Leo02016 / ANTS

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ANTS

Code for paper "Deep Co-Attention Network for Multi-View Subspace Learning"

Environment

  • Python 3.7
  • Pytorch
  • Tensorflow (For downloading mnist dataset)

Demo

  1. Download dataset from http://www.vision.caltech.edu/visipedia/CUB-200.html
  2. Download the mask-rcnn from https://github.com/matterport/Mask_RCNN, and install the required package.
  3. Run the following command to generate two views as well as the image segments:
python mask_rcnn.py
  1. Run the following command to get the hidden representation for the final training:
python pre-train_vgg.py 
  1. Run the following command to train the model:
python main.py -g 0 -e 150 -hid 300 -d birds

About


Languages

Language:Python 100.0%