Firmin.Sun comments

Results 8 comments of


                                            Firmin.Sun

A simple idea to solve the error : "rpn_loss_box: nan"

I also get this issue. And I have deleted the -1. But it still happen! Does it have a better solution now? ![image](https://user-images.githubusercontent.com/9877644/41644942-26dc5d3a-74a2-11e8-858e-3b25719ed70e.png)

A simple idea to solve the error : "rpn_loss_box: nan"

@kinzzoku yes, I've deleted .pkl file and rebuild it again, but same issue with me.

获取联系人资料过程发生错误

已经无法获取好友，组等信息，网络错误了：第5次请求“http://s.web2.qq.com/api/get_group_name_list_mask2”时出现网络错误 HTTPConnectionPool(host='s.web2.qq.com', port=80): Read timed out. (read timeout=30), html='' [2018-05-04 00:27:57] [ERROR] 获取群列表失败

When does the code release?

Maybe,it can help you guys. https://github.com/Feynman27/pytorch-detect-to-track

Trying to create an rttensor for a lora, I got the error ERROR:root:Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm) Traceback (most recent call last):

same issue, who can fix it, thanks

Firmin.Sun

A simple idea to solve the error : "rpn_loss_box: nan"

A simple idea to solve the error : "rpn_loss_box: nan"

获取联系人资料过程发生错误

When does the code release?

Trying to create an rttensor for a lora, I got the error ERROR:root:Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm) Traceback (most recent call last):

Custom Recipient for email

Custom Recipient for email

Custom Recipient for email