Downloads · 30 days
0
denoise-sr-baseline
Pranshu554/denoise-sr-baseline
denoise-sr-baseline is a machine learning model from Pranshu554. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Compact residual CNN (12 res-blocks, PixelShuffle 4x upsampling) trained to jointly denoise and 4x super-resolve low-light images.
Access
Public
Updated Sep 6, 2026
Repo size
4.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth4.9 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- f5653faf
Model card
From the Hugging Face model README
Denoise + 4x Super-Resolution Baseline
Compact residual CNN (12 res-blocks, PixelShuffle 4x upsampling) trained to jointly denoise and 4x super-resolve low-light images.
Training
- Loss: L1
- Optimizer: Adam, lr=2e-4, cosine annealing
- Epochs: 80
- Metric: PSNR (validation)
Usage
Load with the DenoiseSRNet architecture from the training notebook and
model.load_state_dict(torch.load("best_model.pth")).
- License
- mit
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026