How to use OpenVINO pre-trained models?

可紊 提交于 2019-12-08 08:59:47

问题


I have installed OpenVINO recently but I don't know how I should give inputs and get the predict from OpenVINOs pre-trained models.

there is two files with .bin and .xml suffixes, I've just worked with keras so I can't use this models in opencv.

I find this code but it didn't work.

import cv2 as cv

net = cv.dnn.readNet('face-detection-adas-0001.bin', 'face-detection-adas-0001.xml')

cap = cv.VideoCapture(0)

while cv.waitKey(1) < 0:
    hasFrame, frame = cap.read()
    if not hasFrame:
        break

    blob = cv.dnn.blobFromImage(frame, size=(672, 384))
    net.setInput(blob)
    out = net.forward()

    for detection in out.reshape(-1, 7):
        confidence = float(detection[2])
        xmin = int(detection[3] * frame.shape[1])
        ymin = int(detection[4] * frame.shape[0])
        xmax = int(detection[5] * frame.shape[1])
        ymax = int(detection[6] * frame.shape[0])

        if confidence > 0.5:
            cv.rectangle(frame, (xmin, ymin), (xmax, ymax), color=(0, 255, 0))

    cv.imshow('OpenVINO face detection', frame)

there's the error code:

Traceback (most recent call last):
  File "C:\Users\Ali-10\Desktop\facial_landmark\face.py", line 3, in <module>
    net = cv.dnn.readNet('face-detection-adas-0001.bin', 'face-detection-adas-0001.xml')
    cv2.error: OpenCV(3.4.4) C:\projects\opencv-python\opencv\modules\dnn\src\dnn.cpp:2428: error: (-2:Unspecified error) Build OpenCV with Inference Engine to enable loading models from Model Optimizer. in function 'cv::dnn::experimental_dnn_34_v10::Net::readFromModelOptimizer'

I expect the prediction of the model but I just get this error.


回答1:


You need to build OpenCV with Inference Engine support as mentioned in the message. See wiki for details: https://github.com/opencv/opencv/wiki/Intel%27s-Deep-Learning-Inference-Engine-backend.

If you use OpenCV from OpenVINO distribution, it must be already built with IE (maybe except a single R5.1 release from January of 2019).

We also work on simplified way to build OpenCV with IE (without specifying paths but just downloading it's source code by cmake), see PR https://github.com/opencv/opencv/pull/13965.



来源:https://stackoverflow.com/questions/55345798/how-to-use-openvino-pre-trained-models

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!