xiaoyuzhu666

Results 7 comments of xiaoyuzhu666

train on COCO but precision,recall and cls_acc Value has not changed it always 0

I got the same problem.

RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

> please，help me Hi，I got the same error，did you solve it？

RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

Thanks,but I have changed it, the error still exist(filters=18,class=1)😭 ---Original--- From: "AadeIT"

RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

> @xiaoyuzhu666 > filters of config file > A total of three > find [yolo] > > [convolutional] > size=1 > stride=1 > pad=1 > filters=255 activation=linear > > [yolo]...

RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

> @xiaoyuzhu666 Has nothing to do with the anchor I changed “anchors”and “num” using k-means clustering，，，the number of anchor is 3（not 9） [yolo] mask = 0 anchors = 65,65, 97,97,...

RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

> @xiaoyuzhu666 > I think you useing the default anchors > K-means clustering in yolo v2 ,not yolov3 0.0 Oh！！！Thank you！

你好，请问训练时recall50、recall75、precision都始终为0是咋回事？另外，学习率始终为0.001嘛？

刚开始是0,再多训练一些epoch就不是0了哦 ---原始邮件--- 发件人: "FELT"