Encountered Nan problem while training a new robot about ikflow HOT 8 CLOSED

This is the loss curve

from ikflow.

Hi!

I'd first change nb_nodes to 12 - this will give you greater model capacity which improves performance and can also make training more stable (but also take longer, fyi).

Next, try reducing the learning rate. You can try 3.75*1e-4, 2.5*1e-4, 1.25*1e-4, 1e-5

Let me know how that goes!

• jeremy

from ikflow.

Thank you, Jeremy!
My training results are very good, you have been a big help to me!
btw, your code comments are very cute, making my coding less tedious :)

from ikflow.

Glad to hear it! What are you using IKFlow for if you don't mind me asking?

from ikflow.

I use it for a loco-manipulation project, and when I complete it better, I will share more details with you!

from ikflow.

Nice! sounds exciting.

If I could ask one more follow up - to do training have you created a new Robot subclass in the jrl package? Or have you changed the code around so you just use a presaved dataset of configuration/EE pose pairs

if it's the former (a new Robot subclass), would you consider adding it to the jrl package?

from ikflow.

I am very sorry for my delayed reply.
I previously implemented a class based on pytorch_kinematic for my project, which can calculate the forward and inverse kinematics of floating base robots. It is simply a transformation on the solution of a fixed base robot. Then, in order to adapt to ikflow, I also implemented methods such as save_dataset_to_disk and solution_pose_errors etc, and used my custom class to replace the Robot in the code.

So I'm sorry, I didn't make any valuable contribution to jrl package. It is a great tool that implements more features than pytorch_kinematic, thank you for your efforts!

from ikflow.

Got it, makes sense. Thanks, this helps me understand how others are using the code.

from ikflow.