reference:

0. Environment

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
cffi
Cython
ipython

1. Preparation

1.1 Environmental preparation

run:

cd srn/extensions
sh build_ext.sh

1.2 Data preparation

From the content of image_list.txt in the directory, you can find that the tested images are directly placed under data/images, that is, after downloading the widerface data, just copy the images in val directly.

http://shuoyang1213.me/WIDERFACE/

Directory Structure:

data
    images
        data/images/0--Parade/0_Parade_Parade_0_72.jpg

1.3 Model preparation

https://drive.google.com/drive/folders/1T4Qt99SdM7c8G4ZuC1igensY0bZdEETF

https://pan.baidu.com/s/1ambmu1Bu6Oi7zTcEnigFyg（6fba）

Put the model under model.

2. Modify

Add a sentence to line86 to prevent insufficient GPU memory (the content in the corresponding for loop should be indented 4 spaces back accordingly):

    with torch.no_grad():

3. Test

The test probably needs 7-8G video memory.

cd tools
sh ./val.sh

The directory structure of the generated files after the test is as follows:

tools
    results_dir
        21--Festival
            21_Festival_Festival_21_254.txt

The content is displayed as follows:

4. Evaluation

Copy these files in Pytorch_Retinaface/widerface_evaluate to the SRN/tools directory.

Refer to https://blog.csdn.net/qq_35975447/article/details/109447929 :

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

vim evaluation.py
# line 187-188
parser.add_argument('-p', '--pred', default="./results_dir/")
parser.add_argument('-g', '--gt', default='./widerface_eval/ground_truth/')

python evaluation.py

reference

1. Reproduce Pytorch_Retinaface (Pytorch version)

2. SRN (official source code)

3.Selective Refinement Network for High Performance Face Detection（官方文章）

[Face Detection] SRN test and evaluation recurrence