Fu Yuqian
Fu Yuqian
open “data_loader.py” by vim, and you will find the “^@”, just delete them. and if you use Pycharm or other IDEs, you can not observe this null byte.
我传了一下在这里： https://drive.google.com/file/d/1e3TklMlVBCG0XRfEw6DKStJGdmmXgvq5/view?usp=drive_link
> Hi, > I solved that with this: #11 @Luciano07 @bharat-b7 Thanks very much！！(#^.^#)
I am not sure whether I can find the script I exactly used. But it can be easily achieved by randomly sampling $num_{target}$ examples from the target base set.
> Could you please provide your code about generating .json file? Hi, @canaan33 , I just uploaded the code: https://github.com/lovelyqian/Meta-FDMixup/blob/main/process_labeled_target_data.py, hope it helps.
Thanks，u are right!
> I want to know when will you release the model and the submodels rgb and depth? > Also, you mentioned we can train the submodels by ourselves through the...
这个txt只是用来记录测试结果的，可以随意替换路径
> 运行测试文件时，总是显示数据集参数无法识别，不清楚是哪儿的问题 应该就是你在另一个issue中提到的txt文件没有定义的问题
只用rgb帧用标准的feature--FC---softmax分类任务训练backbone network