def __init__(self, params):
super(Seq2Seq, self).__init__()
self.embedding_matrix = load_embedding_matrix()
self.params = params
self.encoder = Encoder(self.embedding_matrix, params["enc_units"],
params["batch_size"])
self.attention = BahdanauAttention(params["attn_units"])
self.decoder = Decoder(self.embedding_matrix, params["dec_units"],
params["batch_size"])
def __init__(self, params):
super(Seq2Seq, self).__init__()
self.embedding_matrix = load_embedding_matrix()
self.params = params
self.encoder = Encoder(params["vocab_size"], params["embed_size"],
self.embedding_matrix, params["enc_units"],
params["batch_size"])
self.attention_layer = BahdanauAttention(self.params['attn_units'])
self.decoder = Decoder(self.params['vocab_size'],
self.params['embed_size'],
self.embedding_matrix, self.params['dec_units'],
self.params['batch_size'])
def __init__(self, params):
super(PGN, self).__init__()
self.embedding_matrix = load_embedding_matrix(
max_vocab_size=params['max_vocab_size'])
self.params = params
self.encoder = Encoder(self.embedding_matrix, params["enc_units"],
params["batch_size"])
self.attention = BahdanauAttention(params["attn_units"])
self.decoder = Decoder(self.embedding_matrix, params["dec_units"],
params["batch_size"])
self.pointer = Pointer()
def __init__(self, name_scope, params):
super(Seq2Seq, self).__init__(name_scope)
self.embedding_matrix = wv_loader.load_embedding_matrix()
self.params = params
self.encoder = Encoder('encoder',
enc_units=params["enc_units"],
batch_size=params["batch_size"],
word_vector=self.embedding_matrix)
self.attention = BahdanauAttention('attention', params["attn_units"])
self.decoder = Decoder('decoder',
dec_units=params["dec_units"],
batch_size=params["batch_size"],
word_vector=self.embedding_matrix)
def __init__(self, params, vocab):
super(Seq2Seq, self).__init__()
self.embedding_matrix = load_embedding_matrix()
self.params = params
self.vocab = vocab
self.batch_size = params["batch_size"]
self.enc_units = params["enc_units"]
self.dec_units = params["dec_units"]
self.attn_units = params["attn_units"]
print(self.embedding_matrix)
print(self.enc_units)
print(self.batch_size)
self.encoder = Encoder(self.embedding_matrix, self.enc_units,
self.batch_size)
self.attention = BahdanauAttention(self.attn_units)
self.decoder = Decoder(self.embedding_matrix, self.dec_units,
self.batch_size)
"""
from utils import config
from utils.data_processing import load_dataset
from utils.wv_loader import load_vocab, load_embedding_matrix
import tensorflow as tf
import time
import os
gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
train_x, train_y, test_x = load_dataset()
vocab, reverse_vocab = load_vocab(config.vocab_path)
embedding_matrix = load_embedding_matrix()
# 训练集的长度
BUFFER_SIZE = len(train_x)
# 输入的长度
max_length_inp = train_x.shape[1]
# 输出的长度
max_length_targ = train_y.shape[1]
BATCH_SIZE = 10
# 训练一轮需要迭代多少步
steps_per_epoch = len(train_x) // BATCH_SIZE
# 词向量维度
def call(self, context_vector, dec_hidden, dec_inp):
return tf.nn.sigmoid(
self.w_s_reduce(dec_hidden) + self.w_c_reduce(context_vector) +
self.w_i_reduce(dec_inp))
if __name__ == '__main__':
# GPU资源配置
config_gpu()
# 读取vocab训练
vocab, reverse_vocab = Vocab.load_vocab(save_wv_model_path)
# 计算vocab size
vocab_size = len(vocab)
# 使用GenSim训练好的embedding matrix
embedding_matrix = load_embedding_matrix(save_wv_model_path)
input_sequence_len = 250
BATCH_SIZE = 64
embedding_dim = 500
units = 1024
# 编码器结构
encoder = Encoder(vocab_size, embedding_dim, embedding_matrix, units,
BATCH_SIZE)
# example_input
example_input_batch = tf.ones(shape=(BATCH_SIZE, input_sequence_len),
dtype=tf.int32)
# sample input
sample_hidden = encoder.initialize_hidden_state()
