In this blog, the problem of improper captioning to images has been studied and adding attention layers to the model has been implemented to solve it. The LSTM, which is the specialized RNN is used for the sequence of words as captions while a CNN model using InceptionV3 setting the'imagenet' weights. RNN models are used to work better with the words and CNN models work better with the images. The two are merged followed by addition of attention layers. Thus, we have defined a deep learning model that combines the CNN features with RNN with the help of an attention mechanism, thereby developing a more accurate model.

So, this is the second Computer Vision project that I have implemented. If you haven't checked out the first project that is the Facial Keypoint Detection's blog already, I'll leave a link here. Now, You might think what in the world is image captioning? and How can it be done automatically? Okay! so, in order to explain that to you in simple "gestures", let me introduce, the almighty Pikotaro. I'll take it from here.

Deep Learning is a very rampant field right now – with so many applications coming out day by day. And the best way to get deeper into Deep Learning is to get hands-on with it. Take up as much projects as you can, and try to do them on your own. This would help you grasp the topics in more depth and assist you to become a better Deep Learning practitioner. In this article, we will take a look at an interesting multi modal topic where we will combine both image and text processing to build a useful Deep Learning application, aka Image Captioning.