Changes:

• Downgrade the dependencies to tensorflow 1.10.1 and numpy 1.14.5 as some users reported long initialization times. (Thanks to Shaun Rawson)
• The initialization weights are not longer shipped with the package and downloaded on-the-fly (because they are big and pypi does not allow such big packages)
• crYOLO is installed through pypi
• crYOLO box manager is installed through pypi and automatically shipped with the crYOLO package
• Fix fine-tune mode (Thanks to Antoine Koehl)
• Fixed normalization function for YOLO backend (Thanks to Wolfgang Lugmayr)

As the dependencies changed again, I recommend to use a fresh environmen:

conda env remove --name cryolo

After that, create a new virtual environment:

conda create -n cryolo -c anaconda python=3.6 pyqt=5 cudnn=7.1.2 cython

Activate the environment:

source activate cryolo

Install fast numpy from conda:

conda install numpy==1.14.5

In case you run crYOLO on a GPU run:

pip install 'cryolo[gpu]==1.4.1rc3' 

But if you want to run crYOLO on a CPU run:

pip install 'cryolo[cpu]==1.4.1rc3' 

Thats it