realtime_object_detection icon indicating copy to clipboard operation
realtime_object_detection copied to clipboard

Half FPS using tensorflow's official .pb file

Open charlielito opened this issue 7 years ago • 1 comments

There is something really weird happening to the execution times when using the official weights. If I use the frozen_graph.pb of this repo I get around 120 fps in my Laptop (A predator helios 300). BUT If I use the official frozen_grahp that you can download from this link I get only 60 FPS. That was using the split version, but the same behavior occurs not splitting the graph...

What kind of sorcery did you do to your weights? 0:

To reproduce this just download the weights from the link and replace them in the folder models

Pd: This pull request fixes the URL for the download of the mobilenet's weights.

charlielito avatar Jun 10 '18 02:06 charlielito

@charlielito To be honest i dont know the answer. My weights / my model is based on the ssd_mobilenet_v1 released in November 2017, how newer Versions perfom and why they might be slower is beyond my knowledge.

TF does a lot of changing and often its not for the better, thats all i know after working on this for 7 months :D

gustavz avatar Jun 11 '18 09:06 gustavz