0

我正在实施 Minh-Thang Luong 的注意力模型来构建一个英文到中文的翻译器。我训练的模型大小异常大(980 MB)。Minh-Thang Luong 的原始论文
模型结构

这是模型参数

state size:120  
source language vocabulary size:400000  
source language word embedding size:400000*50  
target language vocabulary size:20000  
target language word embedding size:20000*300

这是我在 tensorflow 中的模型实现。

import tensorflow as tf

src_vocab_size=400000
src_w2v_dim=50
tgt_vocab_size=20000
tgt_w2v_dim=300
state_size=120

with tf.variable_scope('net_encode'):
    ph_src_embedding = tf.placeholder(dtype=tf.float32,shape=[src_vocab_size,src_w2v_dim],name='src_vocab_embedding_placeholder')
    #src_word_emb = tf.Variable(initial_value=ph_src_embedding,dtype=tf.float32,trainable=False, name='src_vocab_embedding_variable')

    encoder_X_ix = tf.placeholder(shape=(None, None), dtype=tf.int32)
    encoder_X_len = tf.placeholder(shape=(None), dtype=tf.int32)
    encoder_timestep = tf.shape(encoder_X_ix)[1]
    encoder_X = tf.nn.embedding_lookup(ph_src_embedding, encoder_X_ix)
    batchsize = tf.shape(encoder_X_ix)[0]

    encoder_Y_ix = tf.placeholder(shape=[None, None],dtype=tf.int32)
    encoder_Y_onehot = tf.one_hot(encoder_Y_ix, src_vocab_size)

    enc_cell = tf.nn.rnn_cell.LSTMCell(state_size)
    enc_initstate = enc_cell.zero_state(batchsize,dtype=tf.float32)
    enc_outputs, enc_final_states = tf.nn.dynamic_rnn(enc_cell,encoder_X,encoder_X_len,enc_initstate)
    enc_pred = tf.layers.dense(enc_outputs, units=src_vocab_size)
    encoder_loss = tf.losses.softmax_cross_entropy(encoder_Y_onehot,enc_pred)
    encoder_trainop = tf.train.AdamOptimizer(0.001).minimize(encoder_loss)

with tf.variable_scope('net_decode'):
    ph_tgt_embedding = tf.placeholder(dtype=tf.float32, shape=[tgt_vocab_size, tgt_w2v_dim],
                                      name='tgt_vocab_embedding_placeholder')
    #tgt_word_emb = tf.Variable(initial_value=ph_tgt_embedding, dtype=tf.float32, trainable=False, name='tgt_vocab_embedding_variable')
    decoder_X_ix = tf.placeholder(shape=(None, None), dtype=tf.int32)
    decoder_timestep = tf.shape(decoder_X_ix)[1]
    decoder_X_len = tf.placeholder(shape=(None), dtype=tf.int32)
    decoder_X = tf.nn.embedding_lookup(ph_tgt_embedding, decoder_X_ix)

    decoder_Y_ix = tf.placeholder(shape=[None, None],dtype=tf.int32)
    decoder_Y_onehot = tf.one_hot(decoder_Y_ix, tgt_vocab_size)

    dec_cell = tf.nn.rnn_cell.LSTMCell(state_size)
    dec_outputs, dec_final_state = tf.nn.dynamic_rnn(dec_cell,decoder_X,decoder_X_len,enc_final_states)

    tile_enc = tf.tile(tf.expand_dims(enc_outputs,1),[1,decoder_timestep,1,1]) # [batchsize,decoder_len,encoder_len,state_size]
    tile_dec = tf.tile(tf.expand_dims(dec_outputs, 2), [1, 1, encoder_timestep, 1]) # [batchsize,decoder_len,encoder_len,state_size]
    enc_dec_cat = tf.concat([tile_enc,tile_dec],-1) # [batchsize,decoder_len,encoder_len,state_size*2]
    weights = tf.nn.softmax(tf.layers.dense(enc_dec_cat,units=1),axis=-2) # [batchsize,decoder_len,encoder_len,1]
    weighted_enc = tf.tile(weights, [1, 1, 1, state_size])*tf.tile(tf.expand_dims(enc_outputs,1),[1,decoder_timestep,1,1]) # [batchsize,decoder_len,encoder_len,state_size]
    attention = tf.reduce_sum(weighted_enc,axis=2,keepdims=False) # [batchsize,decoder_len,state_size]
    dec_attention_cat = tf.concat([dec_outputs,attention],axis=-1) # [batchsize,decoder_len,state_size*2]
    dec_pred = tf.layers.dense(dec_attention_cat,units=tgt_vocab_size) # [batchsize,decoder_len,tgt_vocab_size]
    pred_ix = tf.argmax(dec_pred,axis=-1) # [batchsize,decoder_len]
    decoder_loss = tf.losses.softmax_cross_entropy(decoder_Y_onehot,dec_pred)
    total_loss = encoder_loss + decoder_loss
    decoder_trainop = tf.train.AdamOptimizer(0.001).minimize(total_loss)

_l0 = tf.summary.scalar('decoder_loss',decoder_loss)
_l1 = tf.summary.scalar('encoder_loss',encoder_loss)
log_all = tf.summary.merge_all()
writer = tf.summary.FileWriter(log_path,graph=tf.get_default_graph())

这是到目前为止我能想到的模型参数大小的缩减

encoder cell
=(50*120+120*120+120)*4
=(src_lang_embedding_size*statesize+statesize*statesize+statesize)*(forget gate,remember gate,new state,output gate)
=(kernelsize_for_input+kernelsize_for_previous_state+bias)*(forget gate,remember gate,new state,output gate)  
=82080 floats

encoder dense layer  
=120*400000
=statesize*src_lang_vocabulary_size
=48000000 floats

decoder cell
=(300*120+120*120+120)*4
=(target_lang_embedding_size*statesize+statesize*statesize+statesize)*(forget gate,remember gate,new state,output gate)
=(kernelsize_for_input+kernelsize_for_previous_state+bias)*(forget gate,remember gate,new state,output gate)
=202080 floats

dense layer that compute attention weights
=(120+120)*1
=(encoder_output_size+decoder_output_size)*(1 unit)
=240 floats

decoder dense layer
=(120+120)*20000
=(attention_vector_size+decoder_outputsize)*target_lang_vocabulary_size
=4800000 floats

将它们相加得到 212 MB,但实际模型大小为 980 MB。那么哪里错了?

4

1 回答 1

1

您只是在计算可训练参数的数量,这些并不是您需要在 GPU 内存中容纳的唯一数字。

您正在使用 Adam 优化器,因此您需要存储所有参数的梯度和所有参数的动量。这意味着您需要将每个参数存储 3 次,即 636 MB。

然后,您需要为前向和后向传递容纳网络的所有中间状态。

假设批量大小为b和源,目标长度为 50,那么你有(至少,我可能忘记了一些东西):

  • b × l ×50 个源嵌入,
  • b × l ×300 个目标嵌入,
  • b × l ×5×120 个编码器状态,
  • b × l ×400000 编码器 logits,
  • b × l ×5×300 解码器状态,
  • b × l ×120 个中间注意力状态,
  • b × l ×20000 输出 logits。

这总共是 421970× b × l浮点数,您需要为前向和后向传递存储这些浮点数。

顺便提一句。源词汇 400k 是一个非常大的数字,我不相信它们中的大多数频繁到足以学习任何有意义的东西。您应该使用预处理(即SentencePiece)将您的词汇量减少到合理的大小。

于 2019-04-10T09:35:52.333 回答