Detecting with pre-trained model

qqwweee / keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

MIT License

7.14k stars 3.44k forks source link

Detecting with pre-trained model #733

Open yr-lee7 opened 3 years ago

yr-lee7 commented 3 years ago

After data labeling with YOLO_mark on the darknet and training custom data, I got a weights file and a cfg file. And I convert this weight file to h5 file via keras-yolo3.

And I tried to check the detection, but none of them are detected.

When using a pre-trained model, are there any files we need other than h5 files?

pgw928 commented 3 years ago

어떤식으로 detection 하신지 모르겠지만 class에 있는 물체가 포함된 이미지 넣으신게 맞나요?