1

I have a medical image set and I am trying to train my network using faster rCNN. The idea is to detect tumors in image. My example image containing a tumor like below.. enter image description here

I have extracted all the tumor location coordinates and it is ready to be trained using faster rCNN. I follow this github page.. https://github.com/you359/Keras-FasterRCNN According to this, the input file format should be like this;

file_path_to_the_image, x_min, y_min, x_max, y_max, class

When training the network, I must include background class as well. For example, benign tumors, malignant tumors, background as classes. How do I include background class? it is not very clear to me, how to teach the system about the background class. Much appreciate if someone could give a hint.

Mass17
  • 1,555
  • 2
  • 14
  • 29

1 Answers1

0

https://github.com/you359/Keras-FasterRCNN from this link we can see that

/data/imgs/img_001.jpg,837,346,981,456,cow /data/imgs/img_002.jpg,215,312,279,391,cat

so you can set thing like this

file_path_to_the_image, x_min, y_min, x_max, y_max, benign file_path_to_the_image, x_min, y_min, x_max, y_max, malignant file_path_to_the_image, x_min, y_min, x_max, y_max, background

deepak sen
  • 437
  • 4
  • 13