train issue

[LPatstar]

thanks for opening-source
i follow your instructions but when i do python train.py i encounter the error below:

Importing module 'gym_38' (/home/robodog/isaacgym/python/isaacgym/_bindings/linux-x86_64/gym_38.so)
Setting GYM_USD_PLUG_INFO_PATH to /home/robodog/isaacgym/python/isaacgym/_bindings/linux-x86_64/usd/plugInfo.json
PyTorch version 2.2.2+cu121
Device count 1
/home/robodog/isaacgym/python/isaacgym/_bindings/src/gymtorch
Using /home/robodog/.cache/torch_extensions/py38_cu121 as PyTorch extensions root...
Emitting ninja build file /home/robodog/.cache/torch_extensions/py38_cu121/gymtorch/build.ninja...
Building extension module gymtorch...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/2] c++ -MMD -MF gymtorch.o.d -DTORCH_EXTENSION_NAME=gymtorch -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/include -isystem /home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/include/TH -isystem /home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/include/THC -isystem /home/robodog/miniconda3/envs/apex/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DTORCH_MAJOR=2 -DTORCH_MINOR=2 -c /home/robodog/isaacgym/python/isaacgym/_bindings/src/gymtorch/gymtorch.cpp -o gymtorch.o
[2/2] c++ gymtorch.o -shared -L/home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/lib -lc10 -ltorch_cpu -ltorch -ltorch_python -o gymtorch.so
Loading extension module gymtorch...
Setting seed: 39
Not connected to PVD
+++ Using GPU PhysX
Physics Engine: PhysX
Physics Device: cuda:0
GPU Pipeline: enabled
/home/robodog/miniconda3/envs/apex/lib/python3.8/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Preprocessed 1076 imitation data samples to GPU
Traceback (most recent call last):
File "legged_gym/scripts/train.py", line 47, in
train(args)
File "legged_gym/scripts/train.py", line 42, in train
ppo_runner, train_cfg = task_registry.make_alg_runner(env=env, name=args.task, args=args)
File "/home/robodog/txc/APEX/legged_gym/utils/task_registry.py", line 147, in make_alg_runner
runner = OnPolicyRunner(env, train_cfg_dict, log_dir, device=args.rl_device)
File "/home/robodog/txc/APEX/rsl_rl/rsl_rl/runners/on_policy_runner.py", line 61, in init
_, _ = self.env.reset()
File "/home/robodog/txc/APEX/legged_gym/envs/base/base_task.py", line 120, in reset
obs, privileged_obs, _, _, _ = self.step(torch.zeros(self.num_envs, self.num_actions, device=self.device, requires_grad=False))
File "/home/robodog/txc/APEX/legged_gym/envs/base/legged_robot.py", line 143, in step
self.post_physics_step()
File "/home/robodog/txc/APEX/legged_gym/envs/go2/go2.py", line 597, in post_physics_step
super().post_physics_step()
File "/home/robodog/txc/APEX/legged_gym/envs/base/legged_robot.py", line 324, in post_physics_step
self.compute_reward()
File "/home/robodog/txc/APEX/legged_gym/envs/go2/go2.py", line 544, in compute_reward
r = group_reward_functionsreward_name * group_reward_scales[reward_name]
File "/home/robodog/txc/APEX/legged_gym/envs/go2/go2.py", line 1218, in _reward_imitate_end_effector_pos
end_effector_target = torch.where(is_standing.unsqueeze(1), self.default_foot_pos_body_frame, end_effector_ref)
RuntimeError: The size of tensor a (12) must match the size of tensor b (0) at non-singleton dimension 1

[shivam-sood00]

Hey! Thanks for reaching out. The error was because param_config was referencing to the humanoid data in the last push. I have changed it back to refer to Go2. Let me know if the latest push works for you :-)