From 773a300797d9d42ec199f15e8b43f3e9c1654116 Mon Sep 17 00:00:00 2001 From: KaiyangZhou Date: Mon, 12 Mar 2018 12:22:02 +0000 Subject: [PATCH] update readme --- README.md | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 7620043..f37f3c6 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,6 @@ This repo contains [pytorch](http://pytorch.org/) implementations of deep person We will actively maintain this repo. -## Pretrained models ## Prepare data Create a directory to store reid datasets under this repo via `mkdir data/`. @@ -31,7 +30,7 @@ htri: triplet loss with hard positive/negative mining [4]
#### Market1501 | Model | Size (M) | Loss | Rank-1 / -5 / -10 (%) | mAP (%) | Reported Rank | Reported mAP | -| :---: | :---: | :---: | :---: | :---: | :---: | :---: | +| --- | --- | --- | --- | --- | --- | --- | | ResNet50 [1] | 25.05 | xent | 85.8 / 94.4 / 96.3 | 70.1 | | | | ResNet50M [2] | 30.01 | xent | 88.8 / 95.3 / 97.0 | 74.4 | 89.9 / - / - | 75.6 | | DenseNet121 [3] | 7.72 | xent | | | | | @@ -39,6 +38,16 @@ htri: triplet loss with hard positive/negative mining [4]
### Video person reid #### MARS +## Pretrained models +You can use `wget` to download the following models. + +### Image person reid models +| Model | Loss | Download | +| --- | --- | --- | +| ResNet50 | xent | | +| ResNet50M | xent | | +| DenseNet121 | xent | | + ## References [1] [He et al. Deep Residual Learning for Image Recognition. CVPR 2016.](https://arxiv.org/abs/1512.03385)
[2] [Yu et al. The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching. arXiv:1711.08106.](https://arxiv.org/abs/1711.08106)