NNDL 作业10 BPTT

习题6-1P 推导RNN反向传播算法BPTT.

习题6-2 推导公式(6.40)和公式(6.41)中的梯度．

 习题6-3 当使用公式(6.50)作为循环神经网络的状态更新公式时， 分析其可能存在梯度爆炸的原因并给出解决方法．

习题6-2P 设计简单RNN模型，分别用Numpy、Pytorch实现反向传播算子，并代入数值测试.

import torch
import numpy as np
class RNNCell:
    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.x_stack=[]
        self.dx_list=[]
        self.dw_ih_stack=[]
        self.dw_hh_stack=[]
        self.db_ih_stack=[]
        self.db_hh_stack=[]

        self.prev_hidden_stack=[]
        self.next_hidden_stack=[]

        self.prev_dh=None

    def __call__(self,x,prev_hidden):
        self.x_stack.append(x)
        next_h=np.tanh(
            np.dot(x,self.weight_ih.T)
            +np.dot(prev_hidden,self.weight_hh.T)
            +self.bias_ih+self.bias_hh)

        self.prev_hidden_stack.append(prev_hidden)
        self.next_hidden_stack.append(next_h)
        self.prev_dh=np.zeros(next_h.shape)
        return next_h

    def backward(self,db):
        x=self.x_stack.pop()
        prev_hidden=self.prev_hidden_stack.pop()
        next_hidden=self.next_hidden_stack.pop()

        d_tanh=(db+self.prev_dh)*(1-next_hidden**2)
        self.prev_dh=np.dot(d_tanh,self.weight_hh)

        dx=np.dot(d_tanh,self.weight_ih)
        self.dx_list.insert(0,dx)

        dw_ih=np.dot(d_tanh.T,x)
        self.dw_ih_stack.append(dw_ih)

        dw_hh=np.dot(d_tanh.T,prev_hidden)
        self.dw_hh_stack.append(dw_hh)

        self.db_ih_stack.append(d_tanh)
        self.db_hh_stack.append(d_tanh)

        return self.dx_list

if __name__=='__main__':
    np.random.seed(123)
    torch.random.manual_seed(123)
    np.set_printoptions(precision=6,suppress=True)

    rnn_PyTorch=torch.nn.RNN(4,5).double()
    rnn_numpy=RNNCell(rnn_PyTorch.all_weights[0][0].data.numpy(),
                      rnn_PyTorch.all_weights[0][1].data.numpy(),
                      rnn_PyTorch.all_weights[0][2].data.numpy(),
                      rnn_PyTorch.all_weights[0][3].data.numpy())
    nums=3
    x3_numpy=np.random.random((nums,3,4))
    x3_tensor=torch.tensor(x3_numpy,requires_grad=True)

    h3_numpy=np.random.random((1,3,5))
    h3_tensor=torch.tensor(h3_numpy,requires_grad=True)

    dh_numpy=np.random.random((nums,3,5))
    dh_tensor=torch.tensor(dh_numpy,requires_grad=True)

    h3_tensor = rnn_PyTorch(x3_tensor, h3_tensor)
    h_numpy_list = []

    h_numpy = h3_numpy[0]
    for i in range(nums):
        h_numpy = rnn_numpy(x3_numpy[i], h_numpy)
        h_numpy_list.append(h_numpy)

    h3_tensor[0].backward(dh_tensor)
    for i in reversed(range(nums)):
        rnn_numpy.backward(dh_numpy[i])

    print("numpy_hidden :\n", np.array(h_numpy_list))
    print("torch_hidden :\n", h3_tensor[0].data.numpy())
    print("-----------------------------------------------")

    print("dx_numpy :\n", np.array(rnn_numpy.dx_list))
    print("dx_torch :\n", x3_tensor.grad.data.numpy())
    print("------------------------------------------------")

    print("dw_ih_numpy :\n",
          np.sum(rnn_numpy.dw_ih_stack, axis=0))
    print("dw_ih_torch :\n",
          rnn_PyTorch.all_weights[0][0].grad.data.numpy())
    print("------------------------------------------------")

    print("dw_hh_numpy :\n",
          np.sum(rnn_numpy.dw_hh_stack, axis=0))
    print("dw_hh_torch :\n",
          rnn_PyTorch.all_weights[0][1].grad.data.numpy())
    print("------------------------------------------------")

    print("db_ih_numpy :\n",
          np.sum(rnn_numpy.db_ih_stack, axis=(0, 1)))
    print("db_ih_torch :\n",
          rnn_PyTorch.all_weights[0][2].grad.data.numpy())
    print("-----------------------------------------------")
    print("db_hh_numpy :\n",
          np.sum(rnn_numpy.db_hh_stack, axis=(0, 1)))
    print("db_hh_torch :\n",
          rnn_PyTorch.all_weights[0][3].grad.data.numpy())

 

 参考：

NNDL 作业9：分别使用numpy和pytorch实现BPTT-CSDN博客

L5W1作业1 手把手实现循环神经网络-CSDN博客