vced icon indicating copy to clipboard operation
vced copied to clipboard

VCED 可以通过你的文字描述来自动识别视频中相符合的片段进行视频剪辑。该项目基于跨模态搜索与向量检索技术搭建,通过前后端分离的模式,帮助你快速的接触新一代搜索技术。

Results 6 vced issues
Sort by recently updated
recently updated
newest added

ConnectionError: failed to connect to all addresses; last error: UNKNOWN: ipv4:0.0.0.0:56207: Failed to connect to remote host: Connection refused |Gateway: Communication error with deployment at address 0.0.0.0:56207. Head or worker...

./startup.sh cannot import name 'nametuple' from 'collections' (unknown location), centos7 python3.9.8

我已经让我的环境满足了下面这个三个条件: os.environ.get("DEVICE") == "cuda" and torch.cuda.is_available() and os.environ.get("JINA_MP_START_METHOD") == "spawn" 但是当我上传视频开始提取画面的时候,却报错了,提示cuda无法使用,难道还需要修改其他地方嘛? 我的本机是win10,笔记本电脑,本机有6g显卡。我用的wsl里的ubuntu 像开启GPU,让速度快一些,有谁知道嘛?

结果只显示done, 但是没有剪辑的片段 [ ![图片](https://user-images.githubusercontent.com/86837980/218306028-f64bf70e-7369-4098-97d1-52d42aeca8ee.png) ](url)

目前部署在服务器上,查看到文件大小被限制在200M,演示的gif显示是有100GB的,这个如何去修改?

报错日志如下: ERROR Flow@21255 Flow is aborted due to ['video_loader', 'image_encoder', 'text_encoder', [11/20/22 21:17:04] 'indexer'] can not be started. Traceback (most recent call last): File "/home/liwensheng/rustprojects/testdir/vced/code/service/app.py", line 76, in with f:...