About speed of sfd and fan Inference

I tested the code on my nvidai k40 gpu，but both sfd and fan Inference are too slow. sfd=12s fan=3s around. May I know how fast you have tested ?
Thx.

The issue mentions slow inference times for SFD and FAN models on an NVIDIA K40 GPU. Start by checking the model loading and inference code in the repository, likely in the main inference scripts or model definitions. Look for any existing benchmarks or performance tests. Compare with the expected speeds by reviewing documentation or related issues. Profiling the inference step with tools like PyTorch profiler can identify bottlenecks.

Escrita pelo modelo de indexação a partir do texto da issue.