使用 NCS2 异步推理—

环境：

Python：3.7.3
OpenVINO：2021.4.582
g++ (Raspbian 8.3.0-6+rpi1) 8.3.0
raspberrypi：5.10.52-v7l+
系统指令集：armv7l

组件：

Raspberry Pi 4B 8G
NCS2

人脸检测器基于 MobileNetV2 作为主干，带有多个 SSD 头，用于前置摄像头拍摄的室内和室外场景。在这个模型的训练过程中，训练图像被调整为 384x384。

下载人脸识别模型：

https://storage.openvinotoolkit.org/repositories/open_model_zoo/2021.2/models_bin/3/face-detection-0202/FP32/face-detection-0202.xml

https://storage.openvinotoolkit.org/repositories/open_model_zoo/2021.2/models_bin/3/face-detection-0202/FP32/face-detection-0202.bin

输入

名称：input，形状：[1 x 3 x 384 x 384] - 格式为 [B x C x H x W] 的输入图像，其中：

B ：批量大小
C ：通道数
H ：图像高度
W ：图像宽度

预期颜色顺序：BGR。

输出

网络输出 blob 的形状为：[1, 1, N, 7]，其中 N 是检测到的边界框的数量。每个检测都具有 [ image_id, label, conf, x_min, y_min, x_max, y_max]格式，其中：

image_id ：批次中图像的 ID
label ：预测类 ID（0 ：人脸）
conf ：对预测类别的置信度
(x_min, y_min) ：左上边界框角的坐标
(x_max, y_max) ：右下边界框角的坐标。

使用Python代码测试

from openvino.inference_engine import IECore
import time
import cv2 as cv# 配置推断计算设备，IR文件路径
model_xml = "face-detection-0202.xml"
model_bin = "face-detection-0202.bin"
DEVICE = 'MYRIAD'
# DEVICE = 'CPU'# 异步加载摄像头
def ssd_webcam_demo():# 初始化插件，输出插件版本号ie = IECore()for device in ie.available_devices:print(device)# 读取IR模型文件net = ie.read_network(model=model_xml, weights=model_bin)# 准备输入输出张量print("Preparing input blobs")input_blob = next(iter(net.input_info))out_blob = next(iter(net.outputs))# 读入图片n, c, h, w = net.input_info[input_blob].input_data.shapeprint(n, c, h, w)# 打开摄像头cap = cv.VideoCapture(2)ret, frame = cap.read()curr_request_id = 0next_request_id = 1# 载入模型到AI推断计算设备print("Loading IR to the plugin...")# exec_net = ie.load_network(network=net, device_name=DEVICE) # 同步推理exec_net = ie.load_network(network=net, device_name=DEVICE, num_requests=2)  # 异步推理while True:ret, next_frame = cap.read()if ret is not True:breakimage = cv.resize(frame, (w, h))image = image.transpose(2, 0, 1)# 执行推断计算print("Starting inference in synchronous mode")inf_start = time.time()# res = exec_net.infer(inputs={input_blob: [image]})  # 调用同步推理exec_net.start_async(request_id=next_request_id, inputs={input_blob: [image]})  # 调用异步推理inf_end = time.time() - inf_startprint("infer time(ms)：%.3f" % (inf_end * 1000))# 根据状态检查if exec_net.requests[curr_request_id].wait(-1) == 0:res = exec_net.requests[curr_request_id].output_blobs[out_blob].buffer# 处理输出ih, iw, ic = frame.shapefor obj in res[0][0]:if obj[2] > 0.75:xmin = int(obj[3] * iw)ymin = int(obj[4] * ih)xmax = int(obj[5] * iw)ymax = int(obj[6] * ih)cv.rectangle(frame, (xmin, ymin), (xmax, ymax), (0, 255, 255), 2, 8)cv.putText(frame, "infer time(ms): %.3f" % (inf_end * 1000), (50, 50), cv.FONT_HERSHEY_SIMPLEX, 1.0,(255, 0, 255),2, 8)cv.imshow("Face Detection", frame)c = cv.waitKey(1)if c == 27:break# 交换数据frame = next_framecurr_request_id, next_request_id = next_request_id, curr_request_idcv.waitKey(0)cv.destroyAllWindows()if __name__ == "__main__":ssd_webcam_demo()

face-detection-adas-0001.xml 文件下载网址：https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16

