linjiaojiao

@xmyqsh Hi, you mentioned that the logic of choosing the feature map for ROI can be implemented either in proposal_target_layer or in roi_pooling_layer. And I implemented this algorithm in roi...

@xmyqsh Thank you very much! May I ask you about your training results? I modified the roi_pooling_layer by choosing the feature map (P2/P3/P4/P5) before roi pooling operate, and the rest...

@xmyqsh OK. Thank you for answering me!

@iamZe 您好！我现在也在用casia数据集并使用softmaxloss进行训练，可是loss一直在8.x，并且没有下降趋势，我用的是vgg16，accuracy也才0.00x。请问您的prototxt是什么样的，以及学习率如何设置呢？我的proto分类有10572类，学习率0.01和0.001都试过，也不好。。。

@IrvingShu 没有。。 不过你的loss确实有点小，你用softmax预训练过了吗