util.py

import numpy as np
import pandas as pd
import matplotlib as mpl
mpl.use('TkAgg')
import matplotlib.pyplot as plt

def init_weight_and_bias(M1, M2):
    W = np.random.randn(M1, M2) / (np.sqrt(M1 + M2) * 2)
    b = np.zeros(M2)
    return W.astype(np.float32), b.astype(np.float32)

def init_filter(shape, poolsz):
    w = np.random.randn(*shape) /np.sqrt(np.prod(shape[:-1]) + shape[-1]*np.prod(shape[:-2] / np.prod(poolsz)))
    return w.astype(np.float32)

def error_rate(p, t):
    return np.mean(p != t)

def y2indicator(y):
    N = len(y)
    K = len(set(y))
    ind = np.zeros((N, K))
    for i in range(N):
        ind[i, int(y[i])] = 1
    return ind



def getData(balance_ones = True):
    #images are 48x48 = 2304 size vectors
    # N = 35887
    Y = []
    X = []
    first = True
    for line in open('fer2013/fer2013.csv'):
        if first:
            first = False
        else:
            row = line.split(',')
            Y.append(int(row[0]))
            X.append([int(p) for p in row[1].split()])

    X, Y = np.array(X) / 255.0, np.array(Y)

    if balance_ones:
        # repeat class 1 to balance classes
        X0, Y0 = X[Y!=1, :], Y[Y!= 1]
        X1 = X[Y==1, :]
        X1 = np.repeat(X1, 9, axis= 0)
        X = np.vstack([X0, X1])
        Y = np.concatenate((Y0, [1]*len(X1)))

    return X, Y

def getImageData():
    X, Y = getData()
    N, D = X.shape
    d = int(np.sqrt(D))
    X = X.reshape(N, d, d, 1)
    return X, Y