Files
FastDeploy/model_zoo/vision/retinaface/retinaface.py
DefTruth adddd3c452 Add RetinaFace Model support (#48)
* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* Add RetinaFace Model support

* fixed retinaface/api.md typos
2022-07-28 10:35:27 +08:00

25 lines
769 B
Python

import fastdeploy as fd
import cv2
# 下载模型
model_url = "https://github.com/DefTruth/Pytorch_Retinaface/releases/download/v0.1/Pytorch_RetinaFace_mobile0.25-640-640.onnx"
test_img_url = "https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/raw/master/imgs/3.jpg"
fd.download(model_url, ".", show_progress=True)
fd.download(test_img_url, ".", show_progress=True)
# 加载模型
model = fd.vision.biubug6.RetinaFace(
"Pytorch_RetinaFace_mobile0.25-640-640.onnx")
# 预测图片
im = cv2.imread("3.jpg")
result = model.predict(im, conf_threshold=0.7, nms_iou_threshold=0.3)
# 可视化结果
fd.vision.visualize.vis_face_detection(im, result)
cv2.imwrite("vis_result.jpg", im)
# 输出预测结果
print(result)
print(model.runtime_option)