jianbaba
jianbaba
我用的是自己的xml数据集,用coco是可以跑通的
解决了,是我数据集的数据太少了,打扰啦
解决了,是我数据集的数据太少了,打扰啦
哦哦,懂了,您的det1-memory-stitch.prototxt + "det1.caffemodel"的作用是什么?还有里面的三个层的作用是?是您自己定义的层?我看原作者没有这个! layer { name: "box“ type: "PredictBox" bottom: "Softmax" bottom: "conv4-2" top: "bb_map" top: "boudning_box" predict_box_param { positive_thresh: 0.6 stride: 2 receptive_field: 12 bbreg_exp: false } } layer...
@happynear https://github.com/happynear/caffe-windows/tree/ms 请问用您的caffe的意思是在这里下载并配置是么?能不能在linux下配置?要怎么做
@happynear 嗯嗯,好的谢谢您了,我就是要找一份c++实现,在linux下分装成静态库。因为我之前只用python调用caffe,c++基本小白,您写的c++代码对我也很有帮助,有助于我学习c++调用caffe,您还耐心帮我解答问题,真是太谢谢了
@Seanlinx ,hi,Can you tell me how to plot the PR curve for WIDER test?
I use the demo script ofDemo_AFEW_Attention.py. Is this the reason?
thanks
excuse me , I have the same question, can you tell me how to do it ? thanks! @buweiaini