Image Classifiers - Various Concepts

Visit the App

Image Content Classification with Tensorflow

Application of Google-made image content classifier built with Tensorflow. Training this kind of model in home conditions would took an eternity, that's why it was downloaded from official website. Model accuracy is amazing.

(Heroku-hosted app works only with small photos with white background due to limited memory, works perfect on local hosts)

Cat vs Dog Classifier with Keras & SK

Image classifier trained to distinct between cats and dogs images. Convolutional Neural Network was built with Keras & Tensorflow(GPU).

CONVOLUTIONAL NEURAL NETWORK CHARACTERISTICS

1. Image Input Shape - 128,128,3, activation - relu
2. Three additional Convolutional Layers (batch size - respectively 32,64,128, dropout rate - 0.25,0.2,0.3)
3. Units in hidden layer - 128
4. Compiler - optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy']
5. Acc - 89% Loss - 25% (approx 30min/epoch on GPU)
6. CNN Code Location: deep_learning/ConvolutionalNeuralNetwork.py

Digit Recognition with Keras & Ajax.js

Hand-Written Digit Recognition based on MNIST Dataset. Convolutional Neural Network was built with Keras & Tensorflow(GPU). Heroku-hosted web application was built with Flask framework, Ajax & FileSaver.

MNIST Dataset

Top 10 Twitter Trends

Home Value Estimator - Ireland

Artificial Sommelier

Blockchain Simulation

Ireland Geocoder

To UTF-8

PDF Extractor