feixiangdekaka

Question about stylized dataset improve robustness

3

Hi, I have trained the combined VOC2007 2012 trainval datasets on CenterNet(objects as points) with resnet50dcn backbone, the result is bellow: resnet50dcn without stylized : 75.19 resnet50dcn with combined data...

question about nms

3

the nms doesn't according score ,why not according each class and score .

label for negative!

4

# 计算每一个先验框应该有的权重 alpha_factor_for_back = keras.backend.ones_like(labels_for_back) * alpha alpha_factor_for_back = backend.where(keras.backend.equal(labels_for_back, 1), alpha_factor_for_back, 1 - alpha_factor_for_back) focal_weight_for_back = backend.where(keras.backend.equal(labels_for_back, 1), 1 - classification_for_back, classification_for_back) focal_weight_for_back = alpha_factor_for_back * focal_weight_for_back ** gamma...