fps?

[wangzhegeek]

Have you test the fps in your computer?
when I run the eval.py, it is only 2.17samples/sec, this is too slow for light head? is it?

[TreB1eN]

@PCML-WangZhe I think 2 fps is quite fast indeed, what machine are you using btw

[TreB1eN]

@PCML-WangZhe The backbone is Resnet101, How fast would you think it could be ? In the original paper, resnet101 is used to prove its' performance, another xception like backbone is used for speed side.

[lucasjinreal]

@TreB1eN What does Xception speed got?

[wangzhegeek]

I know it is resnet101,but I think it should be faster than 2fps, because when I run faster rcnn which is writed with pytorch in the same machine(GTX 1080), the speed is almost 10fps, even though consider the image size problem ,I think light head should be more faster, but it is slower than faster rcnn right now, I don't know why

[TreB1eN]

@PCML-WangZhe what's the backbone, which repo, and test image size and proposals number in your comparison, this is not a speed oriented implementation, I dont think there is much point in discussing the speed here

[TreB1eN]

@jinfagang 100fps, according to the paper

[wangzhegeek]

the repo is https://github.com/jwyang/faster-rcnn.pytorch
the backbone is resnet101, proposal number is 300 when test, test size is 600, maxsize is 1200

[TreB1eN]

@PCML-WangZhe this repo Test size is 1000