open-reid
open-reid copied to clipboard
Cysu
Open source person re-identification library in python
Hello, do you have a weight model for re-identification of trained personnel?
Dear author, Thanks for your great work. It's really helpful to me who is new to this area. But I came across a problem when trying to adjust your code....
Hi, I'm trying to reproduce your benchmark on Market1501. For now, I successfully accomplished the Resnet50 both triplet and softmax, but when using inception module with softmax loss, I always...
Dear author: I think your work is wonderful, and this repository really helps a lot in person reid! But I have a few question. Why are you initialize the weights...
I can's see any advance since few month ago. I wondering that is this project managing or not.
Hi, Tong Xiao. I find that `sklearn.metrics.average_precision_score` has changed its behavior since version `0.19`. Previous versions (I have only tested 0.18.1) generate mAP identical to the code of [Market1501](http://www.liangzheng.org/Project/project_reid.html), while...
Hi, I try to implement the batch-all loss with this framework, modified from triplet.py, like: `from __future__ import absolute_import import torch from torch import nn from torch.autograd import Variable class...
I want to modify the file'/examples/triplet loss' and add some parameters into the trainer. I have modified the file 'reid/trainers' ``` criterion1 = nn.CrossEntropyLoss().cuda() criterion2 = TripletLoss(margin=args.margin).cuda() trainer = Trainer(model,criterion1,criterion2,factor1,factor2)...
