ryanjay0/miles-deep

Health v2 · maintenance only

Adoption not part of the score

2658 stars · 280 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Miles Deep is a C++ deep learning application built on Caffe that classifies each second of a pornographic video into six sexual act categories with 95% accuracy, then automatically edits the video based on those classifications. It also serves as a general framework for classifying video with any Caffe model using batching and threading.

Use cases

• automatically edit porn videos to remove non-sexual scenes
• cut out specific sexual acts from a video
• classify video content per second with a CNN
• run video classification with a custom Caffe model
• batch-process videos for NSFW scene detection

When to choose

• you need automated per-second classification and editing of adult video content
• you want a reusable C++ framework for video classification with Caffe models
• you need a GPU-accelerated video scene classifier on Linux

When to avoid

• you need a maintained tool - the project has not been updated since 2018
• you need Windows or macOS support
• you need general-purpose NSFW image classification rather than video act classification
• you prefer modern frameworks like PyTorch over Caffe

Facets

application · maturity abandoned

machine-learning deep-learning video-processing image-processing computer-vision machine-learning deep-learning media cpp nsfw-classification video-editing caffe adult-content video-classification video linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ryanjay0/miles-deep")