henghuiding/Vision-Language-Transformer

Two questions about the model training: weight mismatch and yolov3_480000.h5

jianhua2022 opened this issue · 1 comments

jianhua2022 commented

Hi,
I am running your code for model training, but I have two questions:

  1. How to generate the weights of yolov3_480000.h5. I try to generate the yolov3_480000.h5 follow the Keras implementation of YOLOv3 by Converting the Darknet YOLO model to a Keras model: python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5. So is it right?
  2. After generating the yolov3_480000.h5, I start to train the model. But it shows some warming information, why?
    image
changliu19 commented

Hi Jianhua,

Thanks for your questions.

  1. Please follow the instructions about "Pretrained Backbones" in the README file to prepare the backbone weights.

  2. This is expected. Don't worry😃

  • 👍1