def __init__(self, vocab_size, num_hidden, **kwargs):
super(RNNModel, self).__init__(**kwargs)
self.rnn = rnn.RNN(num_hidden)
self.rnn.initialize()
self.vocab_size = vocab_size
self.dense = nn.Dense(vocab_size) #output to observation
import d2lzh as d2l
from mxnet import autograd, gluon, init, nd
from mxnet.gluon import loss as gloss, nn, rnn
import math, time
(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()
################################################# TODO 定义模型 #####################################################
# 构造单隐藏层，个数是256
num_hiddens = 256
rnn_layer = rnn.RNN(num_hiddens)
rnn_layer.initialize()
batch_size = 2
state = rnn_layer.begin_state(batch_size=batch_size) # 返回初始化隐藏状态列表
print(state[0].shape) # （隐藏层个数，batch_size，num_hiddens）
num_steps = 35
X = nd.random.uniform(shape=(num_steps, batch_size, vocab_size))
Y, state_new = rnn_layer(X, state)
print(Y.shape, len(state_new), state_new[0].shape) # state_new和state同型
class RNNModel(nn.Block):
def __init__(self, rnn_layer, vocab_size, **kwargs):
super().__init__(**kwargs)
self.rnn = rnn_layer
self.vocab_size = vocab_size
self.dense = nn.Dense(vocab_size)
for x in inputs:
h = nd.tanh(nd.dot(x, self.w_xh) + nd.dot(h, self.w_hh) + self.b_h)
y = nd.dot(h, self.w_hq) + self.b_q
outputs.append(y)
y_hat = nd.concat(*outputs, dim=0)
return y_hat, (h, )
if __name__ == '__main__':
_corpus_indices, _idx_to_char, _char_to_idx, _vocab_size = \
data_sets.load_jaychou_lyrics("../data/jaychou_lyrics.txt.zip")
_num_hidden = 256
_num_steps = 35
_batch_size = 32
_lr = 1e2
use_gluon = False
if use_gluon:
_rnn_layer = rnn.RNN(_num_hidden)
model = BaseRNNGluon(_vocab_size, _idx_to_char, _char_to_idx,
_num_hidden, _rnn_layer)
else:
model = RNNScratch(_vocab_size, _idx_to_char, _char_to_idx,
_num_hidden)
model.fit(_corpus_indices,
_num_steps, {
"lr": _lr,
"batch_size": _batch_size
},
epochs=250)
