Neural networks very bad accuracy when using more than one hidden layer

I have created the following neural network:

def init_weights(m, n=1):
    """
    initialize a matrix/vector of weights with xavier initialization
    :param m: out dim
    :param n: in dim
    :return: matrix/vector of random weights
    """
    limit = (6 / (n * m)) ** 0.5
    weights = np.random.uniform(-limit, limit, size=(m, n))
    if n == 1:
        weights = weights.reshape((-1,))
    return weights


def softmax(v):
    exp = np.exp(v)
    return exp / np.tile(exp.sum(1), (v.shape[1], 1)).T


def relu(x):
    return np.maximum(x, 0)


def sign(x):
    return (x > 0).astype(int)


class Model:
    """
    A class for neural network model
    """

    def __init__(self, sizes, lr):
        self.lr = lr

        self.weights = []
        self.biases = []
        self.memory = []
        for i in range(len(sizes) - 1):
            self.weights.append(init_weights(sizes[i + 1], sizes[i]))
            self.biases.append(init_weights(sizes[i + 1]))

    def forward(self, X):
        self.memory = [X]
        X = np.dot(self.weights[0], X.T).T + self.biases[0]
        for W, b in zip(self.weights[1:], self.biases[1:]):
            X = relu(X)
            self.memory.append(X)
            X = np.dot(W, X.T).T + b
        return softmax(X)

    def backward(self, y, y_pred):
        #  calculate the errors for each layer
        y = np.eye(y_pred.shape[1])[y]
        errors = [y_pred - y]
        for i in range(len(self.weights) - 1, 0, -1):
            new_err = sign(self.memory[i]) * \
                      np.dot(errors[0], self.weights[i])
            errors.insert(0, new_err)
            
        # update weights
        for i in range(len(self.weights)):
            self.weights[i] -= self.lr *\
                np.dot(self.memory[i].T, errors[i]).T
            self.biases[i] -= self.lr * errors[i].sum(0)

The data has 10 classes. When using a single hidden layer the accuracy is almost 40%. when using 2 or 3 hidden layers, the accuracy is around 9-10% from the first epoch and remains that way. The accuracy on the train set is also in that range. Is there a problem with my implementation that could cause such a thing?

from Neural networks very bad accuracy when using more than one hidden layer