Xinxin Peng

Results 10 comments of Xinxin Peng

各位大佬，paddlevideo中的st-gcn修改训练配置文件，将window_size从50改为100后，训练推理，并在paddledetection中进行pipeline测试，报错？如何修改呢，没找到修改位置，应该是reshape问题吧？

请问一下你是怎样导出paddlevideo训练出的模型到pphuman的pipeline呢

使用NTU-RGBD数据集时配置文件报错

> ST-GCN在FSD上的推理功能已添加， 但ST-GCN在NTU-RGB+D数据集上的推理功能还没加， 两者数据预处理过程有些区别 请问最新的版本里添加了NTU-RGB+D数据集上的推理功能吗

PoseC3D configuration about SlowFast network

@taliegemen Hi I am just wondering have you been able to implement the fusion of pose and rgb?

PPHuman可以增加自定义视频的行为检测教程吗?

https://blog.csdn.net/Andrwin/article/details/124250580 请问一下我用paddlevideo训练了可以识别120种动作类型的stgcn模型后，尝试用tools/export_model.py 导出模型，在对应的configs/recognition/stgcn/stgcn_ntucs.yaml 里怎样修改configs/recognition/stgcn/stgcn_ntucs.yaml 里的Inference参数呢

The relevent source/paper to cite for each method

Thanks @sacdallago ! are there any chance that the details of training dataset for Word2Vec model can be provided? Just found so hard nowadays to find some other available source...

PoseC3D RGBPose-SlowFast

> I am trying to implement a mmaction dataset for loading skeleton and rgb videos in same time. > > I would really appreciate it if the part of loading...

Do Inference size width and height have to be equal?

> It doesn't need to be width=height but you must use the same size of the trained model (640) to get the correct output. The sizes must be multiple of...

Question on memory consumption for CRD loss when the dataset is very large

Hey TMays I am coming accross the same issue here. Have you been able to solve it?

webcam_demo code

> Hi have you made any progress in this project?

Video MiniGPT4

> Yes! We are trying to train a video model for better temporal reasoning! any timeline proposed yet for the new module? rumor says that the gpt5 might incorporate video...