Menu

Tree [4e8ddc] master /
 History

HTTPS access


File Date Author Commit
 docs 2019-01-02 Nesac128 Nesac128 [4e8ddc] Converted MD file to RST
 tensorimage 2018-12-30 Nesac128 Nesac128 [c79146] Fixed error and added INFO logs
 .gitignore 2018-12-23 Nesac128 Nesac128 [fac8a3] - moved sources into tensorimage package
 LICENSE.md 2018-12-12 Nesac128 Nesac128 [6eb7a1] Change license to MIT
 MANIFEST.in 2018-12-23 Nesac128 Nesac128 [fac8a3] - moved sources into tensorimage package
 README.md 2018-12-26 Nesac128 Nesac128 [ff8a6e] Update README.md
 requirements.txt 2018-12-08 Nesac128 Nesac128 [7ee133] Added scipy
 setup.py 2018-12-30 Nesac128 Nesac128 [2a4eef] Update description

Read Me

License: MIT
Generic badge
GitHub release
Github all releases

TensorImage

Example

TensorImage is and open source image classification library designed to easily train and deploy models.

The main features are:
- Image classification model training. A wide range of data augmentation operations to boost testing accuracy and prevent overfitting are available

  • Training clusters -- makes hyperparameter tuning easier and faster by automatically comparing performance of different models

  • Organization -- all files, data and trained models are automatically stored and ordered inside your workspace directory which can be accessed at any time

  • Large-scale deployment of trained image classification models -- generating more training data for further improved classification

Installation

From the terminal:

$ pip3 install tensorimage

Documentation

You can view TensorImage's documentation here.

Support

If you are experiencing any errors or bugs, please report them in the issues section or contact us at tensor.image2@gmail.com

Contributing

If you have any ideas for features that should be added to TensorImage, please feel free to fork TensorImage and open a pull request.

License

MIT

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.