attention.py

import numpy as np

def encoder_layer(Q, K_transpose, V, Wq, Wk, Wv):
    Q_proj = np.dot(Q, Wq.T)
    K_proj = np.dot(K_transpose.T, Wk.T)
    V_proj = np.dot(V, Wv.T)
    attention_scores = scaled_dot_product_attention_2D(Q_proj, K_proj, V_proj)
    return attention_scores

def calcular_pesos_proyeccion(attention_matrix):
    num_letras = attention_matrix.shape[0]
    Wq = np.zeros((num_letras, attention_matrix.shape[1]))
    Wk = np.zeros((num_letras, attention_matrix.shape[1]))
    Wv = np.zeros((num_letras, attention_matrix.shape[1]))
    for i in range(num_letras):
        Wq[i, i] = 1
        Wk[i, i] = 1
        Wv[i, i] = 1
    return Wq, Wk, Wv

def scaled_dot_product_attention_2D(Q, K_transpose, V):
    out = np.zeros((Q.shape[0], V.shape[1]))
    for i in range(Q.shape[0]):
        scores = np.dot(Q[i, :], K_transpose)
        softmax_scores = np.exp(scores - np.max(scores)) / np.sum(np.exp(scores - np.max(scores)))
        out[i, :] = np.dot(softmax_scores, V)
    return out