Question about using pytorch-tcn vs. keras-tcn

Hi everyone :waving_hand:

I’m currently experimenting with Temporal Convolutional Networks (TCN) and I wanted to ask:

Has anyone here used the pytorch-tcn implementation?
Is it considered reliable or effective for sequence modeling tasks?

Also, I tested the same model architecture and hyperparameters using:
• keras-tcn
• pytorch-tcn

However, I got noticeably different results between the two.

What could be the cause of this mismatch?

Any insights or tips would be greatly appreciated!

Thanks