This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).
I really want to use your algorithm to detect object pose, however, I don't have GPU, but still want to try it on my normal laptop.
Is it possible? I believe there is way to change the codes so that it could work on CPU.
Currently, I am reading the code in valid.py in hope of making some modifications that make the program running on CPU, I also did make the program to run on 1 image only to reduce the total work load.
I have fixed some code of the project and executed it on CPU successfully, containing training model and validating it. You can contact me if you still want to try this idea.
Hello everyone,
I really want to use your algorithm to detect object pose, however, I don't have GPU, but still want to try it on my normal laptop.
Is it possible? I believe there is way to change the codes so that it could work on CPU.
Currently, I am reading the code in valid.py in hope of making some modifications that make the program running on CPU, I also did make the program to run on 1 image only to reduce the total work load.
Please give me some ideas,
Hope the best for you!