Skip to content

Latest commit

 

History

History
26 lines (21 loc) · 1.13 KB

README.md

File metadata and controls

26 lines (21 loc) · 1.13 KB

Shopping-Recommender

Required Python >= 3.8
Required Packages

  • pytorch
  • sklearn
  • tkinter
  • numpy
  • matplotlib
  • pillow
  • warnings

Dataset

Download dataset here. This data set consists of 16,000 images of apparels including some outliers.

Creation of Embeddings

efficient-net.ipynb has the required code to generate embeddings from images. Generate required embeddings from the dataset which gives a .npy file with all embedings. Some pretrained embedings can be found here.

Training and Testing

Use the recommender.ipynb to train and test the embeddings data.

Some Images of the recommender system