sieci neuronowe - litery

This commit is contained in:
AgataWojciech 2021-06-21 01:43:32 +02:00
parent aa3e0b59c1
commit 5930cb6d3c
6 changed files with 102 additions and 46 deletions

BIN
src/litery/1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 383 B

BIN
src/litery/2.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 402 B

BIN
src/litery/3.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 403 B

BIN
src/litery/4.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 454 B

BIN
src/litery/5.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 376 B

View File

@ -1,91 +1,78 @@
from emnist import list_datasets
from emnist import extract_test_samples from emnist import extract_test_samples
from emnist import extract_training_samples from emnist import extract_training_samples
import numpy as np import numpy as np
import torch
from torch import nn
from torch import optim
import scipy.special import scipy.special
from matplotlib.pyplot import imshow
import glob import glob
import imageio import imageio
""" pobranie obrazów cyfr i liter z biblioteki """
dig_train_images, dig_train_labels = extract_training_samples('digits') dig_train_images, dig_train_labels = extract_training_samples('digits')
dig_test_images, dig_test_labels = extract_test_samples('digits') dig_test_images, dig_test_labels = extract_test_samples('digits')
let_train_images, let_train_labels = extract_training_samples('letters') let_train_images, let_train_labels = extract_training_samples('letters')
let_test_images, let_test_labels = extract_test_samples('letters') let_test_images, let_test_labels = extract_test_samples('letters')
""" przekształcenie tablic """
#print(dig_train_images[0])
dig_train_images = dig_train_images.reshape(len(dig_train_images),28*28) dig_train_images = dig_train_images.reshape(len(dig_train_images),28*28)
dig_test_images = dig_test_images.reshape(len(dig_test_images),28*28) dig_test_images = dig_test_images.reshape(len(dig_test_images),28*28)
#print(d_test.shape) let_train_images = let_train_images.reshape(len(let_train_images),28*28)
print(d_labelstest) let_test_images = let_test_images.reshape(len(let_test_images),28*28)
#print(dig_train_images[0])
#print(dig_train_images.shape)
class NeuralNetwork: class NeuralNetwork:
""" inicjalizacja sieci neuronowej """
def __init__(self, inputNodes, hiddenNodes, outputNodes, learningGrade, fileWeight, fileHidden): def __init__(self, inputNodes, hiddenNodes, outputNodes, learningGrade, fileWeight, fileHidden):
self.inodes = inputNodes self.inodes = inputNodes
self.hnodes = hiddenNodes self.hnodes = hiddenNodes
self.onodes = outputNodes self.onodes = outputNodes
"""te pierwsze dwa użyj przy nauce, potem zostaw cały czas te 2""" """ używane przy uczeniu sieci """
#self.weights = (np.random.rand(self.hnodes, self.inodes) - 0.5) self.weights = (np.random.rand(self.hnodes, self.inodes) - 0.5)
#self.hidden = (np.random.rand(self.onodes, self.hnodes) - 0.5) self.hidden = (np.random.rand(self.onodes, self.hnodes) - 0.5)
self.weights = np.load(fileWeight) """ używane przy pobieraniu danych o nauczonej sieci, z pliku """
self.hidden = np.load(fileHidden) # self.weights = np.load(fileWeight)
# self.hidden = np.load(fileHidden)
#print( 'Matrix1 \n', self.weights)
#print( 'Matrix2 \n', self.hidden)
self.lr = learningGrade self.lr = learningGrade
""" funkcja aktywacji """
self.activationFunction = lambda x: scipy.special.expit(x) self.activationFunction = lambda x: scipy.special.expit(x)
pass pass
"""trening sieci neuronowej"""
def train(self, inputsList, targetsList): def train(self, inputsList, targetsList):
""" konwersja list na tablice 2d """
inputs = np.array(inputsList,ndmin=2).T inputs = np.array(inputsList,ndmin=2).T
targets = np.array(targetsList,ndmin=2).T targets = np.array(targetsList,ndmin=2).T
#forward pass """ forward pass """
hiddenInputs = np.dot(self.weights, inputs) hiddenInputs = np.dot(self.weights, inputs) # input -> hidden layer
hiddenOutputs = self.activationFunction(hiddenInputs) hiddenOutputs = self.activationFunction(hiddenInputs)
finalInputs = np.dot(self.hidden, hiddenOutputs) finalInputs = np.dot(self.hidden, hiddenOutputs)
finalOutputs = self.activationFunction(finalInputs) finalOutputs = self.activationFunction(finalInputs)
""" backward pass """
outputErrors = targets - finalOutputs outputErrors = targets - finalOutputs
#print(outputErrors.shape)
x =self.weights.T x =self.weights.T
#print(x.shape)
hiddenErrors = np.dot(self.hidden.T, outputErrors) hiddenErrors = np.dot(self.hidden.T, outputErrors)
#print('OutputErrors', outputErrors.shape)
#print('finalOutputs',finalOutputs.shape)
#print(x.shape)
self.hidden += self.lr * np.dot((outputErrors * finalOutputs * (1.0 - finalOutputs)) , np.transpose(hiddenOutputs)) self.hidden += self.lr * np.dot((outputErrors * finalOutputs * (1.0 - finalOutputs)) , np.transpose(hiddenOutputs))
