facebookresearch/SlowFast

Demo programme on camera input

Open

#34 建立於 2019年11月18日

在 GitHub 查看
 (57 留言) (0 反應) (0 負責人)Python (6,064 star) (1,167 fork)batch import
enhancementgood first issue

描述

Hi,

I find this project very interesting and thanks for open-sourcing it.

I am trying to make a demo programme to load and run the models (e.g. SlowFast) and infer it using input from a USB camera to visually evaluate the accuracy and performance and I wonder if it would it be possible? if so could you briefly elaborate on which modules should be used and how it could be implemented?

Thanks in advance.

貢獻者指南

技術棧
pythonpytorch
領域
machine learningai
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
3-5 days
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
needs investigation
前置要求
PythonPyTorch basicsOpenCVSlowFast model understanding
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
20
研究方向
The issue asks whether it is possible to run SlowFast models on live USB camera input and requests guidance on implementation. To proceed, first explore the existing SlowFast repository for any camera or demo scripts. Then, consider using OpenCV to capture frames from the camera and feed them into the model's inference pipeline. Look at the provided inference examples (e.g., tools/run net.py) and adapt them for real time processing. The many comments likely contain suggestions from maintainers and community members; review those for specific module references and potential pitfalls.