Keras-unet

Latest version: v0.1.2

Safety actively analyzes 613682 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

27.01.2020

- Modified `custom_unet` to not use a bias when using BatchNorm
- Added `SpatialDropout2D` to `custom_unet`. Regular Dropout does not perform as well as Spatial Dropout in CNNs. Compare [here](https://github.com/keras-team/keras/blob/master/keras/layers/core.pyL178).
- Added test coverage to the new code.
- Added a `__version__` to `__init__.py`

14.02.2020

- Bumped version to 0.0.8
- Added support for TF >= 2.0 and solved issue 14
- From this point forward `keras-unet` will import `tf.keras` instead of regular `Keras` when TF >= 2.0 is present.
- Added `color` param to `keras_unet.utils.plot_imgs` function allowing to change the mask color when plotting on top of orginal image. Thanks muminoff picking that up
- Added some docs scafoldings for `keras_unet.utils`

08.05.2020

- Bumped version to 0.1.0 and released to PyPI
- Approved PR13 from moritzknolle with `custom_vnet` (a Conv3D U-Net) implementation
- Approved PR13 from moritzknolle with attention layers for `custom_unet` and `custom_vnet`
- Removed `keras` from requirements in `setup.py`
- Removed `keras` and `tenserflow` from `requirements.txt`
- Fixed image links in `README.md` to make them work on PyPI website

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.