Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/abhishtagatya/veingan
🩻 Generating Syntethic Vein Images using GAN
https://github.com/abhishtagatya/veingan
Last synced: about 11 hours ago
JSON representation
🩻 Generating Syntethic Vein Images using GAN
- Host: GitHub
- URL: https://github.com/abhishtagatya/veingan
- Owner: abhishtagatya
- Created: 2023-10-06T21:59:52.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2023-11-18T14:29:59.000Z (almost 1 year ago)
- Last Synced: 2024-07-23T15:21:00.958Z (4 months ago)
- Language: Jupyter Notebook
- Size: 6.05 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# VeinGAN
> Synthetic Image Generation of Veins using Generative Models
[](https://colab.research.google.com/drive/1-GCMNedTP3j0v8AhIl7Rg3qGMDB-9lj7?usp=sharing)
### Usage
#### Requirements
Use this script to install the requirements for this implementation.
```python
pip install -r requirements.txt
```
#### Download Dataset
To download the dataset locally, use this script as follows.
```python
python -m scripts.download --dataset= --target=
```
Parameter
- `dataset`: A Kaggle Dataset Name or Key
- `kaggle-fv`: Kaggle Finger Vein Dataset (Default)
- `target`: Target Directory for Dataset (Default: ./veingan-tmp/dataset/)
#### Generate Images
To train the model and generate synthetic images, use the following command and adjust the given parameters.
```python
python -m scripts.generate --verbose --epoch= --configuration=
```
Parameter
- `model`: The GAN model to generate the image-
- `gan`: Deep Convolutional GAN
- `vae`: Variational Autoencoders
- `cyclegan`: CycleGAN
- `dataset`: The dataset to train on
- `target`: The target directory to save the images
- `verbose`: Argument to enable verbose output of model progress
- `epoch`: The amount of cycle to train on
- `configuration`: Configuration Specifc for Model
- `vae_128+cpu`: VAE CPU Mode (Default)
- `vae_128+gpu`: VAE GPU Mode
- `gan128_64+cpu`: GAN CPU Mode (Default)
- `gan128_64+gpu`: GAN GPU Mode
- `gan128_64+full`: GAN GPU Mode with (Full Train)
- `cyclegan128_1+cpu+train`: CycleGAN CPU Mode (Default)
- `cyclegan128_1+gpu+train`: CycleGAN GPU Mode
- `cyclegan128_1+full+train`: CycleGAN GPU Mode (Full Train)
- `cyclegan128_1+infer`: CycleGAN Inference Mode
#### Evaluate Result
Evaluate some sample of the dataset using various methods.
```python
python -m scripts.evaluate --configuration=
```
Parameter
- `method` Method of Evaluation
- `entropy`: Calculates Entropy of Sample Sets
- `laplace`: Calculates Laplace Gradient of Sample Sets
- `inception`: Calculates Inception Score of Sample Sets
- `snapshot`: Preview a snapshot of Sample Sets
- `target` : Target Directory and Label of Evaluation Sets (Example: "dir:label;dir:label")
- `configuration` : Specific Configuration for Evaluation Method
### Authors
- Abhishta Gatya Adyatma [Email](mailto:[email protected])
- Francisco Colino [Email](mailto:[email protected])