Metadata-Version: 2.1
Name: flaxsr
Version: 0.0.2
Summary: Super Resolution models with Jax/Flax
Home-page: https://github.com/dslisleedh/FlaxSR
Author: dslisleedh
Author-email: dslisleedh@gmail.com
Project-URL: Bug Tracker, https://github.com/dslisleedh/FlaxSR/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# FlaxSR

Super Resolution models with Jax/Flax

## HOW TO USE

### Install
```shell
pip install flaxsr
```

### Usage
```python
from FlaxSR.models import VDSR
import jax
import jax.numpy as jnp

inputs = jnp.ones((16, 256, 256, 3))
key = jax.random.PRNGKey(42)
model = VDSR(n_filters=64, n_blocks=20, scale=4)
params = model.init(key, inputs)
outputs = model.apply(params, inputs)
print(outputs.shape)
```

## Models implemented
 - SRCNN
 - FSRCNN
 - ESPCN
 - VDSR
 - EDSR, MDSR,
 - NCNet
 - SRResNet(SRGAN will be implemented in future)
 - NAFSSR

## Feats will be added in future

 - More models
 - Pre-trained parameters
 - Training states(includes Generative-sr models)
