99.7% accuracy solution for Dogs vs Cats Redux Kaggle competition

QuickCNN is high-level library written in Python, and backed by the Keras, TensorFlow, and Scikit-learn libraries. It was developed to exercise faster experimentation with Convolutional Neural Networks(CNN). Majorly, it is intended to use the Google-Colaboratory to quickly play with the ConvNet architectures. It also allow to train on your local…

Query by example spoken term detection using bottleneck features and a convolutional neural network

An IPython notebook demonstrating the process of Transfer Learning using pre-trained Convolutional Neural Networks with Keras on the popular CIFAR-10 Image Classification dataset.

Simple classifier in your browser to predict dog breeds using Flask and Keras/Tensorflow.

Simple, yet fast, Python scripts to read Kaldi NNet3 models and compute bottleneck features

Given an image of a dog, our algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.

Part 1 of Undergraduate Thesis Project @ UniBo: implementation of a convolutional neural network to recognize pills from photos, based on VGG16, using transfer learning, fine tuning

Image captioning is the task of generating a caption for an image. We explore new models and analyse their performances. We will be using Tensorflow in this project.

Transfer Learning for Dentist diagnosis aid , an intelligent healthcare application for train/validate/test/predict.

Image classifier with Jax and Elegy. Using as an input any net to get the bottleneck features.

Deep Learning Nanodegree Project : Given an image of a dog, the algorithm will identify an estimate of the canine’s breed. If supplied with an image of a human, the code will identify the resembling dog breed.

Concept Bottleneck Models

A Keras implementation of YOLOv3 (Tensorflow backend)

dog breed classifier based on convnets, using catdog and lfw datasets.

An autoencoder that improves quality of a picture

Built an algorithm to identify canine breed given an image of a dog. If given image of a human, the algorithm identifies the dog breed that is most resembling.