search

nilboy / tensorflow-yolo

tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test)
774 stars 312 forks source link

question about speed #13

Closed ywpkwon closed 7 years ago

ywpkwon commented 7 years ago

Thanks for sharing your work. I tried the demo.py and it seems to work fine. I think I could understand more about YOLO.

However, I am slightly curious why it takes quite long. One single image query took 116 sec (model load 0.4, inference 115.5, post-process 0). I am seeing 9 conv + 3 fc layers. It must be only feed-forward. Such size usually takes that long? Do you have any idea? Is it tensorflow problem?

nilboy commented 7 years ago

loading model takes most of the time

ywpkwon commented 7 years ago

However, for me, model loading was 0.4 sec, inference was 115.5 sec. This is unusual to you?

nilboy commented 7 years ago

loading model and constructing graph take most of the time, you should test 'sess.run(...)' time.