PyNeuralNet is a python library for prototyping and building neural networks. PyNeuralNet uses PyTorch as a computational backend for deep learning models.
Project description
PyNeuralNet
Welcome to the PyNeuralNet repository! PyNeuralNet is a python library for prototyping and building neural networks. PyNeuralNet uses PyTorch as a computational backend for deep learning models.
Installation
- First, make sure you have Python installed on your system.
- Use this pip command to install the latest version of package.
pip install pyneuralnet
Usage
from pyneuralnet import train
dataset_loader = 'local'
root_dir = 'path/to/root_diractory'
metadata_file = 'path/to/meta_info_file.txt'
network = 'usrcnn'
batchs = 4
train(datasetloader, metadata_file, root_dir, epochs=25, batch_size=batchs, network=network)
- Parameters
- dataset_loader: Type of dataset loader, there is two type of dataloaders (locally -
local
and from internet -internet
). In this example, it is set to 'local'. - metadata_file: Path to the metadata file. If you load your dataset from internet you should type an url like this.
- root_dir: Path to the root directory where the dataset is located. If you load your dataset from internet you should type an url like this, example image.
- network: Neural network architecture to be used (e.g., 'usrcnn'). There are 6 type of networks(for now) which are based on
Convolutional Neural Network
e.g.,usrcnn
,esrcnn
,bsrcnn
,isrcnn
,rsrcnn
andsrcnn
. - epochs: Number of training epochs.
- batch_size: Size of each training batch.
- dataset_loader: Type of dataset loader, there is two type of dataloaders (locally -
Contributing
Contributions are welcome! If you'd like to contribute to this project, follow these steps:
- Fork this repository.
- Create a new branch for your feature or bug fix.
- Make your changes and submit a pull request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contact
Feel free to reach out to me at loghot.gamerz.official@gmail.com if you have any questions or feedback! Or just open an issue on PyNeuralNet's github page.
Happy coding! 🚀
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for PyNeuralNet-1.1.15-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 00577ef58643d8f4e0f9efbac099baf64b6caff4baf3563e3691bdf9e33a2013 |
|
MD5 | a06258b1c9f9cab56c46b63e93cd0253 |
|
BLAKE2b-256 | 415e3b3db88362bd64309341909264d5016af6d3c1bf2680f3cb8a20be50c0a7 |