torch-model-compression
torch-model-compression copied to clipboard
Does there any params and speed comparasion on common models?
Hi, does there any speed test on common models such as resnet50, YOLOv4 before and after compression? if there is a table indicates that would be very nice
Um, not yet. Since it varies among devices and flops percentages, it's a bit too hard to write a table for it.
@gdh1995 i think it's not need speed among different devices, just compare same model on same device, but before and after prune. That's enough convincing, otherwise not so convincing.