mnn_example
alibaba MNN, mobilenet classifier, centerface detector, pfld landmarker and zqlandmarker, mobilefacenet
1.更新日志
| 时间 | 更新内容 |
|---|---|
| 20200621 | 1.remove the interface of GetImg; |
| 20200320 | 1.fix bug in face aligner; |
| 20200305 | 1.add ultraface and blending nms; |
| 20200221 | 1.add mobilefacenet; |
| 20200220 | 1.use template to reduce the reaptly code in NMS; |
| 20200218 | 1.refacter the project; |
| 20200217 | 1.add zwnet and face database; |
| 20200216 | 1.refacter the project and add zqlandmarker; |
| 20200215 | 1.add pfld landmarker and face aligner; |
| 20200214 | 1.add centerface detector; |
| 20200205 | 1.add object detection; |
| 20200128 | 1.add image classification; |
2.How to use?
- (1). convert model
-
- classifier model comes from: https://github.com/tensorflow/models/tree/master/research/slim
-
- object detection model comes from: https://github.com/C-Aniruddh/realtime_object_recognition
./MNNConvert -f TF --modelFile mobilenet_v1_1.0_224_frozen.pb --MNNModel mobilenet.mnn --bizCode MNN
./MNNConvert -f CAFFE --modelFile MobileNetSSD_deploy.caffemodel --prototxt MobileNetSSD_deploy.prototxt --MNNModel mobilenetssd.mnn --bizCode MNN
- (2). build
mkdir build && cd build && make -j3 && cd src && ./classifier && ./object && ./face
- (3). result
classifier result:
object result:
face detection result:
3. TODO:
- add pose