hangon666
hangon666
Traceback (most recent call last): File "test.py", line 32, in frontalize(saved_model, datapath, 3) File "test.py", line 16, in frontalize test_pipe = ImagePipeline(datapath, image_size=128, random_shuffle=False, batch_size=mtest) File "/home/hanchao/Wu/frontalization/data.py", line 108, in...
请问在不同网络模型上进行对比实验时,初始学习率等超参数是怎么设定的?
请问在您计算wing loss的时候,作为ground truth的 68个3D人脸点是怎么得到的?
请教信
同学您好,冒昧打扰了,不好意思! 我对三维人脸重建方向的研究很感兴趣,在Github上的很多项目上都有见过您,想和您请教一些问题。 请问您知道带人脸纹理texture的三维人脸重建是怎么实现的吗,请问您有相关的训练代码或测试代码可以分享一下吗?万分感谢!!! 我的邮箱:[email protected] 希望能和您交流一下,期待您的回复,谢谢!
Hi, thanks for your great job, byt the way, did you reimplement the loss functions and could you give me some guide?
您好,您提供的google driver地址没法下载,请问可以提供别的下载方式吗?谢谢!
Hello, sorry for disturb, I'm wondering about the effect of inv_normalize, and `target_img = self.inv_normalize(input_img)` why target_img can be defined like this? Thanks for your help!!!