starrlu

Results 3 issues of starrlu

Can you release the training weight of ROHQD? And what is the epoch of training, the training epoch is not seen in the code and the paper, and the code...

使用第一阶段的预训练模型 训练vqfrv1 20万迭代后 训练结果如下图 ![image](https://github.com/TencentARC/VQFR/assets/85616217/a3de072c-ac1c-4584-8966-a86670789ed1) 请问有遇到过类似情况吗 该怎么解决

![image](https://github.com/TencentARC/VQFR/assets/85616217/c23c2dd5-5c4a-4952-a008-6434e2b6dd13)