myt889

icon location Beijing

Results 6 comments of myt889

Trained on small dataset with pre-trained weight, don't have good result.

> I also tried the experiment. > lr = 3e-5 > batch_size = 8 > > > Epoch : 1 - loss : 0.0648 - acc: 0.9752 - val_loss :...

Need the code for the multi-label dataset Pascal VOC

> hey, buddy, I am trying to revise this project to a multi-label-appropriate version. I don't know if you have already begun this work, and now I have some code...

IOError: [Errno 2] No such file or directory: '/path/to/identity_meta.csv'

Hi,I can not open the path as you have offered,can you send the corrsponding file to [email protected], thank you so much. > You can find it here: http://www.robots.ox.ac.uk/~vgg/data/vgg_face2/meta_infor.html

Several Questions

Ok. Thank you for your quick reply. I will try your method, and hope you can offer guidence if needed. Once again, I really appreciate your works. Best regards!

一个函数中同时取多个变量

> 作者你好，最近用了一下你的这个小工具，非常好用。但是有个问题，比方说我想一次性获取forward函数中的多个变量，请问我该怎么做？ 您好，您实现了一个函数中同时取多个变量了么？

Hi， i have some questions about the project-NCR

> Hi, > > 1. log operation is already applied to logits on Line 44: > s_softmax_temp = jax.nn.log_softmax(logits / temperature) # [n, d] > > No need to do...