search

loeweX / Greedy_InfoMax

Code for the paper: Putting An End to End-to-End: Gradient-Isolated Learning of Representations
https://arxiv.org/abs/1905.11786
MIT License
283 stars 36 forks source link

Pre-trained vision model? #19

Closed nikparth closed 3 years ago

nikparth commented 3 years ago

Hi! Is there a pre-trained vision model available somewhere? It would be really helpful instead of having to re-train the model from scratch.

Thanks! Nikhil

loeweX commented 3 years ago

Hi,

Luckily, I still had this model lying around somewhere - I've uploaded it here. Does this work for you?

Best, Sindy

nikparth commented 3 years ago

Hi yes that works great thank you very much!

Best, Nikhil

nikparth commented 3 years ago

Hi Sindy, Sorry to bother you again, but I downloaded the checkpoint but had not tried loading it in and I seem to be getting a "MemoryError" when using torch.load() with that checkpoint? I have more than enough memory, so I'm wondering what the issue might be- if you have any idea that would be great but if it's too much trouble the no worries, I'll just try training from scratch.

Thanks, Nikhil

loeweX commented 3 years ago

Hi Nikhil,

I'm afraid I cannot help you with that. I've tried it on my machine, and there things work without a problem.

Best, Sindy