For this experiment, I am going to use the Fashion MNIST dataset that consists of Zalando’s article images which is a set of 28x28 greyscale images of clothes, a drop-in replacement for the MNIST dataset. This is how the dataset looks like:

These instructions will get you a copy of the project up and running on your local machine .

• python3.6 installed (app tested on3.6 only)
• Have virtualenv installed on your machine
• create virtual environment conda create --name adver or virtualenv adver --python python3
• activate virtual env conda activate adver or source path_to_virtualenv/adver/bin/activate

There is 2 releases that one can install

• First relase use crossEntropyLoss + Hyperparameter tuning
  git clone -b v1.0 https://github.com/EmnamoR/AdverFashionMnist.git
  
• Second release uses Triplet Loss/ CrossEntropyLoss + Hyperparameter tuning
  git clone -b v1.2 https://github.com/EmnamoR/AdverFashionMnist.git
  

pip install -r requirements.txt

To run this app

pythton train.py

please find the full documentation of v1.1 release: here
please find the full documentation of v1.3 release(triplet loss release): here