questions about inference fps about aot-benchmark HOT 7 CLOSED

Sorry, but I am still confused about the speed, in model zoo , AOTS has around 40 FPS and AOTT 50 FPS in DAVIS-VOS as marked in the following picture.

from aot-benchmark.

@xinyeCH I update the code about result saving. At present, the result saving happens after the inference of each sequence instead of each frame.

The speed should be faster on your device.

from aot-benchmark.

@xinyeCH One more update. Currently, the evaluator call torch.cuda.synchronize() only once. After the inference of each sequence, I synchronize all the frame timers (start and end). The influence of slow CPU and storage devices should be negligible now.

I evaluated the new code on a V100 device with slow storage, maybe like your device, the speed results are slightly faster than the reported results now (AOTS: 41fps now, 33fps before).

from aot-benchmark.

@z-x-yang Thanks for your reply.

I updated the evaluator.py according to your newest commit and modified some hyperparameters of dataloader such as worker numbers. FPS of AOTS is about 34 now and AOTT 45.

I think the difference between my testing result and paper maybe comes from computer environment.

from aot-benchmark.

@xinyeCH Could try to use a single GPU in the inference?

from aot-benchmark.

@z-x-yang Sorry for the late reply. Yes, I use only one V100 during inference. Using 2 gpus gets worser performance.

from aot-benchmark.

OK. If your cpu is strong enough, using multiple gpus should not make speed slower.

from aot-benchmark.