Manu Mathew

+1 Kindly share the top-1 accuracy that you got and if possible the trained model as well.

Isn't this line taken from the MobilenetV1 paper? I couldn't find any such statement in the MobilenetV2 paper. I wonder if all parameters are to be decayed in MobileNetV2 training...

If you don't add a license file, it is difficult to use it freely. Please add a license file. If in doubt, please add this license file: https://github.com/BVLC/caffe/blob/master/LICENSE That will...

Please see the repository https://github.com/naver-ai/relabel_imagenet It shows impressive accuracy improvements with CutMix CutMix implementation: https://github.com/naver-ai/relabel_imagenet/blob/main/utils/data_augment.py#L54 It does mixing within the batch. This may be a simpler alternative to using multiple...

+1 for RetinaNet.

Thanks. I did a +1 for your feature request :)

Alternately, the correlation can be implemented with PyTorch code like the CorrelationLayer here: https://github.com/onlytailei/pytorch-flownet2/blob/master/nets/flownetC.py Not sure about its speed though.

Hi, I was wondering about the speedup compared to a pure PyTorch implementation (i.e. without C++/CUDA kernels). Do you have any idea? This is just out of curiosity - but...

Has any one tried both kind of losses together - i.e. some thing like: layer { name: "mbox_loss" type: "MultiBoxLoss" bottom: "mbox_loc" bottom: "mbox_conf" bottom: "mbox_priorbox" bottom: "label" top: "mbox_loss"...

It seems this has implemented Softmax Focal Loss, where as the original paper [RetinaNet](https://arxiv.org/pdf/1708.02002.pdf) paper descibed used of Sigmoid instead of Softmax to compute the p. (See equatioon 5 and...