纯Python和PyTorch对比实现循环神经网络LSTM及反向传播

最新推荐文章于 2025-05-07 19:17:18 发布

原创

最新推荐文章于 2025-05-07 19:17:18 发布 · 1.8k 阅读

1 ·

CC 4.0 BY-SA版权

本文对比了纯Python和PyTorch两种方式实现循环神经网络LSTM的详细过程，包括LSTMCell的创建与测试，探讨了反向传播的实现。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

摘要

本文使用纯 Python 和 PyTorch 对比实现循环神经网络LSTM及其反向传播.

正文

1. LSTMCell 类

文件目录 : vanilla_nn/lstmcell.py

import numpy as np


def sigmoid(x):
    return 1 / (1 + np.exp(-x))


class LSTMCell:
    def __init__(self, weight_ih, weight_hh, bias_ih, bias_hh):
        self.weight_ih = weight_ih
        self.weight_hh = weight_hh
        self.bias_ih = bias_ih
        self.bias_hh = bias_hh

        self.dc_prev = None
        self.dh_prev = None

        self.weight_ih_grad_stack = []
        self.weight_hh_grad_stack = []
        self.bias_ih_grad_stack = []
        self.bias_hh_grad_stack = []

        self.x_stack = []
        self.dx_list = []
        self.dh_prev_stack = []

        self.h_prev_stack = []
        self.c_prev_stack = []

        self.h_next_stack = []
        self.c_next_stack = []

        self.input_gate_stack = []
        self.forget_gate_stack = []
        self.output_gate_stack = []
        self.cell_memory_stack = []

    def __call__(self, x, h_prev, c_prev):
        a_vector = np.dot(x, self.weight_ih.T) + np.dot(h_prev, self.weight_hh.T)
        a_vector += self.bias_ih + self.bias_hh

        h_size = np.shape(h_prev)[1]
        a_i = a_vector[:, h_size * 0:h_size * 1]
        a_f = a_vector[:, h_size * 1:h_size * 2]
        a_c = a_vector[:, h_size * 2:h_size * 3]
        a_o = a_vector[:, h_size * 3:]

        input_gate = sigmoid(a_i)
        forget_gate = sigmoid(a_f)
        cell_memory = np.tanh(a_c)
        output_gate = sigmoid(a_o)

        c_next = (forget_gate * c_prev) + (input_gate * cell_memory)
        h_next = output_gate * np.tanh(c_next)

        self.x_stack.append(x)

        self.h_prev_stack.append(h_prev)
        self.c_prev_stack.append(c_prev)

        self.c_next_stack.append(c_next)
        self.h_next_stack.append(h_next)

        self.input_gate_stack.append(input_gate)
        self.forget_gate_stack.append(forget_gate)
        self.output_gate_stack.append(output_gate)
        self.cell_memory_stack.append(cell_memory)

        self.dc_prev = np.zeros_like(c_next)
        self.dh_prev = np.zeros_like(h_next)

        return