retinaface onnx

tensorrt代码：

https://github.com/azhe198827/retinaface_tensorRT

https://github.com/lesurp/retinanet_cpp/blob/master/examples/single_image.cpp

https://github.com/wuchaodzxx/tensorrt_retinaface

废话不说，上代码

retina face，

import os
import time
from math import ceilimport onnxruntime
import numpy as np
import cv2
import argparse
import argparse
import numpy as np
from data import cfg_mnet, cfg_peleenet
from utils.nms.py_cpu_nms import py_cpu_nms
from math import ceil
from itertools import product as product#sigmoid函数
def sigmoid(x):s = 1 / (1 + np.exp(-1*x))return s
def softmax(x, axis=1):# 计算每行的最大值row_max = x.max(axis=axis)# 每行元素都需要减去对应的最大值，否则求exp(x)会溢出，导致inf情况row_max = row_max.reshape(-1, 1)x = x - row_maxx_exp = np.exp(x)x_sum = np.sum(x_exp, axis=axis, keepdims=True)s = x_exp / x_sumreturn sdef decode_landm(pre, priors, variances):"""Decode landm from predictions using priors to undothe encoding we did for offset regression at train time.Args:pre (tensor): landm predictions for loc layers,Shape: [num_priors,10]priors (tensor): Prior boxes in center-offset form.Shape: [num_priors,4].variances: (list[float]) Variances of priorboxesReturn:decoded landm predictions"""landms = np.concatenate((priors[:, :2] + pre[:, :2] * variances[0] * priors[:, 2:],priors[:, :2] + pre[:, 2:4] * variances[0] * priors[:, 2:],priors[:, :2] + pre[:, 4:6] * variances[0] * priors[:, 2:],priors[:, :2] + pre[:, 6:8] * variances[0] * priors[:, 2:],priors[:, :2] + pre[:, 8:10] * variances[0] * priors[:, 2:],), 1)return landmsdef decode(loc, priors, variances):"""Decode locations from predictions using priors to undothe encoding we did for offset regression at train time.Args:loc (tensor): location predictions for loc layers,Shape: [num_priors,4]priors (tensor): Prior boxes in center-offset form.Shape: [num_priors,4].variances: (list[float]) Variances of priorboxesReturn:decoded bounding box predictions"""boxes = np.concatenate((priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:],priors[:, 2:] * np.exp(loc[:, 2:] * variances[1])), 1)boxes[:, :2] -= boxes[:, 2:] / 2boxes[:, 2:] += boxes[:, :2]return boxesclass PriorBox(object):def __init__(self, cfg, image_size=None, phase='train'):super(PriorBox, self).__init__()self.min_sizes = cfg['min_sizes']self.steps = cfg['steps']self.image_size = image_sizeself.feature_maps = [[ceil(self.image_size[0]/step), ceil(self.image_size[1]/step)] for step in self.steps]def forward(self):anchors = []for k, f in enumerate(self.feature_maps):min_sizes = self.min_sizes[k]for i, j in product(range(f[0]), range(f[1])):for min_size in min_sizes:s_kx = min_size / self.image_size[1]s_ky = min_size / self.image_size[0]dense_cx = [x * self.steps[k] / self.image_size[1] for x in [j + 0.5]]dense_cy = [y * self.steps[k] / self.image_size[0] for y in [i + 0.5]]for cy, cx in product(dense_cy, dense_cx):anchors += [cx, cy, s_kx, s_ky]# back to torch landoutput = np.array(anchors)output = output.reshape(-1, 4)return output
def sigmoid(x):# TODO: Implement sigmoid functionreturn 1/(1 + np.exp(-x))
def main():parser = argparse.ArgumentParser()parser.add_argument('--input_shape', help="caffe's caffemodel file path",default=(480,360))parser.add_argument('--img_path', help="test image path", default="d:/cat.jpg")parser.add_argument('--onnx_path', help="onnx model file path",  default="mobileretina.onnx")# parser.add_argument('--onnx_path', help="onnx model file path",  default=r"pelee_detector.onnx")# parser.add_argument('--onnx_path', help="onnx model file path",  default="yolov3.onnx")parser.add_argument('--confidence_threshold', help="confidence threshold", default=0.9, type=float)parser.add_argument('--nms_thres', help="nms threshold",  default=0.6, type=float)parser.add_argument('--top_k',help="to choice anchors", default=20, type=int)parser.add_argument('--nms_threshold',help="to choice anchors", default=0.4, type=float)parser.add_argument('--show_image',help="to choice anchors", default=True, type=bool)args = parser.parse_args()cfg = cfg_peleenetonnx_path = args.onnx_pathsession = onnxruntime.InferenceSession(onnx_path)input_shape = args.input_shape #模型输入尺寸nms_threshold = args.nms_thresimg_path = args.img_pathprint("image path:",img_path)print("onnx model path:",onnx_path)# list_path = r"D:\project\face\face_mask\2020\0/"list_path = r"D:\input\faces/"g = os.walk(list_path)files = ['%s\\%s' % (i[0], j) for i in g for j in i[-1] ifj.endswith('jpg')]width=input_shape[0]height=input_shape[1]scale = np.array([width, height, width, height])scale1 = np.array([width, height, width, height,width, height, width, height,width, height])resize_level=1count = 0ok_count = 0priorbox = PriorBox(cfg, image_size=(height, width))priors = priorbox.forward()# vc = cv2.VideoCapture(r"D:\project\face\Face-Track-Detect-Extract\videos\2_Obama.mp4")  # 读入视频文件vc = cv2.VideoCapture(0)  # 读入视频文件while True:  # 循环读取视频帧rval, img_raw = vc.read()# for file in files:#     file=r"d:/7_Cheering_Cheering_7_426.png"#     img_raw = cv2.imread(file)if img_raw is None:# print(file)continuestart = time.time()img_raw = cv2.resize(img_raw, input_shape)img=cv2.cvtColor(img_raw,cv2.COLOR_BGR2RGB)img = np.float32(img)img -= (104, 117, 123)image = img[:, :, ::-1].transpose((2, 0, 1))TestData = image[np.newaxis, :, :, :]start2=time.time()inname = [input.name for input in session.get_inputs()][0]outname = [output.name for output in session.get_outputs()]loc, conf,landmarks = session.run(outname, {inname:TestData})print('net time', time.time() - start2)start1=time.time()boxes = decode(np.squeeze(loc, axis=0), priors, cfg['variance'])boxes = boxes * scale / resize_levelscores = np.squeeze(conf, axis=0)[:,1]landmarks = decode_landm(np.squeeze(landmarks, axis=0), priors, cfg['variance'])landmarks = landmarks * scale1 / resize_level# ignore low scoresinds = np.where(scores > args.confidence_threshold)[0]boxes = boxes[inds]landmarks = landmarks[inds]scores = scores[inds]# keep top-K before NMSorder = scores.argsort()[::-1][:args.top_k]boxes = boxes[order]landmarks = landmarks[order]scores = scores[order]# do NMSdets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)keep = py_cpu_nms(dets, args.nms_threshold)dets = dets[keep, :]landmarks = landmarks[keep, :]print('time',time.time()-start,start1-start)dets = np.concatenate((dets, landmarks), axis=1)if args.show_image:for box in dets:if (box[3] < - box[1]) or (box[2] < - box[0]):continueelif box[0] < 0 or box[1] < 0:box[0] = max(0, box[0])box[1] = max(0, box[1])if (box[3] + box[1] > 2 * img_raw.shape[0]) or (box[0] + box[2] > 2 * img_raw.shape[1]):continueelif box[3] > img_raw.shape[0] or box[2] > img_raw.shape[1]:box[3] = min(img_raw.shape[0], box[3])box[2] = max(img_raw.shape[1], box[2])if (box[2] - box[0]) > 4 * (box[3] - box[1]) or (box[2] - box[0]) * 4 < (box[3] - box[1]):continue# if box[3]*resize_level > img_raw.shape[0] + 5 or box[2]*resize_level > img_raw.shape[1] + 5:#     # print('out_show', img_raw.shape, int(box[2]*resize_level),int(box[3]*resize_level))#     continuetext = "{:.2f}".format(box[4])box = list(map(int, box))cv2.rectangle(img_raw, (box[0] * resize_level, box[1] * resize_level),(box[2] * resize_level, box[3] * resize_level), (0, 0, 255), 1)cv2.circle(img_raw, (box[5], box[6]), 1, (0, 0, 255), 4)cv2.circle(img_raw, (box[7], box[8]), 1, (0, 255, 255), 4)cv2.circle(img_raw, (box[9], box[10]), 1, (255, 0, 255), 4)cv2.circle(img_raw, (box[11], box[12]), 1, (0, 255, 0), 4)cv2.circle(img_raw, (box[13], box[14]), 1, (255, 0, 0), 4)cx = box[0] * resize_level + 18cy = box[1] * resize_level + 18# cv2.putText(img_raw, text, (cx, cy),                           cv2.FONT_HERSHEY_DUPLEX, 0.3, (0, 255, 0))# landms# cv2.circle(img_raw, (b[5], b[6]), 1, (0, 0, 255), 4)# cv2.circle(img_raw, (b[7], b[8]), 1, (0, 255, 255), 4)# cv2.circle(img_raw, (b[9], b[10]), 1, (255, 0, 255), 4)# cv2.circle(img_raw, (b[11], b[12]), 1, (0, 255, 0), 4)# cv2.circle(img_raw, (b[13], b[14]), 1, (255, 0, 0), 4)# save imageif img_raw.shape[0] > 1080:fy = 1070 / img_raw.shape[0]img_raw = cv2.resize(img_raw, (0, 0), fx=fy, fy=fy, interpolation=cv2.INTER_NEAREST)cv2.imshow("sdf", img_raw)cv2.waitKey(1)# print(time.time()-start,"inputs name:", inname, "outputs name:", outname,prediction)# drawBox(boxes,img,img_shape)if __name__ == '__main__':main()

