What are the different Pre-trained models available in keras?

Ans: It is not always possible to build a model from scratch due to lack of time or any other reasons. This is the time where Pre trained models are useful. A pre-trained model is a model that was trained on a large standard dataset to solve a problem which is similar to the one that we have to solve.

The different Pre trained models used in keras for Computer vision applications are:

Mask RCNN – developed for the purpose of Object instance Segmentation


YOLOv2 – Object Detection Framework for Deep Learning Applications

Mobile net – It is architecture designed for Mobile devices

VGG Face Model – It is a dataset that contains 2,622 unique identities with more than two million faces

3D Face reconstruction from a single Image – This model works in order to reconstruct the facial features into a 3-dimensional space.

Semantic Image Segmentation – Deeplabv3 – It finds the outlines of objects and thus places restrictions on the accuracy requirements

Robot Surgery Segmentation – This model attempts to address the problem of image segmentation of surgical instruments in a robot-assisted surgery scenario.

Image Captioning – It converts a given input image into a short and meaningful description.