cbaziotis

#!/bin/bash
#-----------------------------------------------------------------------------------------------------------------------
# This script contains the preprocessing pipeline for some predefined datasets.
# 1. It learns a joint sentencepiece model on a sub-set of the data (training-side)
# 2. It tokenizes with the sentencepice model all the data
# 3. It binarizes them for training with faireq
#-----------------------------------------------------------------------------------------------------------------------

DATASET=$1
#DATASET=flores_neen

cbaziotis

import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import torch.nn.functional as F

import matplotlib.pyplot as plt

import numpy as np

cbaziotis

class SelfAttention(nn.Module):
    def __init__(self, attention_size, batch_first=False, non_linearity="tanh"):
        super(SelfAttention, self).__init__()

        self.batch_first = batch_first
        self.attention_weights = Parameter(torch.FloatTensor(attention_size))
        self.softmax = nn.Softmax(dim=-1)

        if non_linearity == "relu":
            self.non_linearity = nn.ReLU()

cbaziotis

# This is shorthened version of blog post 
#  http://ksopyla.com/2017/02/tensorflow-gpu-virtualenv-python3/

# update packages
sudo apt-get update
sudo apt-get upgrade

#Add the ppa repo for NVIDIA graphics driver
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt-get update

cbaziotis

# This is inspired by the fantastic guide https://github.com/saiprashanths/dl-setup
# I have just updated the python-related commands so that everything works in Python 3.
# Tested on Xubuntu 16.04.

# First of all let's update the repos:
sudo apt-get update 

# Only if you have a CUDA-compatible Nvidia card, install CUDA.
# Check on the Nvidia website what is the latest driver version which supports your card. 
# At the time of this writing it was 367.

cbaziotis

def get_class_weights(y, smooth_factor=0):
    """
    Returns the weights for each class based on the frequencies of the samples
    :param smooth_factor: factor that smooths extremely uneven weights
    :param y: list of true labels (the labels must be hashable)
    :return: dictionary with the weight for each class
    """
    counter = Counter(y)

    if smooth_factor > 0:

cbaziotis

def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:
        x (): input
        kernel (): weights
    Returns:
    """
    if K.backend() == 'tensorflow':

cbaziotis

from keras import backend as K, initializers, regularizers, constraints
from keras.engine.topology import Layer


def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args: