Kaiyang

that's a bit weird so if you save the pure weights of mobilenetv2, it'd be around 9M the 12M size might count the oprimizer's and scheduler's states but anyway, which...

what do you mean by how to save the .pth model? isn't it as simple as using `torch.save`?

please have a look at https://github.com/KaiyangZhou/deep-person-reid/issues?q=onnx and see if you can find anything useful I'll try to find some time to write a tutorial code since this issue has been...

too busy, sorry, don't count on me (my bad) does this help https://pytorch.org/docs/stable/onnx.html#example-alexnet-from-pytorch-to-onnx?

> Im confused where do I need to load the converted weight file. Would you please mark the palce I need to do it? First build the model with `model...

Hope you have solved the problem. This might help https://kaiyangzhou.github.io/deep-person-reid/user_guide.html#use-torchreid-as-a-feature-extractor-in-your-projects

it's an error from the pytorch code a simple google search on "RuntimeError: Couldn't open shared file mapping" should give you useful information https://github.com/pytorch/pytorch/issues/18797 https://github.com/pytorch/pytorch/issues/31874

sounds a good idea! I will keep this in mind will release them if available

We have released the pretrained models of three variants of osnet-ain, i.e. x0.75, x0.5 and x0.25. The model weights can be downloaded from https://kaiyangzhou.github.io/deep-person-reid/MODEL_ZOO. The code will automatically download the...

Setting `combineall=True` means the test data are seen during training so the 100% performance is useless Generalization across datasets is an open research problem for re-id Check our work towards...