Bag of Tricks and A Strong Baseline for Deep Person Re-identification
Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.
open-reid with PCB, IDE, triplet, ZJU; MOT/MTMCT feature extraction support included
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Rank-1 89% (Single Query) on Market1501 with raw triplet loss, In Defense of the Triplet Loss for Person Re-Identification, using Pytorch