Results 37 comments of Vladimir Somers

Sorry but I don't know how to do this. There's probably some ways to reduce apk size, but you'll have to search the web for more answers :-) If you...

Sorry for these issues, I hope you're going to find some answers!

Thanks for sharing this. The template wad indeed intended to be used in landscape mode: I didn't try to make it work in portrait mode. If you find a easy/elegant...

Hi @onvungocminh, usually the confidence score is the first value from the second dimension, if you just keep the first value of that second dimension with [:, 0], you should...

Hi @hh23333 , can you share your full configuration?

Hi @hh23333, sorry for the delayed answer, I was looking into my old Wandb experiments to find which hyperparameters changed, here are some stuff you can try: change 'bn_foreg' for...

Hi @hh23333 , this is strange you have a much better rank-1 than what is reported in the paper while still having 1% less mAP. The experiments with ResNet-50 comes...

Hi @frandoLin, indeed, a reid module produces a feature embeddings for each input image (multi part-based embeddings in the case of BPBreID). You can then use these embeddings to perform...

Hi @MatUhrin, thank you! Unfortunately, I don't have any expertise with ONNX and therefore I don't know how difficult it would be to export the model to it. Feel free...

Hi @yimingz1218 , sorry for answering this late, have you found an answer to your question? If you run the codebase and set the "test.visrank" value to True, an image...