Content-Style Modulation for Image Retrieval with Text Feedback
CoSMo.pytorch
Official Implementation of CoSMo: Content-Style Modulation for Image Retrieval with Text Feedback, Seungmin Lee*, Dongwan Kim*, Bohyung Han. *(denotes equal contribution)
Setup
Python: python3.7
Install required packages
Install torch and torchvision via following command (CUDA10)
pip install torch==1.2.0 torchvision==0.4.0 -f https://download.pytorch.org/whl/torch_stable.html
Install other packages
pip install -r requirements.txt
Dataset
Download the FashionIQ dataset by following the instructions on this link.
We have set the default path for FashionIQ datasets in data/fashionIQ.py as _DEFAULT_FASHION_IQ_DATASET_ROOT = '/data/image_retrieval/fashionIQ'. You can change this path to wherever you plan on storing the dataset.
Vocabulary file
Open up a python console and run the following lines to download NLTK punkt:
import nltk
nltk.download('punkt')
Then, open up a Jupyter notebook and run