A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
Hi guys, I have met an issue about running code on GPU. Firstly, I was running mainfer.py on my desktop computer, the GPU installed in the host is TitanX. And I have a laptop, which the GPU is 2070, but I found that the time of running one epoch even way longer than before, it was around one minute per epoch on desktop, but it's more than four minutes on my laptop. Is there anyone can help me what's wrong here?
Hi guys, I have met an issue about running code on GPU. Firstly, I was running mainfer.py on my desktop computer, the GPU installed in the host is TitanX. And I have a laptop, which the GPU is 2070, but I found that the time of running one epoch even way longer than before, it was around one minute per epoch on desktop, but it's more than four minutes on my laptop. Is there anyone can help me what's wrong here?