Herman

麻烦问下我这样配置有问题吗：   SwitchOmega设置：  我这样配置之后总是上不了Google

@choyingw Thank you for your reply. I want to know how to tune the detected bbox size with a little bit? BTW, the I found the image resolution of your...

I encountered this error as well, any help, pls?

@yc19960713 ，能问下大概下载到多少G可以这样弄呀，我在Edge浏览器上下载，怎么没看到有.crdownload文件呢？

@yc19960713 ，我这样尝试了一下，下载了14G左右的train.tar.gz文件，然后修改.crdowndload文件后缀名，解压的时候报错，说文件不完整或者其他错误，反正就是解压不了，修改了.tar.gz和.zip后缀都不行

@yc19960713 你是修改成什么后缀呀，我用Bandzip还是不行，说文件已损坏或未知的文件格式错误。

@Gang-Chen-China I also encountered this problem, has anyone solved this? Update: You can use this one: [https://github.com/v-wewei/etw_pytorch_utils](https://github.com/v-wewei/etw_pytorch_utils)

@AmingWu @HaozheQi, Hello, I wonder how did you final solve this problem, I run the following scripts: ```python python test_tracking.py --data_dir=/mnt/study/Datasets/KITTI/tracking/training ``` And also got the result like yours: ```shell...

Thanks for your reply. So it means you use the surface points (`x`) in `encoder` to get the embedding of `centers` in surface points, and when decoding, you use the...

@1zb Could you offer a subset of the large whole dataset? In this case, at least we can dig into the pipeline for better understanding. Or could you give some...