使用Darknet和coco数据集运行YOLOv3检测

Question

我试图在他们的数据集中运行YOLOv3反对算法(coco文件)。我突然遇到了一个错误。

下载YOLOv3加权，

!wget https://pjredddie.com/media/files/yolov3.weights

函数显示后预测，

def imshow(path):
  import cv2
  import matplotlib.pyplot as plt
  %matplotlib inline

  image = cv2.imread(path)
  height, width=image.shape[:2]
  resized_image = cv2.resize(image, (3*width, 3*height), interpolation=cv2.INTER_CUBIC)
  
  fig = plt.gfc()
  fig.set_size_inches(18,10)
  plt.axis("off")
  plt.imshow(cv2.cvtColor(resized_image, cv2.COLOR_BGR2RGB))
  plt.show()

用Darknet和YOLOv3，运行检测

!./darknet detect <path to config> <path to weights> <path to image>

现在，错误是，

/bin/bash: -c: line 0: syntax error near unexpected token `<'
/bin/bash: -c: line 0: `./darknet detect <path to config> <path to weights> <path to image>'

注意： !./darknet detect <path to config> <path to weights> <path to image>在这段代码中，我从键盘输入<>令牌。

Answer 1

不要在命令中使用这个<>，您必须编写这样的实际路径。

./darknet detect ./data/yolov3.cfg ./data/yolov3.weights ./test/img.bmp