CODEWITHSUNDEEP
pythonarraysnumpyneural-network
Regin.hd
Regin.hd

Reputation: 21

Comparing floating point numbers in python

I've been trying to write a neural network in python and I've been stuck on this part for a while. I have this code:

import numpy as np

np.random.seed(0)

X = [[1.0, 2.0, 3.0, 2.5],
          [2.0, 5.0, -1.0, 2.0],
          [-1.5, 2.7, 3.3, -0.8]]

class Layer:
    def __init__ (self, inputCount, neronCount):
        self.weights = 0.10 * np.random.randn(inputCount, neronCount)
        self.biases = np.zeros((1, neronCount))
    def forward(self, inputs):
        self.output = np.dot(inputs, self.weights) + self.biases


layer1 = Layer(4, 5)
layer2 = Layer(5, 2)

layer1.forward(X)
layer2.forward(layer1.output)

print(layer2.output)

and this outputs:

[[ 0.148296   -0.08397602]
 [ 0.14100315 -0.01340469]
 [ 0.20124979 -0.07290616]]

so I made an array Y that I would use as an expected output so I could compare them. For testing proposes I set the expected output as the actual output so I would know that it works.

Y = np.array([[0.148296,   -0.08397602],
 [0.14100315, -0.01340469],
 [0.20124979, -0.07290616]])

I also wanted to compare each variable so I could know how much they got wrong but when I compare them

for i in range (0, 3):
    for j in range(0, 2):
        if np.asarray(layer2.output[i, j], dtype=np.float32) == Y[i, j]:
            print("TEST")

it outputs nothing, when it should output TEST 3 times. Any suggestions?

whole script:

import numpy as np

np.random.seed(0)

X = [[1.0, 2.0, 3.0, 2.5],
          [2.0, 5.0, -1.0, 2.0],
          [-1.5, 2.7, 3.3, -0.8]]

Y = np.array([[0.148296,   -0.08397602],
 [0.14100315, -0.01340469],
 [0.20124979, -0.07290616]])

class Layer:
    def __init__ (self, inputCount, neronCount):
        self.weights = 0.10 * np.random.randn(inputCount, neronCount)
        self.biases = np.zeros((1, neronCount))
    def forward(self, inputs):
        self.output = np.dot(inputs, self.weights) + self.biases


layer1 = Layer(4, 5)
layer2 = Layer(5, 2)

layer1.forward(X)
layer2.forward(layer1.output)

print(layer2.output)

for i in range (0, 3):
    for j in range(0, 2):
        if np.asarray(layer2.output[i, j], dtype=np.float32) == Y[i, j]:
            print("TEST")

Upvotes: 0

Views: 71

Answers (1)

Bemwa Malak
Bemwa Malak

Reputation: 1349

for i in range(0, 3):
    for j in range(0, 2):
        if layer2.output[i][j] - Y[i][j] <= 1e-13:
            print("TEST")

You should allow for a relative error value like 1e-13 because they are floating point numbers which can't be compared precisely by the == operator.

Upvotes: 1

Related Questions