Classification of Image with Convolutional Neural Network and TensorFlow on CIFAR-10 Dataset

Convolution Neural Networks (CNNs), one type of deep learning model, that have been effective in classification of image and for tasks of object detection have been utilized. In this paper, a model has been proposed to classify images effectively and quickly by using CIFAR-10 dataset. Further, TensorFlow with Google Colab has been utilized for the model's building. The model is trained by providing training dataset images of 32 × 32 size to determine the parameters that best fit the data. The model is designed with limited number of CNN layers and learning rate of 0.001. No dropout technique has been used in our model. The results show that the model gives test accuracy of 98.93% and validation accuracy of 81.91%. This work finds its application in surveillance and Internet of things.