如何从特征向量或单词生成句子? [英] How to generate a sentence from feature vector or words?

问题描述

我将VGG 16层Caffe模型用于图像标题，每个图像有多个标题.现在，我想根据这些标题(单词)生成一个句子.
我在LSTM上的一篇论文中读到，我应该从训练网络中删除SoftMax层，并将4096个特征向量从fc7层直接提供给LSTM.
我是LSTM和RNN的新手.
我应该从哪里开始?有没有教程显示如何通过序列标记生成句子?

I used VGG 16-Layer Caffe model for image captions and I have several captions per image. Now, I want to generate a sentence from those captions (words).
I read in a paper on LSTM that I should remove the SoftMax layer from the training network and provide the 4096 feature vector from fc7 layer directly to LSTM.
I am new to LSTM and RNN stuff.
Where should I begin? Is there any tutorial showing how to generate sentence by sequence labeling?

推荐答案

AFAIK BVLC/caffe的主分支尚不支持递归层体系结构.

AFAIK the master branch of BVLC/caffe does not yet support a recurrent layer architecture.

您应该从 jeffdonahue/caffe 中拉出分支recurrent.该分支支持RNN和LSTM.
它还包含有关如何生成使用<训练的图像标题的详细的示例. a href ="http://mscoco.org/" rel ="nofollow"> MS COCO 数据.

You should pull branch recurrent from jeffdonahue/caffe. This branch supports RNN and LSTM.
It also contains a detailed example on how to generate image captions trained using MS COCO data.

这篇关于如何从特征向量或单词生成句子?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！