brade31919/SRGAN-tensorflow

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

51
/ 100
Established

Uses a two-stage training pipeline: first training a residual network (SRResnet) with MSE loss, then adversarial training with VGG19 perceptual loss for photo-realistic output. Integrates pre-trained VGG19 weights from TensorFlow-Slim for content-based loss computation and supports distributed GPU training with TensorBoard monitoring.

858 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

858

Forks

278

Language

Python

License

MIT

Category

image-super-resolution

Last pushed

May 12, 2023

Commits (30d)

0

GitHub
Image Super-Resolution · 60 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/brade31919/SRGAN-tensorflow"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Compare

SRGAN-tensorflow and Fast-SRGAN

Related frameworks

eugenesiow/super-image

Image super resolution models for PyTorch.

62

NatLabRockies/sup3r

The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial...

60

HasnainRaz/Fast-SRGAN

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps

59

the-database/traiNNer-redux

Deep learning training framework for image super resolution and restoration.

57

EscVM/RAMS

Official TensorFlow code for paper "Multi-Image Super Resolution of Remotely Sensed Images Using...

54

Explore ML Frameworks

All categories Trending ML Framework directory Insights