Dev Log (D-01 to D-04). Implementing neural networks from scratch.

Disclaimer:-I am a noob.(So don't use this if you are learning something).

Getting MNIST data (found this code in https://github.com/tinygrad/tinygrad).

import numpy as np
import gzip
import requests

def fetch(url):
    response = requests.get(url)
    return response.content

def parse(file):
    return np.frombuffer(gzip.decompress(file), dtype=np.uint8).copy()
# Thank to https://github.com/tinygrad/tinygrad mnist example
BASE_URL = "https://storage.googleapis.com/cvdf-datasets/mnist/"
X_train = parse(fetch(f"{BASE_URL}train-images-idx3-ubyte.gz"))[0x10:].reshape((-1, 28*28)).astype(np.float64)
Y_train = parse(fetch(f"{BASE_URL}train-labels-idx1-ubyte.gz"))[8:].astype(np.int8)
X_test = parse(fetch(f"{BASE_URL}t10k-images-idx3-ubyte.gz"))[0x10:].reshape((-1, 28*28)).astype(np.float64)
Y_test = parse(fetch(f"{BASE_URL}t10k-labels-idx1-ubyte.gz"))[8:].astype(np.int8)

# Print the shapes of the loaded data
print("Shape of X_train:", X_train.shape)
print("Shape of Y_train:", Y_train.shape)
print("Shape of X_test:", X_test.shape)
print("Shape of Y_test:", Y_test.shape)

Implementing NN. getting help from help from https://developer.ibm.com/articles/l-neural/

class Neuron:
    def __init__(self):
        # Weight is an vector.
        self.W =  np.random.uniform(-1.,1.,size=(784,)).astype(np.float64)
    def forward(self,X):
        self.wX = X.dot(self.W)
        return self.wX

    def sigmoid(self):
        if self.wX > 0:   
            z = np.exp(-self.wX)
            return 1/(1+z)
        else:
            z = np.exp(self.wX)
            return z/(1+z)
    def sigmoid2(self):
        return np.exp(self.wX) / (1 +  np.exp(self.wX))

    def tanH(self):
        z = np.exp(2*self.wX)
        return (z-1)/(z+1)

# neuron = Neuron()
# print(neuron.forward(train_data[4]))
# print(neuron.sigmoid())

I am stuck at my activation function bcz dot product of Input and weights is to large.

class NLayer:
    neurons = []
    def __init__(self,number_of_neurons):
        for n in range(0,number_of_neurons):
            self.neurons.append(Neuron())

    def forward(self,X):
        for n in self.neurons:
            n.forward(X)
            print(n.tanH())

layer_1 = NLayer(784)
layer_1.forward(train_data[0])

class NNetwork:
    neuronsLayers = []
    def __init__(self):
        pass
    def train(self):
        # Train and update weights. 
        pass
    def test(self):
        # Don't update weights. check weights.
        pass
    def predict(self):
        # Run Model. 
        pass

I am still stuck at the error when executing the activation function code. OverFollow due to number being too large.