Tex>> Deep-Cross-Modal-Projection-Learning-for-Image-Text-Matching>> 返回
项目作者： labyrinth7x

项目描述 ：
Deep Cross-Modal Projection Learning for Image-Text Matching
高级语言： Python
项目地址: git://github.com/labyrinth7x/Deep-Cross-Modal-Projection-Learning-for-Image-Text-Matching.git


Deep Cross-Modal Projection Learning for Image-Text Matching

This is a Pytorch implmentation for the paper Deep Cross-Modal Projection Learning for Image-Text Matching.
The official implementation in TensorFlow can be found here.

Requirement

  • Python 3.5
  • Pytorch 1.0.0 & torchvision 0.2.1
  • numpy
  • scipy 1.2.1

Data Preparation

  • Download the pre-computed/pre-extracted data from GoogleDrive and move them to data/processed folder. Or you can use the file dataset/preprocess.py to prepare your own data.
  • [Optional] Download the pre-trained model weights from GoogleDrive and move them to pretrained_models folder.

Training & Testing

You should firstly change the param model_path to your current directory. 

  1. sh scripts/run.sh

You can directly run the code instead of performing training and testing seperately.
Or training: 

  1. sh scripts/train.sh

Or testing:

  1. sh scripts/test.sh