LUOLUO1313677

Results 4 issues of LUOLUO1313677

![image](https://user-images.githubusercontent.com/123624781/234787045-970a6482-c2c8-4096-8536-f7728fe6c340.png) ![image](https://user-images.githubusercontent.com/123624781/234787145-9f3a9adc-caf5-48d0-9038-3ddad455dbe9.png) 请问,为什么只有7个type,domain_label却要初始化8个0,我的猜想是第0维度是batch_size, 但是我不理解这个mask处理,为什么要把batch_szie这一维==1的挑出来,就是mask这段不太理解在做什么。

in Table 1, the WQT is used to create type1 data. Does ori+type1 mean that you put ori (4000 images) and also type1 (4000 images) total 8000 images of fully...

If we adopt WQT to create val_8 (do not appear in training set), : 1.how to keep annotation correct when we create val_8 (if we set WQT output size=512,it's a...