search

BarisYazici / deep-rl-grasping

Train deep reinforcement learning model for robotics grasping. Choose from different perception layers raw Depth, RGBD and autoencoder. Test the learned models in different scenes and object datasets
MIT License
192 stars 44 forks source link

Modified README to include GPU installing #17

Closed ManuCorrea closed 2 years ago

ManuCorrea commented 2 years ago

Hello I have included instructions with the proper cuda version to install the needed Tensorflow GPU libraries.

I have to say there is a weird bug when using this, I don't know if you faced this when using GPU training, but the gripper appears upside down.

BarisYazici commented 2 years ago

This looks really good thanks 👍 . Unfortunately, I can't test it cause at the moment I don't have access to the GPU machine.

ManuCorrea commented 2 years ago

Okay once you test it would be nice to know if you get the same bug as I do. Since all dependencies are fixed the upside down thing shouldn't happen. I want to dive deeper on this, I will probably also open an issue on PyBullet

BarisYazici commented 2 years ago

Okay once you test it would be nice to know if you get the same bug as I do. Since all dependencies are fixed the upside down thing shouldn't happen. I want to dive deeper on this, I will probably also open an issue on PyBullet

perfect thanks a lot for the work 👍