/self-critical.pytorch

ai challenger image captionning(Chinese) 12th

Primary LanguagePython

Image-Captioning-Chinese

This repository is my solution for ai challenger Image-Captioning(Chinese).

This is based on ruotianluo's self-critical.pytorch repository.

Requirements

Python 2.7 (because there is no AI_Challenger-caption-eval version for python 3) PyTorch 0.3 (along with torchvision)

You need to extract image feature for yourself, like fast-rcnn, resnet, etc.

Train your own network on ai challenger

Download ai challenger dataset and extract. First, download the ai challenger image caption data from link

Second, extract image feature.

Start training

python train.py