westnight
westnight
thank you shicai. i want know compared with the calculated mean value in input layer, how it perform if i use 127.5.And why you set scale 0.017.
你好happynear，如果有时间的话能否解释一下PCA在训练和测试中怎么用？
have you ever test your model on wider face, it was as low as 0.28, 0.25, 0.12 on val dataset.
how you come up with the idea of the concat train. good job, i will try it
这部分优化代码在哪里能看到？
Hello, I have a question about the structure. In your paper, there is no other layers bwtween the two conv layers with shared weights , but as we know two...