'RuntimeError: CUDA out of memory' on P100

[HalleyStarbun]

Hi there,

I'm using Colab Pro to do some ML experiments and often fail to initialise the RN50x4 CLIP model. Sometimes I even have trouble getting the RN101 model to load up. RN50x16 has never worked in my experience. The notebook is running on a P100 GPU and mentions that "x4 and x16 models for CLIP may not work reliably on lower-memory machines".

I'm just wondering if I need an even more capable GPU (in terms of VRAM) or if there is some problem with the code? I'm not an expert with Tensorflow/ML so apologies if there's a simple solution to this.

[somewheresy]

Hey there,

Both RN50x4 and the RN50x16 model are too big to run reliably on Google Colab's available runtimes. This is an option for people who have their own rigs with more RAM.

[HalleyStarbun]

Ah, sorry. The wording made it sound like it was possible on Colab. Thank you.