Pytorch-seq2seq-Beam-Search icon indicating copy to clipboard operation
Pytorch-seq2seq-Beam-Search copied to clipboard

Published 20 hours ago • verified publisher icon 312shan
→

Metadata

PyTorch implementation for Seq2Seq model with attention and Greedy Search / Beam Search for neural machine translation

Results 2 Pytorch-seq2seq-Beam-Search issues
Sort by recently updated
recently updated
newest added

你好，如何控制Beam_docoded输出的tokens 的数量

如上图，我本身target_sentence(包括SOS，EOS，pading)的长度设定的是8，但是我在测试的时候总会返回大量随机长度的tokens。请问如何解决

Andrew-Xu1 avatar Andrew-Xu1

Attention and Decoder Module hidden state question

Hi 312shan, great work! I was analyzing your code and was curious about parts of the forward for the Decoder and Attention module. . In the forward function of the...

pyoungkangkim avatar pyoungkangkim

← Metadata

55
Stars
11
Forks
Watchers

Owner

verified publisher icon 312shan

Metadata

PyTorch implementation for Seq2Seq model with attention and Greedy Search / Beam Search for neural machine translation

Back