Skip to content

Latest commit

 

History

History
27 lines (18 loc) · 873 Bytes

README.md

File metadata and controls

27 lines (18 loc) · 873 Bytes

Abhivyakthi (Screen Name) :D

ViewU (Tool Name) :P

ViewU is an automated tool, that can enable user to have of view of him/her on the products he/she purchase like dresses, accessories, jewelry etc.This is implemented using GANs

Dependency

Training

To train the model, we used LOOKBOOK dataset, resize images to 64*64. Prepare the dataset using pytorch-GAN/tool/prepare_data.py. Then goto src dir and run

python3 train.py

Monitor the performance

  • Install visdom.

  • Start the visdom server with python3 -m visdom.server 5274

  • Open this URL in your browser: http://localhost:5274 You will see the loss curve as well as the image examples.

  • Development in Progress