Tyushang

Hi, I got a dataset of different keypoints from standard SMPL, and I want to use this dataset to train a net which output SMPL params. so I wonder Where...

Workload imbalance of clients(or SubprocessManager step not evenly over all envs).

1

I noticed the code in Subprocessmanager._queue_steps(): ``` def _queue_steps(self) -> None: print([w.worker_id for w in self.env_workers if not w.waiting]) # to debug. for env_worker in self.env_workers: if not env_worker.waiting: env_action_info...

Is it better to use self.step_queue.get() than self.step_queue.get_nowait() in SubprocessEnvManager._step()?

2

I noticed the code in SubprocessEnvManager._step(): ``` # Poll the step queue for completed steps from environment workers until we retrieve # 1 or more, which we will then return...

multiprocessing for inference and training, to make full use of CPU and GPU.

2

We are devoloping a basketball game, in which the policies(or agents, brains) are almost fixed in a game, say, 3 vs 3. In order to speedup the training process, we...

Not work on windows-11(with spacemacs)?

1

I followed the instruction of this project and https://github.com/cute-jumper/fcitx.el . But it doesn't work(I use emacs28.1 + spacemacs on windows-11). Don't this project support windows-11 or I missed something?

Where do J_regressor_extra/h36m.npy come from? and where do extra/h36m-keypoints locate in the human-body?

1

Hi, I got a dataset of different keypoints from standard SMPL, and I want to use this dataset to train a net which output SMPL params. so I wonder Where...