WENZHE LIU

Thanks for your great job and kind sharing. I just wonder what motivated you to design the architecture, InceptionResnetV1? Did you release any paper already? Thanks in advance.

No pose_hrnet_w48_256x256.pth in GoogleDrive or OneDrive link?

4

heyyyyy, appreciate ur great work. Here is my problem, I couldn't see your pre-trained model, *models/pytorch/pose_mpii/pose_hrnet_w48_256x256.pth* in neither Google Drive or One Drive link. Will you upload it again? Or...

How to get the benchmark performance on FER2013?

14

Thanks for your great job and kind sharing. I am doing some work on FER, and intend to get the performance of some classic network (including Resnet34, Resnet152, etc.) as...

KeyError: 'roi_fmap.0.weight' in train_models_sgcls.sh

2

Hey there, I came across a problem similar to this #41 ,when I did the command `bash train_models_sgcls.sh`， I got the error message listed later. I renamed the downloaded file...

Question about the RCF edge detection framework.

2

Thanks for your great work and kind sharing. I successfully reproduce the edge detection result, as `2018.jpeg`:  `2018.png`:  After NMS process, it turns like:  However, when it...

Thanks for your great work and kind sharing. I am interested in the search space scale of your work, also known as the network options during search. Have you ever...

Poor performnace when reproducing evaluation on market1501

2

Thanks for your great work and kind sharing. I am actually a beginner in ReID, and trying to reproduce the test stage of this repo at first. Environment: 3090Ti, CUDA...

poor metrics when training on market1501

2

hello, thanks for your great work and kind sharing. When I intend to reproduce your work, and simply train on market1501 at first. The output info seems weird. The metrics...

Only 12813 for flow and 13190 for rgb in result

2

Heyyyy! As known, there are 13320 videos in UCF dataset in total, but I only get 12813 results for flow extarction and 13190 for RGB frame. is any other come...

按项目中步骤指示操作之后，无法复现

2

感谢您的分享， 我按照您的步骤操作之后，仍然无法实现功能（无法读取口袋48房间中的新消息），还麻烦各位指导一下。 我是用一个QQ号登陆的酷Q，更改应用管理之前还能有机器人互动，但是之后该QQ号就不会返回消息了。 以下是我的实验情况：  运行两个py文件的结果：   还麻烦指点一下。 另存在以下疑问： 1. 阅读`main.py`的代码之后，本项目关于口袋48实现的功能是否就是监控房间中的消息。有没有类似的项目可以监控如下图这样的信息呢？  2. setting.conf中的roomid和ownerid只能设置一个吗？如何同时监控多个房间应该怎么设置？ 抱歉第一次接触这一类的项目，问题比较多。（表妹给的任务5555）