Skip to content

Latest commit

 

History

History
41 lines (32 loc) · 1.34 KB

README.md

File metadata and controls

41 lines (32 loc) · 1.34 KB
Raw

Introduction

This repository is for Bottom-up and Top-down Object Inference Networks for Image Captioning

Requirements

Data preparation

  1. Download the bottom up features and convert them to npz files
python3 tools/create_feats.py --infeats bottom_up_tsv --outfolder ./mscoco/feature/up_down_10_100

  1. Download the annotations into the mscoco folder. More details about data preparation can be referred to self-critical.pytorch

  2. Download coco-caption and setup the path of __C.INFERENCE.COCO_PATH in lib/config.py

Training

Train BTO-Net model

bash experiments/btonet/train.sh

Evaluation

CUDA_VISIBLE_DEVICES=0 python3 main_test.py --folder experiments/btonet --resume model_epoch

Acknowledgements

Thanks the contribution of self-critical.pytorch and awesome PyTorch team.