了解Trax中的变压器入门示例

问题描述

我是机器翻译和Trax的新手。我的目标是了解Trax中的变压器入门示例，可以在https://trax-ml.readthedocs.io/en/latest/notebooks/trax_intro.html中找到：

import trax

# Create a Transformer model.
# Pre-trained model config in gs://trax-ml/models/translation/ende_wmt32k.gin
model = trax.models.Transformer(
    input_vocab_size=33300,d_model=512,d_ff=2048,n_heads=8,n_encoder_layers=6,n_decoder_layers=6,max_len=2048,mode='predict')

# Initialize using pre-trained weights.
model.init_from_file('gs://trax-ml/models/translation/ende_wmt32k.pkl.gz',weights_only=True)

# Tokenize a sentence.
sentence = 'It is nice to learn new things today!'
tokenized = list(trax.data.tokenize(iter([sentence]),# Operates on streams.
                                    vocab_dir='gs://trax-ml/vocabs/',vocab_file='ende_32k.subword'))[0]

# Decode from the Transformer.
tokenized = tokenized[None,:]  # Add batch dimension.
tokenized_translation = trax.supervised.decoding.autoregressive_sample(
    model,tokenized,temperature=0.0)  # Higher temperature: more diverse results.

# De-tokenize,tokenized_translation = tokenized_translation[0][:-1]  # Remove batch and EOS.
translation = trax.data.detokenize(tokenized_translation,vocab_dir='gs://trax-ml/vocabs/',vocab_file='ende_32k.subword')
print(translation)

该示例运行良好。但是，当我尝试使用已初始化模型（例如

）转换另一个示例时

sentence = 'I would like to try another example.'
tokenized = list(trax.data.tokenize(iter([sentence]),vocab_file='ende_32k.subword'))[0]
tokenized = tokenized[None,:]
tokenized_translation = trax.supervised.decoding.autoregressive_sample(
    model,temperature=0.0)
tokenized_translation = tokenized_translation[0][:-1]
translation = trax.data.detokenize(tokenized_translation,vocab_file='ende_32k.subword')
print(translation)

我在本地计算机和Google Colab上都得到了输出!。其他示例也是如此。

当我建立并初始化新模型时，一切正常。

这是一个错误吗？如果不是，那么有人会这么向我解释这里发生了什么以及如何避免/修复这种行为？

令牌化和去令牌化似乎运行良好，我对此进行了调试。 trax.supervised.decoding.autoregressive_sample中似乎出现了错误/意外。

解决方法

我自己发现了这个问题……需要重置模型的state。因此，以下代码对我有用：

def translate(model,sentence,vocab_dir,vocab_file):
    empty_state = model.state # save empty state
    tokenized_sentence = next(trax.data.tokenize(iter([sentence]),vocab_dir=vocab_dir,vocab_file=vocab_file))
    tokenized_translation = trax.supervised.decoding.autoregressive_sample(
        model,tokenized_sentence[None,:],temperature=0.0)[0][:-1]
    translation = trax.data.detokenize(tokenized_translation,vocab_file=vocab_file)
    model.state = empty_state # reset state
    return translation

# Create a Transformer model.
# Pre-trained model config in gs://trax-ml/models/translation/ende_wmt32k.gin
model = trax.models.Transformer(input_vocab_size=33300,d_model=512,d_ff=2048,n_heads=8,n_encoder_layers=6,n_decoder_layers=6,max_len=2048,mode='predict')
# Initialize using pre-trained weights.
model.init_from_file('gs://trax-ml/models/translation/ende_wmt32k.pkl.gz',weights_only=True)

print(translate(model,'It is nice to learn new things today!',vocab_dir='gs://trax-ml/vocabs/',vocab_file='ende_32k.subword'))
print(translate(model,'I would like to try another example.',vocab_file='ende_32k.subword'))