retinaface onnx相关推荐

RV1126_python人脸识别Retinaface+MobilefaceNet
RV1126_python人脸识别Retinaface+MobilefaceNet RV1126 具备RKNN 模块支持大部分如Pytorch.MXNet.Caffe.tensorflow.keras ...
RetinaFace Mxnet转TensorRT
1. github开源代码 RetinaFace TensorRT推理的开源代码位置在https://github.com/linghu8812/tensorrt_inference/tree/mas ...
ONNX+TensorRT
使用ONNX+TensorRT部署人脸检测和关键点250fps This article was original written by Jin Tian, welcome re-post, firs ...
RetinaFace人脸检测使用
本文将介绍如何使用RetinaFace训练模型进行使用代码下载就去github官方https://github.com/biubug6/Pytorch_Retinaface -- 环境搭建打开An ...
pytorch版本RetinaFace人脸检测模型推理加速
pytorch版本RetinaFace人脸检测模型推理加速_胖胖大海的博客-CSDN博客 pytorch版本RetinaFace人脸检测模型推理加速,去掉FPN第一层,不检测特别小的人脸框_胖胖大海的 ...
pytorch转onnx踩坑日记
在深度学习模型部署时,从pytorch转换onnx的过程中,踩了一些坑.本文总结了这些踩坑记录,希望可以帮助其他人. 首先,简单说明一下pytorch转onnx的意义.在pytorch训练出一个深度学 ...
TensorRT实现RetinaFace推理加速（一）
一.参考资料 tensorrtx/retinaface TensorRT实现yolov5推理加速(一) TensorRT实现yolov5推理加速(二) 二.实验环境 ##系统环境 Environmen ...
【.pth模型转换为.onnx模型】模型转换英特尔神经计算棒树莓派
转换代码注意点:要根据你的代码进行修改,修改最初的包等 import torch from models.with_mobilenet import PoseEstimationWithMobile ...
瑞芯微转化人脸检测retinaface模型
瑞芯微转化人脸检测retinaface模型一.运行docker 二.转换步骤 1.使用https://netron.app/查看模型的输入及输出 2.设置转换模型参数 3.运行文件生成rknn模型文 ...

retinaface onnx

retinaface onnx相关推荐

最新文章

热门文章