Add script to evaluate face detection by WIDERFace

models/face_detection_yunet/README.md

@@ -7,6 +7,15 @@ Notes:
 - For details on training this model, please visit https://github.com/ShiqiYu/libfacedetection.train.
 - This ONNX model has fixed input shape, but OpenCV DNN infers on the exact shape of input image. See https://github.com/opencv/opencv_zoo/issues/44 for more information.
 
+Results of accuracy evaluation with [tools/eval](../../tools/eval).
+
+| Models      | Easy AP | Medium AP | Hard AP | 
+|-------------|---------|-----------|---------|
+| YuNet       | 0.8498  | 0.8384    | 0.7357  |
+| YuNet quant | 0.7751  | 0.8145    | 0.7312  |
+
+\*: 'quant' stands for 'quantized'.
+
 ## Demo
 
 Run the following command to try the demo:

tools/eval/README.md

@@ -4,6 +4,7 @@ Make sure you have the following packages installed:
 
 ```shell
 pip install tqdm
+pip install scipy
 ```
 
 Generally speaking, evaluation can be done with the following command:
@@ -13,7 +14,8 @@ python eval.py -m model_name -d dataset_name -dr dataset_root_dir
 ```
 
 Supported datasets:
-- [ImageNet](./datasets/imagenet.py)
+- [ImageNet](#imagenet)
+- [WIDERFace](#widerface)
 
 ## ImageNet
 
@@ -53,3 +55,42 @@ Run evaluation with the following command:
 python eval.py -m mobilenet -d imagenet -dr /path/to/imagenet
 ```
 
+## WIDERFace
+
+The script is modified based on [WiderFace-Evaluation](https://github.com/wondervictor/WiderFace-Evaluation).
+
+### Prepare data
+
+Please visit http://shuoyang1213.me/WIDERFACE to download the WIDERFace dataset [Validation Images](https://huggingface.co/datasets/wider_face/resolve/main/data/WIDER_val.zip), [Face annotations](http://shuoyang1213.me/WIDERFACE/support/bbx_annotation/wider_face_split.zip) and [eval_tools](http://shuoyang1213.me/WIDERFACE/support/eval_script/eval_tools.zip). Organize files as follow:
+
+```shell
+$ tree -L 2 /path/to/widerface
+.
+├── eval_tools
+│   ├── boxoverlap.m
+│   ├── evaluation.m
+│   ├── ground_truth
+│   ├── nms.m
+│   ├── norm_score.m
+│   ├── plot
+│   ├── read_pred.m
+│   └── wider_eval.m
+├── wider_face_split
+│   ├── readme.txt
+│   ├── wider_face_test_filelist.txt
+│   ├── wider_face_test.mat
+│   ├── wider_face_train_bbx_gt.txt
+│   ├── wider_face_train.mat
+│   ├── wider_face_val_bbx_gt.txt
+│   └── wider_face_val.mat
+└── WIDER_val
+    └── images
+```
+
+### Evaluation
+
+Run evaluation with the following command:
+
+```shell
+python eval.py -m yunet -d widerface -dr /path/to/widerface
+```

tools/eval/datasets/__init__.py

@@ -1,4 +1,5 @@
 from .imagenet import ImageNet
+from .widerface import WIDERFace
 
 class Registery:
     def __init__(self, name):
@@ -13,3 +14,4 @@ def register(self, item):
 
 DATASETS = Registery("Datasets")
 DATASETS.register(ImageNet)
+DATASETS.register(WIDERFace)