../saved_meshes/robot_state_kinematic_val.json'

@iamlilAJ
Copy link

Hi, I encountered similar issues.

It can be resolved by modifying the directory in the config1.yaml.

@MoeHH
Copy link

MoeHH commented Jul 3, 2024

Hello there,

I am facing an issue with executing the following command "CUDA_VISIBLE_DEVICES=0 python ../main.py ../configs/state_condition_kinematic/config1.yaml kinematic ./logs_state-condition_new-global-siren-sdf_1/lightning_logs/version_0/checkpoints/;" as it required robot_state_kinematic_val.json as the following error "FileNotFoundError: [Errno 2] No such file or directory: '../saved_meshes/robot_state_kinematic_val.json'".

The robot_state_kinematic_val.json file is not generated or saved at the Saved_meshes folder. Please can you advise?

Thanks

@iamlilAJ
Copy link

iamlilAJ commented Jul 4, 2024

Hi, I am not sure but you may need to run the first command to generate "cd scripts;
CUDA_VISIBLE_DEVICES=0 python ../main.py ../configs/state_condition/config1.yaml NA;"

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