HumanFallDetection
HumanFallDetection copied to clipboard
FPS is very low
I ran the program on a MacBook m2 chip, the FPS is around 1 and 2. What is the cause behind this? Thanks
I guess it requires a good gpu to do the task?
The library is tested using CUDA-based GPUs on Ubuntu. Since we use PyTorch for the ML model, you should be able to run it using Apple's M1/M2 GPUs with MLP acceleration that provides an inference speedup of around 10x-20x.
Feel free to open up a PR if any changes are required to run the library on Apple M-chip GPUs!