Metadata-Version: 2.1
Name: deepfake-gitract
Version: 1.0.1
Summary: Deepfake gastrointestinal tract image generator.
Home-page: https://github.com/vlbthambawita/deepfake-gitract
Author: Vajira Thambawita
Author-email: vlbthambawita@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: tqdm
Requires-Dist: torch
Requires-Dist: pandas
Requires-Dist: pathlib
Requires-Dist: stylegan2-pytorch

# deepfake-gitract
Generate deepfake-gitract images.  

## Installation

Use the package manager [pip](https://pypi.org) to install deepfake-gitract.



```bash
pip install deepfake-gitract
```

## Usage

### Run on CPU (default setting)

```python
TBA - You have to have a NVIDIA GPU to run this package. We are working on CPU version.
```

### Run on GPU - generation process

```python
import deepfake_gitract

deepfake_gitract.generate(name, result_dir, checkpoint_dir, num_img_per_tile, num_of_outputs, trunc_psi=0.75):
    """ Generate deepfake Gastrointestinal tract images.

    Keyword arguments:
    name -- Any name to keep trac of generations
    result_dir -- A directory to save output
    checkpoint_dir -- A directory to download pre-trained checkpoints
    num_img_per_tile -- Number of images per dimenstion of the grid
    num_of_outputs -- Number of outputs to generate
    trunc_psi -- value between 0.5 and 1.0 (default 0.75)
    """
```

### Run on GPU - to generate interpolations between random points

```python
deepfake_gitract. generate_interpolation(name, result_dir, checkpoint_dir, num_img_per_tile, num_of_outputs, num_of_steps_to_interpolate, save_frames, trunc_psi=0.75):
    """ Generate deepfake Gastrointestinal tract images.

    Keyword arguments:
    name -- Any name to keep trac of generations
    result_dir -- A directory to save output
    checkpoint_dir -- A directory to download pre-trained checkpoints
    num_img_per_tile -- Number of images per dimenstion of the grid
    num_of_outputs -- Number of outputs to generate
    num_of_steps_to_interpolate -- Number of step between two random points
    save_frames -- True if you want frame by frame, otherwise .gif will be generated
    trunc_psi -- value between 0.5 and 1.0 (default 0.75)
    """
```

## Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

## For more details: 
Please contact: vajira@simula.no, michael@simula.no

## License
[MIT](https://choosealicense.com/licenses/mit/)


