基于机器人流的摄像头目标检测

Question

我试着用我的摄像头制作一个目标检测程序，但却无法工作

这是我的密码

import cv2 as cv
import base64
import numpy as np
import requests

ROBOFLOW_API_KEY = "*********"
ROBOFLOW_MODEL = "chess-full-ddsxf"  # eg xx-xxxx--#
ROBOFLOW_SIZE = 416

upload_url = "".join([
    "https://detect.roboflow.com/",
    ROBOFLOW_MODEL,
    "?access_token=",
    ROBOFLOW_API_KEY,
    "&format=image",
    "&stroke=5"
])

video = cv.VideoCapture(1)

# Check if camera opened successfully
if (video.isOpened()):
    print("successfully opening video stream or file")


# Infer via the Roboflow Infer API and return the result
def infer():
    # Get the current image from the webcam
    ret, frame = video.read()

    # Resize (while maintaining the aspect ratio)
    # to improve speed and save bandwidth
    height, width, channels = frame.shape
    scale = ROBOFLOW_SIZE / max(height, width)
    img = cv.resize(frame, (round(scale * width), round(scale * height)))

    # Encode image to base64 string
    retval, buffer = cv.imencode('.jpg', img)
    img_str = base64.b64encode(buffer)

    # Get prediction from Roboflow Infer API
    resp = requests.post(upload_url, data=img_str, headers={
        "Content-Type": "application/x-www-form-urlencoded"
    }, stream=True).raw

    # Parse result image
    image = np.asarray(bytearray(resp.read()), dtype="uint8")
    image = cv.imdecode(image, cv.IMREAD_COLOR)

    return image


# Main loop; infers sequentially until you press "q"
while video.isOpened():
    # On "q" keypress, exit
    key = cv.waitKey(5)
    if key == ord("q"):
        break

    # Synchronously get a prediction from the Roboflow Infer API
    image = infer()
    # And display the inference results
    cv.imshow('image', image)

# Release resources when finished
video.release()
cv.destroyAllWindows()

错误消息：成功打开视频流或文件

追溯(最近一次调用)：文件"C:\Users\Administrator\Documents\Atom\testingCode\webcamRoboflow\infer.py"，第64行，在cv.imshow(“图像”，图像)cv2中。错误: OpenCV(4.6.0) D:\a\opencv-python\opencv-python\opencv\modules\highgui\src\window.cpp:967:错误：(-215:断言失败) size.width>0 & size.height>0中的函数'cv::imshow‘

在22.357秒内完成

Answer 1

看起来，您忘记了包含您想要推断的模型的版本，因此您到达了服务器上未定义的端点。

ROBOFLOW_MODEL = "chess-full-ddsxf"  # eg xx-xxxx--#

这应该是

ROBOFLOW_MODEL = "chess-full-ddsxf/1"  # eg xx-xxxx--#

如果您将模型训练为数据集的第一个生成版本。