【人脸检测】Tencent之FaceDetection-DSFD测试与评估复现

水深无声 2022-12-24 13:00 190阅读 0赞

参考

[https://paperswithcode.com/paper/dsfd-dual-shot-face-detector][https_paperswithcode.com_paper_dsfd-dual-shot-face-detector]

[https://github.com/Tencent/FaceDetection-DSFD][https_github.com_Tencent_FaceDetection-DSFD]

[https://arxiv.org/pdf/1810.10220.pdf][https_arxiv.org_pdf_1810.10220.pdf]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM1OTc1NDQ3_size_16_color_FFFFFF_t_70][]

# 0.环境 #

ubuntu16.04
    python3.6
    torch==0.4.1 # (cuda90)  @ https://download.pytorch.org/whl/cu90/torch-0.4.1-cp36-cp36m-linux_x86_64.whl
    cycler==0.10.0
    kiwisolver==1.3.1
    matplotlib==3.3.3
    numpy==1.19.4
    opencv-python==4.4.0.46
    Pillow==8.0.1
    pyparsing==2.4.7
    python-dateutil==2.8.1
    PyYAML==5.3.1
    scipy==1.2.0
    six==1.15.0
    torchvision==0.2.2
    tqdm==4.19.9
    Cython
    ipython

# 1.修改 #

（1）ImportError: cannot import name 'pa\_sfd\_match'

# FaceDetection-DSFD-master\layers\modules\multibox_loss.py line 13
    from ..box_utils import (log_sum_exp, match, pa_sfd_match, refine_match,
                             sfd_match)
    改为
    from ..box_utils import (log_sum_exp, match, sfd_match, refine_match,
                             sfd_match)

（2）模型下载

[https://download.pytorch.org/models/resnet152-b121ed2d.pth][https_download.pytorch.org_models_resnet152-b121ed2d.pth]

（3）数据下载

[http://shuoyang1213.me/WIDERFACE/][http_shuoyang1213.me_WIDERFACE]

![20201130100019583.png][]

wget http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/support/bbx_annotation/wider_face_split.zip

分别解压在widerface目录下，文件目录：

widerface
        wider_face_split
        WIDER_test
        WIDER_train
        WIDER_val

（4）widerface\_val.py修改

# about cuda device
    
    # line 41 add
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    
    # line 230
    net.load_state_dict(torch.load(args.trained_model, map_location='cpu'))
    net.to(device)
    
    # line 61-67
    x = Variable(x.to(device), volatile=True)
    #net.priorbox = PriorBoxLayer(width,height)
    y = net(x)
    detections = y.data
    scale = torch.Tensor([width, height, width, height])
    
    #改为：
    
    with torch.no_grad():
            x = Variable(x.to(device))
    
            #net.priorbox = PriorBoxLayer(width,height)
            y = net(x)
            detections = y.data
            scale = torch.Tensor([width, height, width, height])
            torch.cuda.empty_cache()

# 2.测试 #

## 2.1 测试 ##

测试大概需要7-8G显存。

CUDA_VISIBLE_DEVICES=0 python widerface_val.py --trained_model ./weights/WIDERFace_DSFD_RES152.pth --save_folder ./results/ --widerface_root ./data/widerface/ --cuda=True

## 2.2 测试结果 ##

跟Retinaface\_Pytorch中类似，都是将测试结果写到一个文件中，最后再通过之前用过的Retinaface\_Pytorch中的评估对几项指标统计。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM1OTc1NDQ3_size_16_color_FFFFFF_t_70 1][]

# 3.评估 #

## 3.1 评估 ##

由于这里没有对应的gt（mat文件），所以这里参考SRN中，根据对应的目录结构，复制与新建对应文件。目录结构如下：

tools
        box_overlaps.c  #这四个文件复制自Pytorch_Retinaface
        box_overlaps.pyx  
        evaluation.py  
        setup.py 
        widerface_eval #复制自SRN
        results #复制自本方法测试后结果，在根目录下

修改evaluation.py（line 287-288）:

parser.add_argument('-p', '--pred', default="./results/")
    parser.add_argument('-g', '--gt', default='./widerface_eval/ground_truth/')

cd ./tools
    python setup.py build_ext --inplace

## 3.2 评估结果 ##

cp -r results/ ./tools/
    python evaluation.py

![2020120120225283.png][]

[https_paperswithcode.com_paper_dsfd-dual-shot-face-detector]: https://paperswithcode.com/paper/dsfd-dual-shot-face-detector
[https_github.com_Tencent_FaceDetection-DSFD]: https://github.com/Tencent/FaceDetection-DSFD
[https_arxiv.org_pdf_1810.10220.pdf]: https://arxiv.org/pdf/1810.10220.pdf
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM1OTc1NDQ3_size_16_color_FFFFFF_t_70]: /images/20221120/5a6100ad587b40f79b48734579984d59.png
[https_download.pytorch.org_models_resnet152-b121ed2d.pth]: https://download.pytorch.org/models/resnet152-b121ed2d.pth
[http_shuoyang1213.me_WIDERFACE]: http://shuoyang1213.me/WIDERFACE/
[20201130100019583.png]: /images/20221120/3e85b22c72074f8dbd268793259ce0e6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM1OTc1NDQ3_size_16_color_FFFFFF_t_70 1]: /images/20221120/bf19baafdb6e430dbb51dc8cf2558e9c.png
[2020120120225283.png]: https://img-blog.csdnimg.cn/2020120120225283.png