NNProject - DeepMask
This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks. The full article can be found here: Learning to Segment Object Candidates.
This was implemented as a final project for TAU Deep Learning course (2016).
Required installations
This was run on Windows 8.1.
- Python
- Theano
- conda install mingw libpython
- git clone https://github.com/Theano/Theano.git
- python setup.py install
- Keras
- conda install keras
- Open CV
- Download installation here
- Copy cv2.pyd to site-packages dir inside python's lib dir in anaconda
- Coco API
- git clone https://github.com/pdollar/coco
- python setup.py build_ext install
Required downloads
- VGG-D
- Net was taken from here. Weights should be downloaded locally.
- Full article: Very Deep Convolutional Networks for Large-Scale Image Recognition
- MSCOCO
- Download annotation files here