Linux下载网络和权重文件

wget --no-check-certificate https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.bin
wget --no-check-certificate https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.xml

pi@raspberrypi:~/Desktop/vision_ai $ wget --no-check-certificate https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.xml
–2021-09-27 19:33:49-- https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.xml
已发出 HTTP 请求，正在等待回应… 200 OK
长度：225964 (221K) [text/xml]
正在保存至: “face-detection-adas-0001.xml”
face-detection-adas 100%[===================>] 220.67K 650KB/s 用时 0.3s
2021-09-27 19:33:51 (650 KB/s) - 已保存 “face-detection-adas-0001.xml” [225964/225964])

pi@raspberrypi:~/Desktop/vision_ai $ wget --no-check-certificate https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.bin
–2021-09-27 19:34:06-- https://download.01.org/opencv/2021/openvinotoolkit/2021.2/open_model_zoo/models_bin/3/face-detection-adas-0001/FP16/face-detection-adas-0001.bin
已发出 HTTP 请求，正在等待回应… 200 OK
长度：2106088 (2.0M) [application/octet-stream]
正在保存至: “face-detection-adas-0001.bin”
face-detection-adas 100%[===================>] 2.01M 2.40MB/s 用时 0.8s
2021-09-27 19:34:07 (2.40 MB/s) - 已保存 “face-detection-adas-0001.bin” [2106088/2106088])

