Spaces:
Running
Running
What is the most appropriate inference time metric if input image sizes are so different?
1
#4 opened 5 months ago
by
Ouz-G
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64881e5bfb6ba030cb511a03/qJ0tDQczMxrHbprp2JWEi.jpeg)
Pareto frontier instead of line fit
#3 opened 5 months ago
by
Ouz-G
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64881e5bfb6ba030cb511a03/qJ0tDQczMxrHbprp2JWEi.jpeg)
Consider adding a field for Inference TFLOP/s
#2 opened 5 months ago
by
andrewlavin