caffe2pytorch-tsn icon indicating copy to clipboard operation
caffe2pytorch-tsn copied to clipboard

Published 20 hours ago • verified publisher icon shuangshuangguo

Mapping of label

Open wsy19961129 opened this issue 5 years ago • 1 comments

hello, I am just wondering how do you map the label to one-hot encoding. Is it just sort the label(string) in alphabetical order? E.g. in UCF101, ApplyEyeMakeup=0 and ApplyLipstick=1. I test the model using your pretrianed weights while on UCF101/split1 is 76% and on HMDB51 is about 43.3% and I do not know what the problem is. Thanks!

wsy19961129 avatar Jun 03 '19 16:06 wsy19961129

@wsy19961129 I got the same problem that the accuracy on UCF101/split1 is only 75.53%. Have you solved this problem?

linshuheng6 avatar Jul 31 '19 13:07 linshuheng6