Objective: - Object Detection with OpenImages Open Images is a new dataset first released in 2016 that contains ~9 million images – which is fewer than ImageNet. What makes it stand out is that these images are mostly of complex scenes that span thousands of classes of objects. Moreover, ~2 million of these images are hand-annotated with bounding boxes making Open Images by far the largest existing dataset with object location annotations. In this subset of images, there are ~15.4 million bounding boxes of 600 classes of object. Dataset Link: - Dataset is pretty big. SO we do not want to train it completely. So please extract any 10 classes images and annotations that you like. Then train it.
Link :- https://github.com/cvdfoundation/open-images-dataset
Task: - Create a Web Application using Flask. Use the end user should be able to upload an image and get results with the prediction score. Use any CNN architecture launched after 2017.
Deployment: - Any Free Platform(Try to look out for free options.)
- Step1: Downloading the dataset ( https://github.com/cvdfoundation/open-images-dataset )
- step2: Download the annotation (https://storage.googleapis.com/openimages/web/download_v4.html)