how to work with only 1 gpu.?

leftthomas / R2Plus1D-C3D

A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition" and CVPR 2014 paper "Learning Spatiotemporal Features with 3D Convolutional Networks"

59 stars 14 forks source link

how to work with only 1 gpu.? #2

Closed ramnamaqsood776 closed 5 years ago

ramnamaqsood776 commented 5 years ago

Hello Could you please guide me about the pre-trained model you used in your train file and can we run this code on only 1 gpu ? if yes, then how it is possible to use pre-trained model on 1 gpu only as whenever i change code according to my gpu it gives me error

RecursionError: maximum recursion depth exceeded while calling a Python object

leftthomas commented 5 years ago

@ramnamaqsood776 you should change code, this is a PyTorch question, you can reference the document of PyTorch