LuoweiZhou / e2e-gLSTM-sc

Code for paper "Image Caption Generation with Text-Conditional Semantic Attention"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

e2e-gLSTM-sc为什么要从e2eglstm-checkpoint 开始训练?

mymuli opened this issue · comments

命令:-start_from /path/to/your/e2eglstm-checkpoint

Hi @Rmuli, it's mentioned in Sec. 4.1, par 2 of the paper