The result on pascal_voc 2007 validation set is bad.

[gauss-clb]

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]

[ss199302]

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

[gauss-clb]

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]

thank you 。