keras-yolo3 icon indicating copy to clipboard operation
keras-yolo3 copied to clipboard

How did you get the backend.h5?

Open WangDeyu opened this issue 7 years ago • 6 comments

1.Did your backend.h5 pre-trained on the ImageNet? 2.Can you give me the details of training process about backend.h5? Thank you so much!

WangDeyu avatar May 06 '18 15:05 WangDeyu

I didn't train it. It's from darknet weights.

experiencor avatar May 08 '18 13:05 experiencor

OSError: Unable to open file (unable to open file: name = 'backend.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

iamgrf avatar May 31 '18 06:05 iamgrf

thanks for @darjoo. He has reuploaded it here, http://www.mediafire.com/file/l1b96fk7j18yi7v/backend.h5. Give it a try.

mengban avatar Jun 12 '18 03:06 mengban

Hi, which weight from darknet is used for creating backend.h5? yolov3.weights? or tiny-yolo?

parvathycec avatar Aug 03 '18 16:08 parvathycec

could you tell more about how to transfer darknet weights to h5 file, I need use other weights file, thanks

phoenares avatar Sep 17 '18 06:09 phoenares

could you tell more about how to transfer darknet weights to h5 file, I need use other weights file, thanks

Have you resolved it, with the other weight file?

Artiintern avatar Jun 03 '22 16:06 Artiintern