Ross Wightman

@rsomani95 it's already implemented in the resnet.py and densenet.py models here. I didn't go further and add to more models because it does have a runtime penalty, but is often...

@timothylimyl thanks for the thoughtful issue, I do actually have plans for a v2 of scheduler and the argument handling would match your idea here. BUT I've held off because...

@ghoshaw @dsp6414 the model itself would be quick to put together, with a bit of fiddling to switch between deploy / train mode. This biggest issue though is that there...

@exnx scheduler will only depend on epoch number if you step once per epoch, if you use the per step lr update it'll change with the number of steps ......

@pfeatherstone I'm starting to work on object detection this summer. But I cannot bring in existing YOLO models, they are either GPL code + weights, or darknet based which is...

@pfeatherstone I believe it would be very difficult to apply GPL to the full specification of an architecture, especially since there are papers, and a mix of GPL and non-GLP...

@liangshi036 I do have an (eventual) plan to add support for BCE and/or MultiLabelSoft margin losses for use in multi-label tasks and include support for a suitable dataset. Have a...

@sowmen not on my list of things todo, but open to contributions

@banda-larga I was going to test the weights but they don't work, I've pinged one of the Google vit researchers to ask...

@etetteh yes, models work fine with arbitrary input channels but the data pipeline components are defaulted to RGB as they've really only been used with color images. The folder dataset...