Deep Neural Network for object segmentation.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
HelperScripts script for reading random test and train data Apr 24, 2016
Trials file order Apr 22, 2016
CocoUtils.py File for project constants, Apr 19, 2016
Constants.py fixed max threshold, Apr 23, 2016
EndToEnd.py minor leftovers May 1, 2016
ExamplesGenerator.py Caching train & test datasets Apr 24, 2016
FullNetGenerator.py file order Apr 22, 2016
ImageUtils.py no img resizing by default Apr 23, 2016
Losses.py File for project constants, Apr 19, 2016
README.md Update README.md Nov 16, 2016
VggDNetGraphProvider.py

README.md

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).

General instructions

  1. Install all requirements, as listed below
  2. Download mscoco annotations (see below)
  3. Download and convert graph weights with HeplerScripts/CreateVggGraphWeights.py (see below)
  4. Create the learning dataset using ExamplesGenerator.py
  5. Create a train and test directories with examples to train and test on. Default locations are 'Predictions/train' and same for test (can be configured in EndToEnd.py)
  6. Run EndToEnd.py

Required installations

This was run on Windows 8.1 (64 bit) on a CPU with 8GB RAM. In brackets are the versions I used.

Required downloads