Why the training process take up 100% CPU?

tnikolla / robot-grasp-detection

Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.

Apache License 2.0

238 stars 84 forks source link

Why the training process take up 100% CPU? #26

Closed edwardnguyen1705 closed 4 years ago

edwardnguyen1705 commented 5 years ago

Hi, Why the training process takes up 100% CPU? Does the calling the function distorted_inputs() cause that?

WuXingrui commented 4 years ago

I meet the same question，it seems that the gpu doesn't work in this job

edwardnguyen1705 commented 4 years ago

Hi @WuXingrui , just wait, I will upload a Pytorch implementation of the same paper.