A high-level deep learning library build on top of PyTorch.
TensorNet is a high-level deep learning library built on top of PyTorch.
NOTE: This documentation applies to the MASTER version of TensorNet only.
You can use pip to install tensornet
pip install torch-tensornet
If you want to get the latest version of the code before it is released on PyPI you can install the library from GitHub
pip install git+https://github.com/shan18/TensorNet.git#egg=torch-tensornet
TensorNet currently supports the following features
- Model architectures
- A custom model called BasicNet
- Model utilities
- Loss functions
- Cross Entropy Loss
- Stochastic Gradient Descent
- L1 regularization
- L2 regularization
- Step LR
- Reduce LR on Plateau
- LR Finder
- Loss functions
- Model training and validation
- Datasets (data is is returned via data loaders)
- Data Augmentation
- Horizontal Flip
- Vertical Flip
- Gaussian Blur
- Random Rotation
- GradCAM and GradCAM++ (Gradient-weighted Class Activation Map)
- Result Analysis Tools
- Plotting changes in validation accuracy and loss during model training
- Displaying correct and incorrect predictions of a trained model
How to Use
For examples on how to use TensorNet, refer to the examples directory.
TensorNet has the following third-party dependencies
Documentation making for the library is currently in progress. So until a documentation is available please refer to the following table for various functionalities and their corresponding module names.
|Dataset downloading and preprocessing||data|
|GradCAM and GradCAM++||gradcam|
|Models, loss, optimizers, regularizers and callbacks||model|
|CUDA, random seed and result analysis||utils|
For a demo on how to use these modules, refer to the notebooks present in the examples directory.
If you need any help or want to report a bug, raise an issue in the repo.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size torch-tensornet-0.0.9.tar.gz (20.2 kB)||File type Source||Python version None||Upload date||Hashes View|