Ugenteraan/Deep_Hierarchical_Classification
PyTorch Implementation of Deep Hierarchical Classification for Category Prediction in E-commerce System
This project helps e-commerce businesses accurately categorize products by their main type (e.g., 'Apparel') and then by a more specific sub-type (e.g., 'Men's Shirts'). It takes product images and associated metadata, and outputs precise hierarchical category predictions, which can be used by anyone managing product listings or inventory in an online store.
No commits in the last 6 months.
Use this if you need to classify products into both broad categories and very specific subcategories simultaneously, rather than running multiple classification steps.
Not ideal if your classification task does not involve a clear hierarchy or if you don't have image data for your items.
Stars
99
Forks
21
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ugenteraan/Deep_Hierarchical_Classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models