Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks

🤖 Plain-English Summary

To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). Our large FasterNet-L achieves impressive 83.5% top-1 accuracy, on par with the emerging Swin-B, while having 36% higher inference throughput on GPU, as well as saving 37% compute time on CPU.

🔑 Key Findings

• We observe that such reduction in FLOPs, however, does not necessarily lead to a similar level of re-duction in latency.
• This mainly stems from inefficiently low floating-point operations per second (FLOPS).
• To achieve faster networks, we revisit popular operators and demonstrate that such low FLOPS is mainly due to frequent memory access of the operators, especially the depthwise con-volution.

🔗 Related Resources