/Image-ClassificationProject

Image classification is an interesting deep learning field. In this project, I built a neural network from scratch to calssify cat vs non-cat dataset from scratch and then convolution neural network on a CIFAR-10 dataset using Keras sequential, tf and Tkinter.

Primary LanguageJupyter Notebook

Image-ClassificationProject

Image classification is a amazing deep learning project that I've worked on.

  • In this project, We build a convolution neural network on a CIFAR-10 dataset.

  • To begin with, we did some exploration in our dataset, and then trained our deep neural network using python and keras.

  • Finally we built a GUI in which images can be uploaded to and can be used for prediction.

Important Dependencies

tkinter is required for GUI creation and launching the application - !conda install -c anaconda tk

About the Dataset

CIFAR-10 is a very popular computer vision dataset. This dataset is well studied in many types of deep learning research for object recognition.

This dataset consists of 60,000 images divided into 10 target classes, with each category containing 6000 images of shape 3232. This dataset contains images of low resolution (3232), which allows researchers to try new algorithms. The 10 different classes of this dataset are:

  • Airplane
  • Car
  • Bird
  • Cat
  • Deer
  • Dog
  • Frog
  • Horse
  • Ship
  • Truck

CIFAR-10 dataset is already available in the datasets module of Keras. We do not need to download it; we can directly import it from keras.datasets.

Starting Project

  • The pretrained model must be loaded in GUI CIFAR10 Dataset.py for its working.

    • model_2o3.h5

  • run main_run.py in a python environment with model_2o3.h5 and all the dependencies setup.

That's all folks! We're good to go!