Object classification and recognition are popular in computer vision. In this project, our objective is to carry out object recognition by using partially annotated dataset. The dataset provides the information about what objects are present in the image but not where they are present. We have used a Convolutional Neural Network(CNN) based architecture to perform this task. We conclude the report by listing the various advantages and disadvantages of this method. The objective of this project is to classify the given pet as dog or cat from the given images using the CNN.

The dataset of images of cats and dogs is available at this URL https://www.kaggle.com/vaishnavkapil/feature-detection-cnn/data

This object recognition program is written in latest Tensorflow 2.0.