softened-similarity-learning icon indicating copy to clipboard operation
softened-similarity-learning copied to clipboard

Published 20 hours ago • verified publisher icon ryanaleksander

Memory vectors,parts and cameras

Open Cyongchun opened this issue 3 years ago • 5 comments

Hi! I have a question. Hope you can help me. In your config.ini , Train Data, there are three memory paths. But i don't have memory_vectors. I think it is saved after training. But your code need to load memory_vectors_path (memory_parts_path, memory_cameras_path) before training. How can i do this?

Cyongchun avatar Apr 01 '21 08:04 Cyongchun

You should be able to find the link to download the files in README. If you want to generate the files yourself just initiate the model with pretrained weights then run inference on the dataset. The model will return the corresponding vectors for each image for you to save. Good luck!

ryanaleksander avatar Apr 02 '21 05:04 ryanaleksander

Thank you so much!

Cyongchun avatar Apr 02 '21 05:04 Cyongchun

I 'm sorry to bother you. But I want the softened labels. How can I get this labels table? Because I can't see your codes that update the labels. Could you help me? Thank you!

Cyongchun avatar Apr 06 '21 01:04 Cyongchun

Softened labels are simply indices, each instance would have a different label. The Market1501Dataset class automatically returns the softened labels.

ryanaleksander avatar Apr 06 '21 05:04 ryanaleksander

hi. sorry to bother you. I have a question. hope you can help me. how can I generate camera.pth, vectors.pth and parts.pth that that are available in memory_table for another dataset (for example Duke dataset)?

RominaZakerian avatar Dec 09 '22 16:12 RominaZakerian