• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

Jeff-sjtu/sampling-argmax: Code for "Localization with Sampling-Argmax&quot ...

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

Jeff-sjtu/sampling-argmax

开源软件地址(OpenSource Url):

https://github.com/Jeff-sjtu/sampling-argmax

开源编程语言(OpenSource Language):

Python 99.5%

开源软件介绍(OpenSource Introduction):

Localization with Sampling-Argmax

[Paper] [arXiv] [Project Page]

Localization with Sampling-Argmax
Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-Lu Li, Cewu Lu
NeurIPS 2021


Differentiable Sampling

Requirements

  • Python 3.6+
  • PyTorch >= 1.2
  • torchvision >= 0.3.0

Install

  1. Install PyTorch
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0
  1. Install sampling_argmax
python setup.py develop

Fetch data

Please download data from MSCOCO, Human3.6M and MTFL. Download and extract them under ./data, and make them look like this:

|-- exp
|-- sampling_argmax
|-- configs
|-- data
`-- |-- coco
        |-- annotations
        |-- train2017
        `-- val2017
    |-- h36m
        |-- annotations
        `-- images
    |-- mtfl
    `-- |-- AFLW
        |---net_7876
        |---lfw_5590
        |-- training.json
        `-- testing.json

Train from scratch

# COCO Keypoint
./scripts/train_pose.sh configs/coco/256x192_res50_lr1e-3_1x-simple-integral.yaml coco_samp
# Human3.6M
./scripts/train_pose.sh configs/h36m/256x192_adam_lr1e-3-simple_3d_base_1x_h36mmpii.yaml h36m_samp
# MTFL
./scripts/train_mtfl.sh configs/mtfl/256x192_res50_lr1e-3_1x-mtfl-simple-integral.yaml mtfl_samp

Evaluation

# COCO Keypoint
./scripts/validate_pose.sh configs/coco/256x192_res50_lr1e-3_1x-simple-integral.yaml ${CKPT}
# Human3.6M
./scripts/validate_pose.sh configs/h36m/256x192_adam_lr1e-3-simple_3d_base_1x_h36mmpii.yaml ${CKPT}
# MTFL
./scripts/validate_mtfl.sh configs/mtfl/256x192_res50_lr1e-3_1x-mtfl-simple-integral.yaml ${CKPT}

Results

COCO Keypoint

Results on COCO validation set:

Method AP @0.5:0.95 AP @0.5 AP @0.75
Samp. Uni. 68.2 87.2 75.0
Samp. Tri. 69.8 87.9 76.2
Samp. Gau. 68.3 87.3 75.2

Human3.6M

Results on S9 and S11:

Method MPJPE PA-MPJPE
Samp. Uni. 49.6 39.1
Samp. Tri. 49.5 39.1
Samp. Gau. 50.9 39.0

MTFL

Results on MTFL:

Method Abs Rel
Samp. Uni. 3.00 6.86
Samp. Tri. 2.98 6.82
Samp. Gau. 2.94 6.96

If you find our code or paper useful, please consider citing

@inproceedings{li2021localization,
    title={Localization with Sampling-Argmax},
    author={Li, Jiefeng and Chen, Tong and Shi, Ruiqi and Lou, Yujing and Li, Yong-Lu and Lu, Cewu},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    year={2021}
}



鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap