latest

'''
This neural network framework nudges both weights and biases in all layers when it performs backpropagation. It can handle multiple outputs and inputs. Working on implementing the relu activation function in backpropagation (try it out it should work)
'''

import numpy as np
import random

class Layer:
    def __init__(self, inputNodes, outputNodes):
        self.weights = 0.1 * np.random.randn(inputNodes, outputNodes)
        self.biases = 1 + np.zeros((1, outputNodes))
        #self.biases = 0.1 * np.random.randn(1, outputNodes)

    def forward(self, inputs):
        self.output = np.dot(inputs, self.weights) + self.biases
class Activation_ReLU:
    def forward(self, inputs):
        self.output = np.maximum(0, inputs)

def trainNetwork(batches, batchSize, epochs):
    elementIterator = 0
    #inputData = np.random.randint(1, 1000, batches*batchSize)
    inputData = np.arange(0, batches*batchSize)
    desired = np.copy(inputData) * 2

    for epochIterator in range(epochs):
        elementIterator = 0
        for batchesIterator in range(batches):
            sum_of_errors_averaged = 0
            for batchSizeIterator in range(batchSize):
                layer1.forward(inputData[elementIterator])
                layer2.forward(layer1.output)

                sum_of_errors_averaged += (layer2.output - desired[elementIterator])
                elementIterator += 1

            sum_of_errors_averaged /= batchSize
            backwards([layer1, layer2], sum_of_errors_averaged)

learningRate = 0.000000001
def backwards(network, error):
    currentLayer = len(network) - 1

    #dError = 2*(network[currentLayer].output[0] - desired)
    dError = error

    gradients = np.zeros((len(network), 10)) #The digit here represent maximum number of neurons per layer

    #This presumes the last layer is a normal one and not an activation
    for neuronsPerLastLayer in range(len(network[currentLayer].output[0])):
        gradients[currentLayer][neuronsPerLastLayer] = dError[neuronsPerLastLayer]

    # Start backpropagation for the rest of the layer
    while currentLayer > 0: # Per layer except last one that's connected to the network input
        if currentLayer == 0:
            '''
            # Nudge the weights and biases in the first layer
            for neuronCurrentLayer in range(len(network[currentLayer].output[0])): # Per neuron in current layer
                network[currentLayer].biases[0][neuronCurrentLayer] -= 1 * gradients[currentLayer][neuronCurrentLayer] * learningRate
                for neuronPreviousLayer in range(len(input_)): # Per neuron in previous layer
                    network[currentLayer].weights[neuronPreviousLayer][neuronCurrentLayer] -= input_[neuronPreviousLayer] * gradients[currentLayer][neuronCurrentLayer] * learningRate

            currentLayer -= 1
            '''
            pass
        else:
            #Nudge the weights and biases
            for neuronCurrentLayer in range(len(network[currentLayer].output[0])): # Per neuron in current layer
                network[currentLayer].biases[0][neuronCurrentLayer] -= 1 * gradients[currentLayer][neuronCurrentLayer] * learningRate
                for neuronPreviousLayer in range(len(network[currentLayer - 1].output[0])): # Per neuron in previous layer/per weight per neuron in current layer
                    network[currentLayer].weights[neuronPreviousLayer][neuronCurrentLayer] -= network[currentLayer - 1].output[0][neuronPreviousLayer] * gradients[currentLayer][neuronCurrentLayer] * learningRate

            # Calculate gradients for every neuron in the next layer you're going to adjust
            if type(network[currentLayer - 1]) == Activation_ReLU:
                for neuronCurrentLayer in range(len(network[currentLayer].output[0])): # Per neuron in current layer
                    for neuronPreviousLayer in range(len(network[currentLayer - 2].output[0])): # Per neuron in previous normal layer (skips activation layer)
                        if(network[currentLayer - 2].output[0][neuronPreviousLayer] > 0):
                            gradients[currentLayer - 2][neuronPreviousLayer] += network[currentLayer].weights[neuronPreviousLayer][neuronCurrentLayer] * gradients[currentLayer][neuronCurrentLayer]
                        else:
                            gradients[currentLayer - 2][neuronPreviousLayer] = 0

                currentLayer -= 2
            else:
                for neuronCurrentLayer in range(len(network[currentLayer].output[0])): # Per neuron in current layer
                    for neuronPreviousLayer in range(len(network[currentLayer - 1].output[0])): # Per neuron in previous layer
                        gradients[currentLayer - 1][neuronPreviousLayer] += network[currentLayer].weights[neuronPreviousLayer][neuronCurrentLayer] * gradients[currentLayer][neuronCurrentLayer]

                currentLayer -= 1

    #print("Error: ", (network[len(network) - 1].output[0] - desired))
    #error = network[len(network) - 1].output[0] - desired
    #print("Gradients total: \n", gradients)



#Create neural network
layer1 = Layer(1, 1)
layer1.biases = 1/layer1.biases
layer1.weights = 1/layer1.weights

layer2 = Layer(1, 1)
activation2 = Activation_ReLU()


#Train the network
trainNetwork(100, 32, 1)

testInput = 9817264
layer1.forward(testInput)
layer2.forward(layer1.output)
print("Guess: ", layer2.output)
print("Error", layer2.output - testInput*2)