ChenFeynman
ChenFeynman
Good job,i get it!
https://bj.bcebos.com/acg-algo/PaddleVideo_application/VideoQualityAssessment/ppTSM.pdparams ValueError: `paddle.load` can not parse the file:pretrained_dygraph/ppTSM.pdparams. 已经排除路径错误。 Debug信息： - 预训练模型是140M，自己从头train的model是89.9M。 环境： - paddlepaddle-gpu 2.2.2 py37_gpu_cuda10.1_many_linux
参考文档的预训练模型可用 [https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/zh-CN/model_zoo/recognition/pp-tsm.md#模型推理]
> annlite=0.3.13
希望非容器化部署，谢谢！
> 最大的困难是milvus的非容器化，大佬们，有什么办法？ 用Faiss替代
torch==1.13.1 onnx==1.13.1 onnxruntime===1.11.1 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 440.64.00 Driver Version: 440.64.00 CUDA Version: 10.2 | 0 Tesla V100-SXM2
> Well, you a need web crawler to download the source videos. We provide the download script, which could be found at [download_cnvid_video.py]. And you need to change the url_head...
### same problem with Nvidia-v100. ``` vllm-0.5.3 nvidia-nccl-cu12-2.20.5 outlines-0.0.46 torch-2.3.1 triton-2.3.1 xformers-0.0.27 ```