Liu Songtao
Results
3
issues of
Liu Songtao
mAP
32
Have you ever evaluate the transformed trained model in VOC2007? I've tried your code and got a 71.9 mAP while the original is 76.8. Then I found a tiny error...
What is your initialization of the detector? Is that exactly the same with original paper to set bias = -log((1-pi)/pi) or use normal softmax for several times like your previous...
Hello, I implemented your setting 2 and 3, but both get a wrong performance much like [https://github.com/revilokeb/inception_resnetv2_caffe](url), so could you release some results or tips about these experiments?