wangguanzhong

先确认下run_mode设置为paddle是否会报错

您好，请问问题还是否需要解决，目前相关图像生成能力集成在PaddleMIX中，https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求

you can refer the doc here https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/develop/install/pip/linux-pip.html

您好，请问问题还是否需要解决，目前多模态视频能力集成在PaddleMIX中，https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求

您好，请问问题还是否需要解决，目前多模态视频能力集成在PaddleMIX中，https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求

您好，请问问题还是否需要解决，目前多模态视频能力集成在PaddleMIX中，https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求

Thx for your contribution，the number of files is too large and maybe you could clean the code or set them to a thirdparty codebase

check the length of input is less than k, if so, could minimize the length of input and k

you could refer to the document https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/zh-CN/quick_start.md for action recognition, and more demand could send to PaddleMIX（https://github.com/PaddlePaddle/PaddleMIX/tree/develop） for large multimodal model

you could also refer to the application here https://github.com/PaddlePaddle/PaddleVideo/tree/72c5b40d3415b34cdf50f2848a230d983dc0f7ae/applications