Ross Wightman

Remi is welcome to port into his style: https://github.com/rwightman/pytorch-image-models/blob/master/models/gen_efficientnet.py

Needs a padding hack to work well with the TF weights though

Right now you'd want to replace the contents of these two transform functions https://github.com/rwightman/efficientdet-pytorch/blob/master/effdet/data/transforms.py#L233-L275 to add own args with minimal changes. Likely the most I'd do right now this is...

@hamadichihaoui thanks for the contribution, I will evaluate the iou loss with my next training experiments before adding One question, the reference impl has a GPL license so code can...

@hamadichihaoui great, thanks for confirming. I'll update here when I get some results training on COCO.

@zlyin nope, no major updates, started looking at the code, paper but haven't finished either.

@rsomani95 that has been the goal, I did train one once (> 1 year ago) on a faster-rcnn type net w/ first version of my dataset code, but not with...

@jdsannchao no not yet, I only have 2x GPU machines free right now and it'd probably take close to two months for a decent sized model. Getting closer to the...

Thanks to the conversion code in this repository, I started on a path that ended up in a Python Tensorflow and PyTorch port of TFJS PoseNet. They both work on...

224 is not a legit resolution for posenet. In the original JS code, these are the legit resolutions... `export type PoseNetResolution = 161|193|257|289|321|353|385|417|449|481|513;` technically though, a resolution that is divisible...