runrun

我也遇到这个问题，怎么会这样

waiting....

not yet

@kevinjliang the file in path Lib.TensorBase is lost, why?

waiting online

@ I have already fined tune resnet101_rfcn_final.caffemodel model, it got 95% accuracy in training. But in demo_rfcn.py, I test my image, the predicted boxes were inaccurate. I do not know...

经过测试，模板中有的边缘梯度，测试图像中除有模板有的，还有多余的东西，实际应该是NG，但是判定为OK，对于多余的，应该如何考虑？

金字塔层数不对应，Detector默认是金字塔层数为2,步长[4,8],在match过程中， for (int l = 0; l < pyramid_levels; ++l) { int T = T_at_level[l]; std::vector &lm_level = lm_pyramid[l]; if (l > 0) //l>0应该去除，i=0代表金字塔层1，i=1代表金字塔层2，以此类推 { for(int i = 0; i...

matchClass()函数中关于int offset = lowest_T / 2 + (lowest_T % 2 - 1);中心点吗？ (x / T - 8 + best_c) * T + offset如何得来的？

第二层不是int lowest_T = T_at_level.back(); //8？ SIMILARITY_LUT是如何得到？