#!/usr/bin/env python3from __future__ import print_function
import sys
import os
from argparse import ArgumentParser, SUPPRESS
import cv2
import time
import logging as logfrom openvino.inference_engine import IECoredef build_argparser():parser = ArgumentParser(add_help=False)args = parser.add_argument_group('Options')args.add_argument('-h', '--help', action='help', default=SUPPRESS, help='Show this help message and exit.')args.add_argument("-m", "--model", help="Required. Path to an .xml file with a trained model.",default="./model/face-detection-adas-0001.xml", type=str)args.add_argument("-i", "--input",help="Required. Path to video file or image. 'cam' for capturing video stream from camera",required=False, type=str)args.add_argument("-l", "--cpu_extension",help="Optional. Required for CPU custom layers. Absolute path to a shared library with the ""kernels implementations.", type=str, default=None)args.add_argument("-d", "--device",help="Optional. Specify the target device to infer on; CPU, GPU, FPGA, HDDL or MYRIAD is ""acceptable. The demo will look for a suitable plugin for device specified. ""Default value is CPU", default="MYRIAD", type=str)args.add_argument("--labels", help="Optional. Path to labels mapping file", default=None ,type=str)args.add_argument("-pt", "--prob_threshold", help="Optional. Probability threshold for detections filtering",default=0.5, type=float)args.add_argument("--no_show", help="Optional. Don't show output", action='store_true')return parserdef main():log.basicConfig(format="[ %(levelname)s ] %(message)s", level=log.INFO, stream=sys.stdout)args = build_argparser().parse_args()log.info("Creating Inference Engine...")ie = IECore()if args.cpu_extension and 'CPU' in args.device:ie.add_extension(args.cpu_extension, "CPU")# Read IRlog.info("Loading network")net = ie.read_network(args.model, os.path.splitext(args.model)[0] + ".bin")if "CPU" in args.device:supported_layers = ie.query_network(net, "CPU")not_supported_layers = [l for l in net.layers.keys() if l not in supported_layers]if len(not_supported_layers) != 0:log.error("Following layers are not supported by the plugin for specified device {}:\n {}".format(args.device, ', '.join(not_supported_layers)))log.error("Please try to specify cpu extensions library path in sample's command line parameters using -l ""or --cpu_extension command line argument")sys.exit(1)img_info_input_blob = Nonefeed_dict = {}for blob_name in net.inputs:if len(net.inputs[blob_name].shape) == 4:input_blob = blob_nameelif len(net.inputs[blob_name].shape) == 2:img_info_input_blob = blob_nameelse:raise RuntimeError("Unsupported {}D input layer '{}'. Only 2D and 4D input layers are supported".format(len(net.inputs[blob_name].shape), blob_name))assert len(net.outputs) == 1, "Demo supports only single output topologies"out_blob = next(iter(net.outputs))log.info("Loading IR to the plugin...")exec_net = ie.load_network(network=net, num_requests=2, device_name=args.device)# Read and pre-process input imagen, c, h, w = net.inputs[input_blob].shapeif img_info_input_blob:feed_dict[img_info_input_blob] = [h, w, 1]if args.input == 'cam':input_stream = 0else:input_stream = args.input#cap = cv2.VideoCapture(input_stream)cap = cv2.VideoCapture(0)assert cap.isOpened(), "Can't open " + input_streamif args.labels:with open(args.labels, 'r') as f:labels_map = [x.strip() for x in f]else:labels_map = Nonecur_request_id = 0next_request_id = 1log.info("Starting inference in async mode...")is_async_mode = Truerender_time = 0if is_async_mode:ret, frame = cap.read()frame_h, frame_w = frame.shape[:2]print("To close the application, press 'CTRL+C' here or switch to the output window and press ESC key")print("To switch between sync/async modes, press TAB key in the output window")while cap.isOpened():if is_async_mode:ret, next_frame = cap.read()else:ret, frame = cap.read()if ret:frame_h, frame_w = frame.shape[:2]if not ret:break  # abandons the last frame in case of async_mode# Main sync point:# in the truly Async mode we start the NEXT infer request, while waiting for the CURRENT to complete# in the regular mode we start the CURRENT request and immediately wait for it's completioninf_start = time.time()if is_async_mode:in_frame = cv2.resize(next_frame, (w, h))in_frame = in_frame.transpose((2, 0, 1))  # Change data layout from HWC to CHWin_frame = in_frame.reshape((n, c, h, w))feed_dict[input_blob] = in_frameexec_net.start_async(request_id=next_request_id, inputs=feed_dict)else:in_frame = cv2.resize(frame, (w, h))in_frame = in_frame.transpose((2, 0, 1))  # Change data layout from HWC to CHWin_frame = in_frame.reshape((n, c, h, w))feed_dict[input_blob] = in_frameexec_net.start_async(request_id=cur_request_id, inputs=feed_dict)if exec_net.requests[cur_request_id].wait(-1) == 0:inf_end = time.time()det_time = inf_end - inf_start# Parse detection results of the current requestres = exec_net.requests[cur_request_id].outputs[out_blob]for obj in res[0][0]:# Draw only objects when probability more than specified thresholdif obj[2] > args.prob_threshold:xmin = int(obj[3] * frame_w)ymin = int(obj[4] * frame_h)xmax = int(obj[5] * frame_w)ymax = int(obj[6] * frame_h)class_id = int(obj[1])# Draw box and label\class_id#color = (min(class_id * 12.5, 255), min(class_id * 7, 255), min(class_id * 5, 255))#color = (min(class_id * 60, 255), min(class_id * 60, 255), min(class_id * 60, 255))color = [(0,0,0),(0,255,0),(255,0,0),(255,255,255),(0,0,0),(203,192,255),(238,130,238),(0,69,255) ]#print(color[class_id])#print(obj)cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), color[class_id], 2)#print(class_id)det_label = labels_map[class_id] if labels_map else str(class_id)cv2.putText(frame, 'face' + ' ' + str(round(obj[2] * 100, 1)) + ' %', (xmin, ymin - 7),cv2.FONT_HERSHEY_COMPLEX, 0.6,(0,255,0), 1)# Draw performance statsinf_time_message = "Inference time: N\A for async mode" if is_async_mode else \"Inference time: {:.3f} ms".format(det_time * 1000)render_time_message = "OpenCV rendering time: {:.3f} ms".format(render_time * 1000)async_mode_message = "Async mode is on. Processing request {}".format(cur_request_id) if is_async_mode else \"Async mode is off. Processing request {}".format(cur_request_id)cv2.putText(frame, inf_time_message, (15, 15), cv2.FONT_HERSHEY_COMPLEX, 0.5, (200, 10, 10), 1)cv2.putText(frame, render_time_message, (15, 30), cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)cv2.putText(frame, async_mode_message, (10, int(frame_h - 20)), cv2.FONT_HERSHEY_COMPLEX, 0.5,(10, 10, 200), 1)#render_start = time.time()if not args.no_show:cv2.imshow("Detection Results", frame)render_end = time.time()render_time = render_end - render_startif is_async_mode:cur_request_id, next_request_id = next_request_id, cur_request_idframe = next_frameframe_h, frame_w = frame.shape[:2]if not args.no_show:key = cv2.waitKey(1)if key == 27:breakif (9 == key):is_async_mode = not is_async_modelog.info("Switched to {} mode".format("async" if is_async_mode else "sync"))cv2.destroyAllWindows()if __name__ == '__main__':sys.exit(main() or 0)

