search

tugstugi / dl-colab-notebooks

Try out deep learning models online on Google Colab
1.72k stars 465 forks source link

RuntimeError: CUDA out of memory. #29

Closed Ericksgeo closed 4 years ago

Ericksgeo commented 4 years ago

Hello, I am using the Semantic segmentation trained on ADE20K using CSAILVision/semantic-segmentation-pytorch. After some tests, I am having this RuntimeError: CUDA out of memory. I was reading about the bach size but I am not sure how your implementation deals with it, and how to change the code to accept a larger image. I am running the code in Colab.

Thanks for your help.

tugstugi commented 4 years ago

It is inferencing so batch size is 1. It sounds like you are using a too big image. Try to resize your image into smaller resolution and try again.