vrjkmr

# imports
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

# set seed
seed = 1
np.random.seed(seed)

vrjkmr

def parse(expr):

    expr = expr.replace('(', ' ( ').replace(')', ' ) ')
    brac_just_opened = False

    def _listify(iter):
        nonlocal brac_just_opened
        items = []
        for item in iter:
            if item == '(':

vrjkmr

# -*- coding: utf-8 -*-

# imports
import re
from nltk.corpus import stopwords as sw

# stopwords : a list/set of strings
stopwords = set(sw.words('english'))

# TextCleaner : cleans text

vrjkmr

# Running our model
train = fashion_mnist.train
test = fashion_mnist.test

parameters = model(train, test, learning_rate=0.0005)

'''
Output:
Cost after epoch 0: 0.5206283370382022
Cost after epoch 1: 0.3820550605650376

vrjkmr

def model(train, test, learning_rate=0.0001, num_epochs=16, minibatch_size=32, print_cost=True, graph_filename='costs'):
    '''
    Implements a three-layer tensorflow neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SOFTMAX.
    
    Arguments:
    train -- training set
    test -- test set
    learning_rate -- learning rate of the optimization
    num_epochs -- number of epochs of the optimization loop
    minibatch_size -- size of a minibatch

vrjkmr

def compute_cost(Z3, Y):
    '''
    Computes the cost
    
    Arguments:
    Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (10, number_of_examples)
    Y -- "true" labels vector placeholder, same shape as Z3
    
    Returns:
    cost - Tensor of the cost function

vrjkmr

def forward_propagation(X, parameters):
    '''
    Implements the forward propagation for the model: 
    LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX
    
    Arguments:
    X -- input dataset placeholder, of shape (input size, number of examples)
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"
                  the shapes are given in initialize_parameters
    Returns:

vrjkmr

def initialize_parameters():
    '''
    Initializes parameters to build a neural network with tensorflow. The shapes are:
                        W1 : [n_hidden_1, n_input]
                        b1 : [n_hidden_1, 1]
                        W2 : [n_hidden_2, n_hidden_1]
                        b2 : [n_hidden_2, 1]
                        W3 : [n_classes, n_hidden_2]
                        b3 : [n_classes, 1]
    

vrjkmr

# Create placeholders
def create_placeholders(n_x, n_y):
 '''
 Creates the placeholders for the tensorflow session.
 
 Arguments:
 n_x -- scalar, size of an image vector (28*28 = 784)
 n_y -- scalar, number of classes (10)
 
 Returns:

vrjkmr

# Network parameters
n_hidden_1 = 128 # Units in first hidden layer
n_hidden_2 = 128 # Units in second hidden layer
n_input = 784 # Fashion MNIST data input (img shape: 28*28)
n_classes = 10 # Fashion MNIST total classes (0–9 digits)
n_samples = fashion_mnist.train.num_examples # Number of examples in training set