meisamrf / racnn

radius adaptive convolutional neural net
GNU General Public License v3.0
7 stars 1 forks source link

RACNN

Radius Adaptive Convolutional Neural Net

This is an implementation of RACNN on Python, Keras, and TensorFlow. Radius adaptive CNN is a method that adopts different kernel sizes (or radii) based on the input content. α defines how much of the neighboring pixels are taken into account. α=0 and α=1 are equivalent to 1x1 and 3x3 convolutions.

RACNN

The repository includes:

Getting Started with Python

Installation (Python)

  1. Install dependencies

    pip3 install package [numpy, keras, opencv-python ...]

  2. Clone this repository

  3. Run setup from the racnn/libs directory

    • for CPU python3 setup.py install

    • for GPU python3 setup_gpu.py install

    or:

    python3 setup.py build and copy the compiled modules (.pyd for windows and .so for linux to your working directory)

Results

Results will be updated here

Weights and test data

weights and test data can be downloaded from racnn1.0