self.weights += self.lr * np.dot((hiddenErrors * hiddenOutputs * (1.0 - hiddenOutputs)) , np.transpose(inputs)) self.weights += self.lr * np.dot((hiddenErrors * hiddenOutputs * (1.0 - hiddenOutputs)) , np.transpose(inputs))
pass pass
""" zapisywanie wytrenowanej sieci do pliku """
def saveTraining(self, fileWeight, fileHidden): def saveTraining(self, fileWeight, fileHidden):
np.save(fileWeight, self.weights) np.save(fileWeight, self.weights)
np.save(fileHidden, self.hidden) np.save(fileHidden, self.hidden)
""" wykorzystanie sieci """
def query(self, inputsList): def query(self, inputsList):
""" konwersja listy na tablicę 2d """
inputs = np.array(inputsList, ndmin=2).T inputs = np.array(inputsList, ndmin=2).T
hiddenInputs = np.dot(self.weights, inputs) hiddenInputs = np.dot(self.weights, inputs)
hiddenOutputs = self.activationFunction(hiddenInputs) hiddenOutputs = self.activationFunction(hiddenInputs)
@ -95,25 +82,26 @@ class NeuralNetwork:
return finalOutputs return finalOutputs
""" tablice sieci neuronowych """
""" dodaj tablicę literek"""
#n = NeuralNetwork(inputNodes=3, hiddenNodes=5, outputNodes=2, learningGrade=0.2)
digitNetwork = NeuralNetwork(inputNodes=784, hiddenNodes=200, outputNodes=10, learningGrade=0.1, fileWeight="Dweights.npy", fileHidden="Dhidden.npy") digitNetwork = NeuralNetwork(inputNodes=784, hiddenNodes=200, outputNodes=10, learningGrade=0.1, fileWeight="Dweights.npy", fileHidden="Dhidden.npy")
letterNetwork = NeuralNetwork(inputNodes=784, hiddenNodes=200, outputNodes=27, learningGrade=0.1, fileWeight="Lweights.npy", fileHidden="Lhidden.npy")
# trainNetwork(digitNetwork, "Dweights_test.npy", "Dhidden_test.npy", let_train_images, let_train_labels)
def trainNetwork(n, fWeight, fHidden, trainingSamples, trainingLabels): def trainNetwork(n, fWeight, fHidden, trainingSamples, trainingLabels):
epochs = 10 epochs = 10
outputNodes = 10 outputNodes = 27
for e in range(epochs): for e in range(epochs):
m=0 m=0
print('Epoch', e+1) print('Epoch', e+1)
for record in trainingSamples: for record in trainingSamples:
""" zmiana wartości przedziału z [0,255] na [0,1] """
inputs = (np.asfarray(record[0:])/255 * 0.99) + 0.01 inputs = (np.asfarray(record[0:])/255 * 0.99) + 0.01
#print(inputs.shape)
targets = np.zeros(outputNodes) + 0.01 targets = np.zeros(outputNodes) + 0.01
targets[trainingLabels[m]] = 0.99 targets[trainingLabels[m]] = 0.99
#print(targets)
n.train(inputs,targets) n.train(inputs,targets)
m+=1 m+=1
@ -122,14 +110,82 @@ def trainNetwork(n, fWeight, fHidden, trainingSamples, trainingLabels):
n.saveTraining(fileWeight=fWeight, fileHidden=fHidden) n.saveTraining(fileWeight=fWeight, fileHidden=fHidden)
def testing(n, testingSamples, testingLabels):
scorecard = []
k = 0
for record in testingSamples:
inputs = (np.asfarray(record[0:])/255 * 0.99) + 0.01
correctLabels = testingLabels[k]
##################################### ODPALANIE TRAINING outputs = n.query(inputs)
#trainNetwork(digitNetwork, "Dweights.npy", "Dhidden.npy", dig_train_images, dig_train_labels) label = np.argmax(outputs)
#record = d_test[0] if(label == correctLabels):
#print('Label', d_labelstest[0]) scorecard.append(1)
#inputs = np.asfarray(record[0:])/ 255 * 0.99 + 0.01 else:
#print(n.query(inputs)) scorecard.append(0)
k+=1
scorecardArray = np.asfarray(scorecard)
print('Performance', scorecardArray.sum() / scorecardArray.size)
testing(digitNetwork,dig_test_images,dig_test_labels)
#testing
li = []
ourOwnDataset = []
record_cache = None
for imageFileName in glob.glob('litery/?.png'):
label = int(imageFileName[-5:-4])
print('loading...', imageFileName)
imgArray = imageio.imread(imageFileName, as_gray=True)
#print(' imgArray: ', imgArray)
imgData = 255 - imgArray.reshape(784)
#print('imgData1: ',imgData)
imgData = (imgData/255 * 0.99) + 0.01
#print('imgData2: ',imgData)
#print(np.min(imgData))
#print(np.max(imgData))
record = np.append(label,imgData)
#print('Record: ',record)
ourOwnDataset.append(record)
if record_cache is None:
record_cache = record
#print(ood[0])
li.append(label)
pass
assert record_cache.shape == ourOwnDataset[0].shape
labelInput = np.asfarray(li)
#print(labelInput)
word = ""
for item in range(0,5):
correctLabels = labelInput[item]
outputs = letterNetwork.query(ourOwnDataset[item][1:])
print(outputs)
label = np.argmax(outputs)
print('label: ',label)
#print('Network says: ', label)
#labelString = np.array_str(label)
letters=['','a','b','c']
word = word + str(label)
print('slowo: ', word)
print('yep')
##################################### URUCHOMIENIE TRENINGU
trainNetwork(letterNetwork, "Lweights_test.npy", "Lhidden_test.npy", let_train_images, let_train_labels)
# trainNetwork(digitNetwork, "Dweights_test.npy", "Dhidden_test.npy", let_train_images, let_train_labels)