Hi, I use my own .weights file from the training of the darknet, and I use your code to test. I modified the network structure and it loads weights successfully. But the outputs of the last layer are very very large numbers about 70000+ instead of smaller than 1. Would you like to tell me why, I have been traped in it for several days.Thank you very very much!!

gliese581gg / YOLO_tensorflow

tensorflow implementation of 'YOLO : Real-Time Object Detection'

Other

1.72k stars 656 forks source link

Hi, I use my own .weights file from the training of the darknet, and I use your code to test. I modified the network structure and it loads weights successfully. But the outputs of the last layer are very very large numbers about 70000+ instead of smaller than 1. Would you like to tell me why, I have been traped in it for several days.Thank you very very much!! #30

Open zh0ngtian opened 7 years ago

zh0ngtian commented 7 years ago

Hi, I use my own .weights file from the training of the darknet, and I use your code to test. I modified the network structure and it loads weights successfully. But the outputs of the last layer are very very large numbers about 70000+ instead of smaller than 1. Would you like to tell me why, I have been traped in it for several days.Thank you very very much!!

ss199302 commented 6 years ago

@YaoZhongtian How to modify the network structure, the need for great God help

zh0ngtian commented 6 years ago

The problem I issued has been solved. I write the test part of YOLOv2 inspired by your code, you can see it in my repositories. Thanks for your work !

wingerboy commented 6 years ago

can you guide me in the first few steps? I do not know how to implement it!!!thank you very much