0
我試圖在tensorflow上創建1,000,000個字的嵌入。每個單詞將有一個256 float32矢量表示該單詞。問題在於我一直在耗盡內存。由於我的GTX 1080擁有8GB的內存，因此這對我來說並不重要。嵌入應該只佔用1e6 * 256 * 4 = 1 Gb的內存。我還在輸出上有另一個相同大小的矩陣。除此之外，還有其他一些張量應該比較小。因此，我只能看到存儲該模型所需的大約2 - 3 GB的內存，當我撥打sess.run(tf.initialize_all_variables())時，該內存會失效。我的記憶在哪裏？你對我如何解決這個問題有任何建議嗎？Tensorflow嵌入空間不足
import tensorflow as tf
import nltk
import numpy as np
import os
import multiprocessing
import itertools
import pickle
from unidecode import unidecode
BATCH_SIZE = 32
TIME_STEPS = 64
WORD_VEC_SIZE = 256
words, training_data = pickle.load(open('vocab.pickle', 'rb'))
word2index = {w:i for i, w in enumerate(words)}
index2word = {i:w for i, w in enumerate(words)}
input_tensor = tf.placeholder(tf.int32, (BATCH_SIZE, TIME_STEPS + 1), 'input_tensor')
embedding = tf.Variable(tf.random_uniform((len(words), WORD_VEC_SIZE), -1, 1), name = 'embedding')
rnn = tf.nn.rnn_cell.BasicRNNCell(WORD_VEC_SIZE)
state = tf.zeros((BATCH_SIZE, rnn.state_size))
input_vectors = tf.nn.embedding_lookup([embedding], input_tensor[:, :TIME_STEPS])
cost = 0
with tf.variable_scope('rnn') as scope:
W_out = tf.get_variable('W_out', (WORD_VEC_SIZE, len(words)), initializer = tf.truncated_normal_initializer(0.0, 1/np.sqrt(WORD_VEC_SIZE)))
b_out = tf.get_variable('b_out', (len(words),), initializer = tf.truncated_normal_initializer(0.0, 0.01))
for t in range(TIME_STEPS):
y, state = rnn(tf.reshape(input_vectors[:, t, :], (-1, WORD_VEC_SIZE)), state)
cost += tf.reduce_mean(tf.nn.sampled_softmax_loss(W_out, b_out, y, tf.reshape(input_tensor[:, t + 1], (-1, 1)), 1000, len(words)))
scope.reuse_variables()
train_step = tf.train.AdamOptimizer(1e-4).minimize(cost)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()