search

brjathu / iTAML

Official implementation of "iTAML : An Incremental Task-Agnostic Meta-learning Approach". CVPR 2020
96 stars 16 forks source link

Running without CUDA #16

Closed nlrahimi closed 4 years ago

nlrahimi commented 4 years ago

Thanks for the code and the amazing job you did to share the requirements and dependencies to facilitate running the model for community. I was able to run the code on a GPU-enabled Ubuntu 18.04. but could not run it without using GPU. I was wondering if we can run the model without using GPU.

Thanks

brjathu commented 4 years ago

Thank you very much :) Actually you can run but there are many parts in the code that assume GPU is available. You can find an replace .cuda() in the code to .cpu() everywhere. It should work, if it doesn’t please let us know.

nlrahimi commented 4 years ago

Great! I will modify it as suggested.

Bests