Is the inference time of the model related to the parameter quantity of the model?

[InstantWindy]

How do you calculate the GFLOPS of a model? The less the parameter quantity of the model, the shorter the inference time of the model?

[akirasosa]

I have rewrite code using PyTorch. It looks that there are some tools to calculate GFLOPS in PyTorch.

• https://github.com/Lyken17/pytorch-OpCounter

The less the parameter quantity of the model, the shorter the inference time of the model?

Generally speaking, Yes. Please take a look at my article about more detail. Real-Time deep learning in mobile application