Image Tagging software automatically identifies and describes objects within images. These objects include locations,ambience, people, food. Image recognition is developed through numerous training steps, which give the software photos and teach it to understand patterns using machine learning.
Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task.It is a popular approach in deep learning where pre-trained models are used as the starting point on computer vision and natural language processing tasks given the vast compute and time resources required to develop neural network models on these problems and from the huge jumps in skill that they provide on related problems.I have used Resnet50 pre-trained model which is trained on huge amount of data from imagenet.
I have used around 30 images each for classes food,people and ambience collected from various sources such as google images and then I fine tuned the model by using the new dataset to act upon new classes. Everything you need to do recreate this project is on the jupyter notebook.