本文首发于个人博客https://kezunlin.me/post/bcdfb73c/,欢迎阅读最新内容! tensorrt fp32 fp16 tutorial with caffe pytorch minist model Series Part 1: install and configure tensorrt 4 on ubuntu 16.04 Part 2: tensorrt fp32 fp16 tutorial Part 3: tensorrt int8 tutorial Code
1. 基础模型 A. Sequence to sequence model:机器翻译.语音识别.(1. Sutskever et. al., 2014. Sequence to sequence learning with neural networks. 2. Cho et. al., 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation.) B
1. Word representation One-hot representation的缺点:把每个单词独立对待,导致对相关词的泛化能力不强.比如训练出“I want a glass of orange juice”后,面对“I want a glass of apple ”,由于任何两个不同单词的one-hot vector的内积都为0,算法不知道orange和apple是一类词,所以没办法泛化出在apple后面填“juice”. Featurized represent