top of page
Comprehensive Linguistic-Visual Composition Network for Image Retrieval
1. Running Environments
Python 3.7.6
Pytorch 1.6.0
TITAN XP
Ubuntu 14.04.6 LTS
2. Main Files
train.py: The training file.
model.py: Defining the CLVC-NET model structure.
text_model.py: Defining the text encoder.
resnet.py: Defining the image encoder.
datasets.py: The data loading file.
test.py: The testing file.
3. Download
Codes and pre-trained models:
https://drive.google.com/file/d/159rBhWyhkLN7sXAi8iyW_ljzFNLJinKa/view?usp=sharing
4. Notes
Note that for the FashionIQ dataset, we first resize the downloaded images follow the XiaoxiaoGuo by resize_images.py
bottom of page