Skip to content

Latest commit

 

History

History
19 lines (15 loc) · 497 Bytes

README.md

File metadata and controls

19 lines (15 loc) · 497 Bytes

Image Caption

This is an implementation of Bridging by Word: Image-Grounded Vocabulary Construction for Visual Captioning based on pytorch 1.0.

Setup

  1. Install python3.6 and pytorch 1.0.

  2. Download the image data of MS COCO to Data/raw/img.

  3. Data processing. You need to create a folder in Data/train with the name of coco_v? to store the processed data.

cd Code
python BuildImgOrderClusterVocab.py
  1. Model training.
cd Code
python Trainer.py