Ross Wightman

@ankmathur96 yeah, I noticed when I was doing my benchmarking in the past that most of the resnet/densenet models in torchvision were better with the default bilinear, but a number...

@JivanRoquet I'm not planning to do that, but others are working one it, this is a TF 2 version forked from here https://github.com/atomicbits/posenet-python. ... it also includes support for the...

@selzero it's still on the list of things to do (eventually), but not highest priority for me right now. One thing that makes it a little more work than I'd...

@JendonYuen it's good to see someone taking a crack at it, but would have been nice to have a reference back to this as he pretty much took my code...

@rigolepe looks good! so it's running with the ResNet50 model, what sort of framerate do you get with a modest GPU running the (non rendering) test?

@rigolepe thanks for the in depth numbers, the mobilenet numbers are a bit odd, I was seeing closer to double the performance for mobilenet 101 in the TF1 version, perhaps...

BTW, something that can easily be done in TF 2, that would have been a pain in the ass in TF 1 graph land is an optimization I made for...

@TKONIY This is one of several problems, see an earlier issue #8

Revisiting this. Google finally released their official version of MobileNet-V3 a few weeks ago now. It confirmed the known issues mentioned here and several more: https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet I have also validated...

@rebeen I have not seen a full implementation of the Mobilenetv3 AutoML search (platform aware NAS (MnasNet) + NetAdapt) that would reproduce these networks. The platform aware NAS is a...