Terrance-Whitehurst

Aerial-Cactus-Classification-Keras

In this project I take the satelite images taken for autonomous feild detection to classify cactuses within the feild. I follow the research paper experiment and use the LeNet-5 Convolutional Neural Network architecture. I use data augmentation to get the model to a 95% accuracy.

Attack-On-Titan-Keras-Classification

In this project I used the keras deep learning library and with convolutional neural network created from scratch to do multi-classification on a custom Attack On Titan deep learning image dataset that I created scraping images from the web with python and javascript.

Blood-Cell-Classification-W-Keras

In this deep learning project I use keras to classify different different images of blood cells. This vision model was trained using Kaggle kernels GPUs. I use the functional keras model along with a custom built convolutional neural network and data augmentation so the model does not see the same image during training which prevents overfitting.

Car-Tracking-ImageAI-Object-Detection

This is a side project I haven been working on to track and count the amount of cars in a video. I use the ImageAI object detection library to track and count the cars in the video. Thanks to the wonderful creators of ImageAI library you also can get the detection analytics for each frame, minute, and seconds of the video. The detection analytics for each second can be found in the "analytics" directory. The video used for detection is a random stock video I found to use for this project to perform object detection.

Crowd-Counting-Object-Detection-ImageAI

This is a side project I haven been working on for crowd counting and tracking. I use the ImageAI object detection library to track and count the crowd in the video. Thanks to the wonderful creators of ImageAI library you also can get the detection analytics for each frame, minute, and seconds of the video. The detection analytics for each second can be found in the "analytics" directory. The video used for detection is a random stock video I found to use for this project to perform object detection.

Keras-Histopathologic-Cancer-Detection

In this competition, you must create an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset (the original PCam dataset contains duplicate images due to its probabilistic sampling, however, the version presented on Kaggle does not contain duplicates).

Keras-Lego-Parts-Classifcation

In this project I create a CNN to clasify lego images from a kaggle dataset. These lego peices were rendered in 3D using Blender. I use data augmentation with a custom built CNN and Keras Callbacks to acheive a 96% accuracy. I used Kaggle's cloud GPUs to run my model and load my data.

Malaria-Cell-Detection-Keras-and-Tensorflow-

In this kaggle kernel I used a very interesting dataset of Malaria Cell images along with a CNN to classify malaraia cells at a 95% accuracy. With Keras and TensorFlow I was able to construct a model that was able to accuractly detect malaria within cell images.

Murray-Object-Detection-ImageAI

In this project I have used the imageAI library along with YoloV3 for object recognition on Andy Murray. I am a professional tennis player so my motivation for this project was to use the imageAI library on my favorite professional players.

Rock-Paper-Scissors-Keras-Classification

In this project I use the a dataset on kaggle that has pictures of human hands playing rock paper scissors. I use Keras with TensorFlow along with data augmentation and Keras ImageDataGenerator for image preprocessing to obtain an accuracy of 99%.

Terrance-Whitehurst/Rock-Paper-Scissors-Keras-Classification

In this project I use the a dataset on kaggle that has pictures of human hands playing rock paper scissors. I use Keras with TensorFlow along with data augmentation and Keras ImageDataGenerator for image preprocessing to obtain an accuracy of 99%.

Terrance-Whitehurst/Crowd-Counting-Object-Detection-ImageAI

This is a side project I haven been working on for crowd counting and tracking. I use the ImageAI object detection library to track and count the crowd in the video. Thanks to the wonderful creators of ImageAI library you also can get the detection analytics for each frame, minute, and seconds of the video. The detection analytics for each second can be found in the "analytics" directory. The video used for detection is a random stock video I found to use for this project to perform object detection.

Terrance-Whitehurst/Keras-Histopathologic-Cancer-Detection

In this competition, you must create an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset (the original PCam dataset contains duplicate images due to its probabilistic sampling, however, the version presented on Kaggle does not contain duplicates).

Terrance-Whitehurst/Keras-Lego-Parts-Classifcation

In this project I create a CNN to clasify lego images from a kaggle dataset. These lego peices were rendered in 3D using Blender. I use data augmentation with a custom built CNN and Keras Callbacks to acheive a 96% accuracy. I used Kaggle's cloud GPUs to run my model and load my data.

Terrance-Whitehurst/Attack-On-Titan-Keras-Classification

In this project I used the keras deep learning library and with convolutional neural network created from scratch to do multi-classification on a custom Attack On Titan deep learning image dataset that I created scraping images from the web with python and javascript.

