A framework for training and evaluating a transformer with scaled dot product attention on a tensorflow dataset.

Classifying citrus leaf images based on disease type using Convolutional Neural Networks(CNNs).

Library aiding testing of models resicilience to adverasial attacks. Created as a part of Bachelor's Thesis.

It's a sample project for a recommender system using TensorFlow

Using Keras models and datasets to build custom prediction models

TensorFlow implementation of Deep Convolutional Generative Adversarial Networks

You can freely purchase the block from:

This repo consists a Python Notebook file where I have performed transfer learning using Keras Xception Transformer.

Demo of data augmentation: a technique to increase the diversity of your training set by applying random (but realistic) transformations, such as image rotation

Image Classification modelling for the Oxford-Flowers102 dataset. Looking at a model that predicts new flower images based on the already pre-trained categories, with relative high accuracy.

Scripts used in experiments to develop models for image classification

dataset generator

Google Summer of Code - 2019

We are going to use CPU for Extract , Transform and Load, and GPU for training model parallelly

In this project I trained a CNN model and predicted three types of potato leaf. Either the potato may be healthy or has an early blight disease or late blight disase. The model has good accuracy on these 3 classes. But it is accepting only images of size (256,256) if we pass images other than that shape it won't work.

Create Convolutional Neural Network from scratch with potato disease classification. App will allow farmers to snap a picture of a plant and determine whether the plant has a disease or not.

Tf dataset Citrus_leaves is demonstrated for the Data Augmentation deep learning.

The repository contains the materials discussed in part 1 of the Image Classification with YonoHub & Tensorflow V2.0 Series

I've completed a number of deep learning and machine learning projects in this repository. In the future, I'll be adding other projects as well. The majority of the data was gathered from Kaggle, TensorFlow datasets, and other places that offer free data. In order to create my models, I used the Google Colab environment.