Which GPU works when running CNN?

Question 1: Is there only one GPU working when running CNN and which GPU is working.
Question 2: I trained the network on my computer to generate the model. I run the model on PX2 to predicted. The predicting time is up to 14 minutes. I want to know why?


Q1: You should be able to access both GPUs. So it depends on how your program implemented.

Q2: Not sure what kind of frameworks do you use. It’s recommended to update your model into TensorRT for a better performance.


Question1: What is the difference between DRIVE PX 2 AutoChauffeur and NVIDIA Tegra X2?

Question2: Which GPU works when I running predict models?

Question3: Why the totalMemory of NVIDIA Tegra X2 is 6.25GiB but the freeMemory is only 2.63GiB.

Here is the program running tips:

name: DRIVE PX 2 AutoChauffeur major: 6 minor: 1 memoryClockRate(GHz): 1.29
pciBusID: 0000:04:00.0
totalMemory: 3.75GiB freeMemory: 3.68GiB

name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.275
pciBusID: 0000:00:00.0
totalMemory: 6.25GiB freeMemory: 2.63GiB