LibreSwinIRm-restore

SwinIR-M x4 real-world super-resolution (BSRGAN-degradation GAN generator), repackaged for LibreYOLO.

Source

Weights derived from JingyunLiang/SwinIR release 003_realSR_BSRGAN_DFO_s64w8_SwinIR-M_x4_GAN.pth (SHA-256 b9afb61e65e04eb7f8aba5095d070bbe9af28df76acd0c9405aeb33b814bcfc6). Copyright (c) 2021 Jingyun Liang. Licensed under the Apache License, Version 2.0. Architecture reference commit: 6545850fbf8df298df73d81f3e8cba638787c8bd.

Modifications

State-dict metadata-wrap only: keys and learned parameters are unchanged; the checkpoint is wrapped in the LibreYOLO v1.0 schema (task=restore, scale=4). Tensor-level parity vs the official model is exact (max_abs_diff == 0, fp32). Converted with weights/convert_swinir_weights.py from the LibreYOLO source repository (converted-file SHA-256 bc86620d0ff09b259e414473b65825858a97418e57f1f8065c57696e41f5ece1).

Usage

from libreyolo import LibreYOLO

model = LibreYOLO("LibreSwinIRm-restore.pt")
res = model.predict("small.jpg")     # res.restored is 4x the input
res.save("upscaled.png")
# large images: model.predict("big.jpg", tile=256)   # halo-padded tiling

License

Apache-2.0 (code and weights). See the LICENSE and NOTICE files in this repository.

Downloads last month: -; Downloads are not tracked for this model. How to track