A fictional startup called Pictr provides a social platforn where users can upload and share pictures of nature and wildlife.
The product team has identified that users that add captions to their pictures get more engagement. The insight they got is that most users aren’t necessarily confident in coming up with descriptive captions for their images.
You’ve been tasked with coming up with a model that can suggest captions based on the image the users uploaded.
Build a convolutional neural network (CNN) model to analyse and extract features from an image, and generate a sentence, in English, that describes the image.
Feel free to come up with your own solution!