LiZhiyuan

Thanks for sharing your work, but I have a problem in the loss function. In dice_coeff, y_true is a label, but y_pred is a probility, what does dice_coeff mean? I...

Question about the probability

2

Hi, thanks for your great work. I notice that the output of the yolo is a 7*7*30 tensor, and some of the output means Pr(class|object), and some means Pr(object)， but...

Question about train and test

8

Thanks for your great work! I have some questions about the training and test setting. When training, [no matter which class attention vector combined with the query feature, the groundtruth...

训练一张最像狗的图片

1

大家好，请问如何利用一个已有的网络，比如VGG，训练一张图片，使得它在狗这个类别上的概率最大呢