You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A Deep Learning Humerus Bone Fracture Detection Model which classifies a broken humerus bone X-ray image from a normal X-ray image with no fracture using Back Propagation, Regularization, Convolutional Neural Networks (CNN), Auto-Encoders (AE) and Transfer Learning.
Deep neural network model combining audio signal processing and pre-trained audio CNN achieved 90.1% adjusted accuracy (27.6% improvement) for classifying audio recording environment.
Convolutional Neural Networks capable of classifying Normal vs. Pneumonia frontal chest radiograph (a set of 32 images in 8 seconds) using Transfer Learning with ResNet50
Transfer Learning using InceptionResNetV2 to the Augmented Neuroimage Data for the Autism Spectrum Disorder (ASD) Classification, using ABIDE I dataset.
An end-to-end multi-class image classification system(web app) that classifies 101 classes of food. I'll be implementing the popular CNN architecture while utilizing the full power of transfer learning to extract features and fine-tune layers. I'll also build an interactive UI using react-js and deploy the system.
Constructed an algorithm that works on user supplied image. If a dog is detected, it estimates the breed of the dog, Trained using Transfer learning with CNN.
Given an image, detects whether there is a human face or a dog in it. In case it is a dog, the algorithm classifies the breed of the dog. Deep Learning Nanodegree project.
It is a autonomous robot equipped with sensors and cameras with deep learning algorithms to monitor and maintain crop health and act as an aid to farmers and huge estate or nursery owners
A dog breed identification model specializing in precise classification from images, leveraging advanced transfer learning techniques with TensorFlow, Keras, and GPU acceleration
The provided code demonstrates transfer learning by adapting a model trained using synthetic data to classify circles, squares, and triangles to classify new shapes like stars and pentagons. By fine-tuning a pre-trained model originally designed for a different task, the repository showcases how to efficiently adapt a model to a new domain.