首先說明代碼只是幫助理解，并未寫出梯度下降部分，默認(rèn)參數(shù)已經(jīng)被固定，不影響理解。代碼主要實現(xiàn)RNN原理，只使用numpy庫，不可用于GPU加速。
import numpy as np
class Rnn():
def __init__(self, input_size, hidden_size, num_layers, bidirectional=False):
self.input_size = input_size
self.hidden_size = hidden_size
self.num_layers = num_layers
self.bidirectional = bidirectional
def feed(self, x):
'''
:param x: [seq, batch_size, embedding]
:return: out, hidden
'''
# x.shape [sep, batch, feature]
# hidden.shape [hidden_size, batch]
# Whh0.shape [hidden_size, hidden_size] Wih0.shape [hidden_size, feature]
# Whh1.shape [hidden_size, hidden_size] Wih1.size [hidden_size, hidden_size]
out = []
x, hidden = np.array(x), [np.zeros((self.hidden_size, x.shape[1])) for i in range(self.num_layers)]
Wih = [np.random.random((self.hidden_size, self.hidden_size)) for i in range(1, self.num_layers)]
Wih.insert(0, np.random.random((self.hidden_size, x.shape[2])))
Whh = [np.random.random((self.hidden_size, self.hidden_size)) for i in range(self.num_layers)]
time = x.shape[0]
for i in range(time):
hidden[0] = np.tanh((np.dot(Wih[0], np.transpose(x[i, ...], (1, 0))) +
np.dot(Whh[0], hidden[0])
))
for i in range(1, self.num_layers):
hidden[i] = np.tanh((np.dot(Wih[i], hidden[i-1]) +
np.dot(Whh[i], hidden[i])
))
out.append(hidden[self.num_layers-1])
return np.array(out), np.array(hidden)
def sigmoid(x):
return 1.0/(1.0 + 1.0/np.exp(x))
if __name__ == '__main__':
rnn = Rnn(1, 5, 4)
input = np.random.random((6, 2, 1))
out, h = rnn.feed(input)
print(f'seq is {input.shape[0]}, batch_size is {input.shape[1]} ', 'out.shape ', out.shape, ' h.shape ', h.shape)
# print(sigmoid(np.random.random((2, 3))))
#
# element-wise multiplication
# print(np.array([1, 2])*np.array([2, 1]))
到此這篇關(guān)于numpy實現(xiàn)RNN原理實現(xiàn)的文章就介紹到這了,更多相關(guān)numpy實現(xiàn)RNN內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！
