nilboy / tensorflow-yolo

tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test)
773 stars 312 forks source link

The result on pascal_voc 2007 validation set is bad. #32

Open gauss-clb opened 6 years ago

gauss-clb commented 6 years ago

I have tested your tiny-yolo on pascal_voc 2007 validation set. The result of test is so bad, I think. Do you use paramters from darknet tiny_yolo or trained by yourself? Can your tiny_yolo reach MAP 50%?

gauss-clb commented 6 years ago

test test

test

ss199302 commented 6 years ago

@gauss-clb Have you solved the problem of tiny_yolo?

gauss-clb commented 6 years ago

I'm sorry, I think it is too difficult to reproduce the MAP of yolo. Maybe the author use many tricks. And I'm also wonder whether the difference of tensorflow and darknet cause the difference in MAP.

ss199302 commented 6 years ago

thank you 。