facebookresearch/SlowFast

Demo programme on camera input

Open

#34 opened on Nov 18, 2019

View on GitHub
 (57 comments) (0 reactions) (0 assignees)Python (6,064 stars) (1,167 forks)batch import
enhancementgood first issue

Description

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.

Contributor guide

Tech stack
pythonpytorch
Domain
machine learningai
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
PythonPyTorch basicsOpenCVSlowFast model understanding
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
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.
Demo programme on camera input · facebookresearch/SlowFast#34 | Good First Issue