-
Notifications
You must be signed in to change notification settings - Fork 73
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
大佬想问一下您的代码细节问题 #5
Comments
targets 包括: idx, class_id, x, y, h, w (yolo format) |
也就是说,这里的class_id, x, y, h, w都是int |
不是 只有idx 和 class_id 是 int (但是在实际计算里的时候是这两个整数会被转化成float的,e.g. 1 -> 1.0) Edit: the target size should be (total # of bounding boxes in a batch) x 6 |
大佬,假如说是(batch_size, 6)的大小的话,假如一张图的bbox有多个呢?这不就没办法表示了吗? |
不好意思 我说错了 target size应该是 一个batch里面bounding box总数 x 6 |
大佬,我代码看得有点晕,这个idx是指该图片矩阵在batch中的位置吧?比如第一张的话idx=0;第二张idx=1这样? |
对的 |
稳了大佬,我大概都看懂了 |
优秀 |
您的YOLOLayer类里的forward函数里的targets的大小是什么呢?能给个比较详细的解释吗?我想用VOC数据集来训练,也是第一次接触YOLO,拜托了
The text was updated successfully, but these errors were encountered: