memory usage and fps on CPU-Only
seekingdeep opened this issue · comments
seekingdeep commented
@songqi-github
Your work shows potential, though somethings require clarification:
- How much memory and is required for inferencing a 1024 x 1024 image using only CPU?
- For cpu-only inferencing, what is the fps count for 1024*1024?
Qi Song commented
Hi, thanks for your attention.
Since all the real-time models are tested on a single GPU (such as GTX 1080Ti), we haven't tested our performance on the CPU. If you need, you can download AttaNet.py and test it on your environment. It is noted that there would be a relatively large gap in the inference time when using CPU for inferencing.
seekingdeep commented
Thank you,
i await the release of the full implementation and models.