- [Script and Sample Code](#script-and-sample-code)
- [Running Example](#running-example)
- [Model Description](#model-description)
- [Performance](#performance)
- [ModelZoo Homepage](#modelzoo-homepage)
# [Face Detection Description](#contents)
This is a Face Detection network based on Yolov3, with support for training and evaluation on Ascend910.
You only look once (YOLO) is a state-of-the-art, real-time object detection system. YOLOv3 is extremely fast and accurate.
Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.
YOLOv3 use a totally different approach. It apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.
[Paper](https://pjreddie.com/media/files/papers/YOLOv3.pdf): YOLOv3: An Incremental Improvement. Joseph Redmon, Ali Farhadi,
University of Washington
# [Model Architecture](#contents)
Face Detection uses a modified-DarkNet53 network for performing feature extraction. It has 45 convolutional layers.
# [Dataset](#contents)
We use about 13K images as training dataset and 3K as evaluating dataset in this example, and you can also use your own datasets or open source datasets (e.g. WiderFace)
- step 1: The dataset should follow the Pascal VOC data format for object detection. The directory structure is as follows:(Because of the small input shape of network, we remove the face lower than 50*50 at 1080P in evaluating dataset )
```python
.
└─ dataset
├─ Annotations
├─ img1.xml
├─ img2.xml
├─ ...
├─ JPEGImages
├─ img1.jpg
├─ img2.jpg
├─ ...
└─ ImageSets
└─ Main
└─ train.txt or test.txt
```
- step 2: Convert the dataset to mindrecord:
```bash
python data_to_mindrecord_train.py
```
or
```bash
python data_to_mindrecord_eval.py
```
If your dataset is too big to convert at a time, you can add data to an existed mindrecord in turn:
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
