CODEWITHSUNDEEP
tensorflowobject-detectionyolo
HELO
HELO

Reputation: 67

Create pre-trained weights for detection without darknet / torch

I want to train my data and create a weights file to train my YOLOV3 network. The objects in my database are not in COCO's classes so I do not want to use their weights file. I also have a limitation - I can not use darknet and I also prefer not to use the torch library.

The files I have: (according https://github.com/AlexeyAB/Yolo_mark/issues/60#issuecomment-401854885)

  1. yolov3-custom.cfg according my classes
  2. obj.names with my class's names
  3. train.txt + test.txt with list of image's location
  4. folder with images+ labels yolo format (object-class, x, y, width, height)
  5. obj.data

What can I do?

Upvotes: 2

Views: 1502

Answers (2)

HELO
HELO

Reputation: 67

I trained my custom according to github.com/qqwweee/keras-yolo3

Upvotes: 0

Y.Ynot
Y.Ynot

Reputation: 417

You can still use the pre-trained weights on ImageNet if you want to start with pre-trained weights. If you have different classes than the COCO dataset that's no problem. You can define your own classes, and start training with the pre-trained weights. During training, the weights will be updated to detect your custom classes.

You can use these weights for YOLOv3: "https://pjreddie.com/media/files/yolov3.weights"

Upvotes: 1

Related Questions