nishantk-iisc/generation-of-indian-sign-language-letters-and-numbers

How nishantk-iisc/generation-of-indian-sign-language-letters-and-numbers works

This repository generates class-conditional Indian Sign Language images, and trains the progressive GAN used for generation. The main workflows are preparing image data from videos, progressively training a generator against a critic, and entering text at inference time to generate and label sign images. The README also describes support for letters, numbers, and words. Inference and training excerpts show model and output handling; some inference steps and dataset details are only documented, so those links use README evidence.

Main entry points: train.py Progressive training · inference.py Prompt inference · attention.py Attention layers · frame_extract.py Frame extraction

Components 13

Dataset preparation

Frame extraction frame_extract.py
Class image data data

GAN models

Conditional generator generator.py
Conditional critic critic.py
Attention layers attention.py

Model training

Run configuration config.py
Progressive training train.py
Model checkpoints

Text inference

Inference options config.py
Prompt inference inference.py
Sign image output inference.py

Other components

Class videos
Text prompt

Connections 14

Class videos → Frame extraction: provides frames frame_extract.py
Frame extraction → Class image data: writes frames frame_extract.py
Class image data → Progressive training: loads images train.py
Run configuration → Progressive training: configures train.py
Progressive training → Conditional generator: trains train.py
Progressive training → Conditional critic: trains train.py
Conditional generator → Attention layers: uses layers generator.py
Conditional critic → Attention layers: uses layers critic.py
Progressive training → Model checkpoints: writes weights train.py
Text prompt → Prompt inference: enters prompt inference.py
Inference options → Prompt inference: sets options inference.py
Prompt inference → Attention layers: uses layers inference.py
Model checkpoints → Prompt inference: provides weights README.md
Prompt inference → Sign image output: generates images inference.py

More Python diagrams: paradigma-inc/limite-violetto · paramind2025/can · thunlp/ouroboros · zijinz456/opentutor · academy-agents/academy

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·