infinitered/nsfwjs

Run on every frame in Video

Open

#39 opened on Mar 4, 2019

View on GitHub
 (18 comments) (0 reactions) (1 assignee)JavaScript (7,090 stars) (507 forks)batch import
enhancementhacktoberfest-acceptedhelp wanted

Description

Much like the discussion over in #38 There's been a request to run on every frame in a video.

It's possible to do in JS like so: https://jsfiddle.net/bmartel/3h98gsvk/11/

Maybe a syntax like model.classifyVideo(video) or model.classifyAny(img|gif|video)

Contributor guide

Tech stack
javascripttensorflow
Domain
machine learning
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.
1-2 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.
clear
Prerequisites
JavaScript basicsfamiliarity with TensorFlow.jsunderstanding of video frame processing
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50
Research direction
The issue requests adding video classification capability to the NSFWJS library, with a suggested API like `model.classifyVideo(video)`. There is a reference implementation in a JSFiddle (see issue body) that processes video frames using canvas and a 'draw' function. To implement, study how the existing `classify` method works for images, then extend it to accept a video element. The video should be sampled at a reasonable frame rate (e.g., requestAnimationFrame) and each frame passed to the model. Look at the discussion in the issue for additional context and any existing attempts. Key files to examine: the main model file (likely `index.js` or similar) and any image classification methods. Ensure the solution is efficient and handles cleanup of video resources.