twsha

Results 6 comments of twsha

How should I further set up the code to change to single gpu training

I train directly through the train file,find that it can't read dateset, can you tell me that below the annotaions file The train.txt under the annotations file have content? thank...

thanks

hi i would like to know how to train your own dataset,thank you

> @xiexinch @AI-Tianlong @ZJLauu I have the same bug and I use the latest version. How to fix ![image](https://private-user-images.githubusercontent.com/7938373/248236065-7c873e65-2567-4c8f-8f64-241b24fcdc77.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.f1vPXYU7ffvEYGaZMI3tWLlW5eRc0jURi3QfgG2PSFc) the bug is : ![image](https://private-user-images.githubusercontent.com/7938373/248236918-4e33db89-365d-4c5b-981b-c600f9b8f8af.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MDYxNjYwMDcsIm5iZiI6MTcwNjE2NTcwNywicGF0aCI6Ii83OTM4MzczLzI0ODIzNjkxOC00ZTMzZGI4OS0zNjVkLTRjNWItOTgxYi1jNjAwZjliOGY4YWYucG5nP1gtQW16LUFsZ29yaXRobT1BV1M0LUhNQUMtU0hBMjU2JlgtQW16LUNyZWRlbnRpYWw9QUtJQVZDT0RZTFNBNTNQUUs0WkElMkYyMDI0MDEyNSUyRnVzLWVhc3QtMSUyRnMzJTJGYXdzNF9yZXF1ZXN0JlgtQW16LURhdGU9MjAyNDAxMjVUMDY1NTA3WiZYLUFtei1FeHBpcmVzPTMwMCZYLUFtei1TaWduYXR1cmU9MDE3ZDExMDFmODdkNTdkOTVkOTVkYmQ0YmJkYzYzYTczMDAzMDhkMzY4YTBlZWM3ZmZjMTVhMDQzYWYzOTM4MSZYLUFtei1TaWduZWRIZWFkZXJzPWhvc3QmYWN0b3JfaWQ9MCZrZXlfaWQ9MCZyZXBvX2lkPTAifQ.TgP1U6ILvHkRs_MmdOrIZ39GEbcWN_r7aK3eVqiYgr4) > > ----> > > ![image](https://private-user-images.githubusercontent.com/7938373/248237032-d08e05c0-049c-4f8b-9349-6c0cd57c5ae5.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.4L45Hn2cGodpjWXu7yqEOx0MVgmt5naLQw7ZCDbU368)...

> 作者你好,我在实验中想使用aff应用于解码结构,但是在使用的时候发现在最深层的尺度时aff是有效的,在其他尺度或者在所有尺度添加aff的时候反而效果变差了,想请教一下这是什么问题,需要对哪些部分进行调整吗? 你好能交流一下怎么把这个注意力出入到encoder和decoder的连接中,我要加的模型是linknet,感谢