运行结果：

出现问题：

缺少 openvino 模块

Traceback (most recent call last):
File “./demo/OpenVINO/python/openvino_inference.py”, line 15, in
from openvino.inference_engine import IECore
ModuleNotFoundError: No module named ‘openvino’

Raspberry Pi 4B安装 OpenVINO™ 工具包：
https://blog.csdn.net/qq_44989881/article/details/119792769?spm=1001.2014.3001.5501

或者
设置 openvino 的环境变量

source /opt/intel/openvino_2021/bin/setupvars.sh

pi@raspberrypi:~/Desktop $ source /opt/intel/openvino_2021/bin/setupvars.sh
[setupvars.sh] OpenVINO environment initialized

使用 NCS2 异步推理——人脸识别相关推荐

OpenVINO™场景文字识别与同步与异步推理
场景文字检测与识别模型 OpenVINO2021.4支持场景文字检测是基于MobileNetV2的PixelLink模型,模型有两个分别是text-detection-0003与text-detect ...
【聆思CSK6 视觉AI开发套件试用】人脸识别和 tflite-micro 语音识别推理实验
本篇文章来自极术社区与聆思科技组织的CSK6 视觉AI开发套件活动,更多开发板试用活动请关注极术社区网站.作者:SunnyCase 1. 前言非常幸运得到这次测评 CSK6 视觉AI开发套件的机会, ...
静默活体检测+人脸检测+人脸识别结合在NCNN模型下的推理(Windows下的VS环境）
前言: 涉及到三个模型静默活体检测模型<2M,人脸检测模型<2M ,人脸识别<5M(模型大小) 至于NCNN不必多说,全C++实现,不依赖第三方库实现,在第三方移动端CPU运 ...
《人脸识别原理及算法——动态人脸识别系统研究》—1章1.2节人脸识别相关学科的进展...
本节书摘来自异步社区<人脸识别原理及算法--动态人脸识别系统研究>一书中的1章1.2节人脸识别相关学科的进展,作者沈理 , 刘翼光 , 熊志勇,更多章节内容可以访问云栖社区"异 ...
身份验证错误错误指定的句柄无效_基于 Web 端的人脸识别身份验证「实践」
作者:沫沫政采云前端团队转发链接:https://mp.weixin.qq.com/s/fRDpXixnLIy9c0Uh2tMezQ 前言近些年来,随着生物识别技术的逐渐成熟,基于深度学习的人脸 ...
深度人脸识别：CVPR2020论文要点
深度人脸识别:CVPR2020论文要点 Towards Universal Representation Learning for Deep Face Recognition 论文链接:https:/ ...
【MediaPipe】(3) AI视觉，人脸识别，附python完整代码
各位同学好,今天和大家分享一下如何使用MediaPipe完成人脸实时跟踪检测,先放张图看效果,FPS值为14,右侧的输出为:每帧图像是人脸的概率,检测框的左上角坐标及框的宽高. 有需要的可以使用 cv ...
二次元会让人脸识别失效吗？
来源 | PyTorch 开发者社区责编 | 寇雪芹头图 | 下载于ICphoto 人脸识别也遇到坑了,识别得了三次元,却对二次元无效.迪士尼的技术团队,正在开发这一算法,以帮助动画制作者进行后期 ...
万人马拉松赛事，人脸识别系统如何快速、准确完成校验？
作者 | 阿里文娱技术专家墨贤出品 | AI科技大本营(ID:rgznai100) 大麦的人脸闸机在2019年杭州马拉松上成功的完成了刷脸入场功能的首秀,相比传统的马拉松入场核验方案在入场体验和入场 ...

使用 NCS2 异步推理——人脸识别

输入

输出

出现问题：

使用 NCS2 异步推理——人脸识别相关推荐

最新文章

热门文章