PokeZoo is webapp that enables users to create their own Pokemon collections by identifying Pokemon from images using deep learning.

This webapp is hosted on Heroku. All features are added using a CI-CD pipeline through Github.

  1. Backend - Node.js, Express.js
  2. Frontend - React.js, Emotion.js, TailwindCSS, Twin.macro
  3. Database - MongoDB
  4. Authentication - JsonWebToken
  5. Pokemon Data API - pokeAPI
  6. Deep learning Inference - Tensorflow.js
  7. Deep learning training - Docker + Tensorflow + Python

Don't forget to tag @theairbend3r in your comment, otherwise they may not be notified.

Authors original post
Research Associate @ Indian Institute of Science. Into computer vision and deep learning. Work with Python, R, and JS.
Share this project
Similar projects
TensorFlow implementation of G-SimCLR.
Segmentation Models
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Awesome TFLite
An awesome list of TFLite models with sample apps, model zoo, helpful tools and learning resources from the community.
Learning to See before Learning to Act: Visual Pre-training
We find that pre-training on vision tasks significantly improves generalization and sample efficiency for learning to manipulate objects.