This repo is a collection of simple image classifiers using neural networks.
- Python v3.x
- Tensorflow v2.x or Tensorflow-GPU v2.x
- PyTorch v1.5.x
- OpenCV v4.3.x
- Numpy
- Matplotlib
Tensorflow:
pip install tensorflow
NOTE: If your system has a CUDA compatible GPU (Nvidia cards):
pip install tensorflow-gpu
The CIFAR dataset is an enormous collection of images belonging to ten diferent classes.
I have used Tensorflow and Keras here to create the neural networks. There are three sections to the project:
- A simple Neural Network that produces the least accurate results. This serves as teh benchmark for the rest of the project.
- A simple Convolutional Neural Network.
- Hyperparameter tuned CNN which produces the best accuracy.
The program aims to distinguish between dogs and cats in an image.