Keras + Universal Sentence Encoder = Transfer Learning for text data

Landmark Detection (Google Lens like Interface) using TensorFlow Hub & Gradio

Image Scene Classification Model for TensorFlow Hub

It detects whether entered questions are similar or not

Tutorial sobre transferência de aprendizado utilizando Tensorflow Hub apresentado no IV Meetup PyData Manaus

A performance comparison of sentiment analysis between pre-trained NLP models and visualization them in TensorBoard . Fine tuning some model to for more accurate prediction.

Build an image classifier using transfer learning

Developed an automated exam proctoring platform that integrates with Google forms and Microsoft Forms for real-time monitoring, multiple people detection, mobile phone detection, tab and full-screen checks, while enabling teachers to create and manage exams, track participation and monitor terminated students for malpractice through an admin portal

Build a simple text classifier with TF-Hub

A website with complete cloud integration that utilizes terraform and dockers for deployment to use an image to predict the location in Asia.

Artnet is a social network based on sharing artworks

Text analysis with NLP Tool kit basics and Preprocessing the text using Tensorflow built-in models

Essa é uma aplicação que utiliza os classificadores do tensor hub e o Tensorflow JS para a criação de uma extensão chrome que filtre toda imagens.

Uses Transfer Learning to create an advanced and more accurate Machine Learning model for classifying type of flowers in the flower dataset

This project uses a pre-trained MobileNetV2 model as a feature extractor and adds a custom dense layer to perform binary classification between cat and dog images.

Multi Class Dog Breed Classification

This project demonstrates the use of various pre-trained models for transfer learning in NLP using TensorFlow Hub.

Basics of machine learning is END-TO-END Repository which includes very Basic Machine Learning Models and Notebook

The comparison between different embeddings (TF-IDF, USE, and TF-IDF + USE) and various classifiers provides valuable insights into the performance of different techniques for sentiment classification.