Home

Awesome

<div align="center">

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks

<a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"></a> <a href="https://mmf.sh/"><img alt="MMF" src="https://img.shields.io/badge/MMF-0054a6?logo=meta&logoColor=white"></a> Conference Paper

</div>

Updates

Our trained model is available at Google Drive.

Please refer to FashionViL repo for the dataset preparation.

Test on FashionIQ

python mmf_cli/run.py \
config=projects/fashionclip/configs/mtl_wa.yaml \
model=fashionclip \
datasets=fashioniq \
checkpoint.resume_file=save/backup_ckpts/fashionclip_512.pth \
run_type=test \
model_config.fashionclip.adapter_config.bottleneck=512