Liu Songtao

@shwoo93 What is your max epoches? The above results are obtained around epoch 220.

There was an error in the original RFB_Net_vgg, as #23 mentioned. And now I fixed that issue and got a new higher performance in VOC ([80.7%mAP](https://drive.google.com/open?id=1apPyT3IkNwKhwuYyp432IJrTd0QHGbIN)) with just one trial....

@pikerbright do you test the released weight above? I got that result (80.72%) at epoch 250 and test it on pytorch 0.3.1, but when I switch to another machine with...

@pikerbright I trained the model on pytorch 0.3.1 with an old version of this repository. But the update codes only fix the incompatibility problem for pytorch 0.4, not a big...

@zhch-sun [Here](https://github.com/ruinmessi/RFBNet/blob/master/train_RFB.py#L242-L253) is the released warm-up code. The default settings could achieve about 80.5% at around 220-250 epoch.

@zhch-sun Hi, for Q1, the multiple versions of priorbox layer comes from the original SSD, and this code is mainly based on the [ssd.pytorch repository](https://github.com/amdegroot/ssd.pytorch). I just use the default...

@lxtGH Did you use the latest code in this repository with correct RFB_Net_vgg? And I suggest you can save the model every 5 epoch after 200 epoch to test the...

@lxtGH I guess the reason is that the default setting is set for batch_size=32, so you may double the lr to 0.008 or 0.007 for batch_size=64. If it still not...

@lxtGH @zhch-sun Well, I will check this gap if I have enough GPU resources.

@LightToYang Yes, you are right! Thanks a lot for pointing out this mistake. And actually all my experiments are using the architecture like your picture. I just ignore this details...