Théo Morales

icon indicating a website link https://theomorales.com icon indicating an email [email protected]

icon company Trinity College Dublin icon location Dublin, Ireland icon location Postdoc researcher in 4D reconstruction. "What I cannot create, I do not understand" - Richard Feynman

Results 17 comments of Théo Morales

How sub_sample the weights?

Well I can't help you, I haven't tried it myself...

Loss quickly stabilizes around 8 and does not converge

Hi @MirzaAnoush, can you help me with the missing link definition ? Did you define one more or remove one ?

Loss quickly stabilizes around 8 and does not converge

Oh never mind I figured it out.

Loss quickly stabilizes around 8 and does not converge

Yes I am training it (with transfer learning) on my custom dataset. I am unsure why I obtain a lot of predicted coordinates outside the image though...

Loss quickly stabilizes around 8 and does not converge

> @M4gicT0 I want to try train the model on my dataset that have two classes, can you tell me how to sub-sample the weight tensors of all the classification...

music progress time shows random numbers

You sure you didn't forget `ipv.start();` right after that ?

Log leak from on_unmount when run_async is used

I'm having the same problem where I need to run the app with `run_async()` because I want to run some code which interacts with my TUI: ```python async def launch_with_async_gui():...