Terrance-Whitehurst/Blood-Cell-Classification-W-Keras

In this deep learning project I use keras to classify different different images of blood cells. This vision model was trained using Kaggle kernels GPUs. I use the functional keras model along with a custom built convolutional neural network and data augmentation so the model does not see the same image during training which prevents overfitting.

Terrance-Whitehurst/Murray-Object-Detection-ImageAI

In this project I have used the imageAI library along with YoloV3 for object recognition on Andy Murray. I am a professional tennis player so my motivation for this project was to use the imageAI library on my favorite professional players.

Terrance-Whitehurst/Car-Tracking-ImageAI-Object-Detection

This is a side project I haven been working on to track and count the amount of cars in a video. I use the ImageAI object detection library to track and count the cars in the video. Thanks to the wonderful creators of ImageAI library you also can get the detection analytics for each frame, minute, and seconds of the video. The detection analytics for each second can be found in the "analytics" directory. The video used for detection is a random stock video I found to use for this project to perform object detection.

Terrance-Whitehurst/Intel-Image-Classification-Challenge-Keras

This data was initially published on https://datahack.analyticsvidhya.com by Intel to host a Image classification Challenge. Thanks to https://datahack.analyticsvidhya.com for the challenge and Intel for the Data. In this project I perform multi-class classifcation on different images from intels image classification competition. I use the deep learning library Keras with a TensorFlow backend and a custom build convolutional neural network. I used keras ImageDataGenerator to perform data augmentation on my images and used Keras callbacks to monitor training and visualize the training result in the kernel and TensorBoard. I was able to reach a 92% accuracy on this model!

Terrance-Whitehurst/Malaria-Cell-Detection-Keras-and-Tensorflow-

In this kaggle kernel I used a very interesting dataset of Malaria Cell images along with a CNN to classify malaraia cells at a 95% accuracy. With Keras and TensorFlow I was able to construct a model that was able to accuractly detect malaria within cell images.

Terrance-Whitehurst/Nadal-Object-Detection-ImageAI

In this project I have used the imageAI library along with YoloV3 for object recognition on Rafa Nadal. I am a professional tennis player so my motivation for this project was to use the imageAI library on my favorite professional players.

Terrance-Whitehurst/pycaret

An open-source, low-code machine learning library in Python

Terrance-Whitehurst/Aerial-Cactus-Classification-Keras

In this project I take the satelite images taken for autonomous feild detection to classify cactuses within the feild. I follow the research paper experiment and use the LeNet-5 Convolutional Neural Network architecture. I use data augmentation to get the model to a 95% accuracy.

Terrance-Whitehurst/10-Monkey-Species-Classification-W-Keras-Transfer-Learning

In this project I used the keras deep learning library with kaggle's free gpu's and with a pre-trained model(resnet50) to do multi-classification on 10 Monkey Species deep learning image dataset from kaggle. I also use transfer learning and data augmentation along with dropout to fight over fitting. I also freeze the first three layers of the pretrained resnet50 to use the richer representation learned from the network in the later layers. My Model was able to reach an accuracy of 94%

Terrance-Whitehurst/amazon-forecast-samples

Notebooks and examples on how to onboard and use various features of Amazon Forecast.

Terrance-Whitehurst/fastapi-yolov5

Terrance-Whitehurst/FastImageClassification

A Step-By-Step tutorial to build and deploy an image classification API

Terrance-Whitehurst/Grigor-Dimitrov-Object-Detection-imageAI

In this project I have used the imageAI library along with YoloV3 for object recognition on Grigor Dimitrov. I am a professional tennis player so my motivation for this project was to use the imageAI library on my favorite professional players.

Terrance-Whitehurst/Keras-Pneumonia-Detection-App

In this project I use Keras along with x-ray photos from the kaggle dataset in order to create an accurate model to classify pneumonia via chest xray images. I also create a web application and deploy it with flask and docker.

Terrance-Whitehurst/sam-cli-install

Terrance-Whitehurst/Wild-Animal-Multi-Classification-Keras

In this project I use Keras and TensorFlow to do multi classification for wild animal images. I use Kaggles free GPUs and Datasets in this competion. I use the Keras deep learning library along with data augmentation.

Terrance-Whitehurst/yolov5-fastapi

Machine Learning Model API using YOLOv5 with FAST API