This project is about defining and training a convolutional neural network to perform facial keypoint detection, and using computer vision techniques to transform images of faces.
a deep learning model uses CNN Encoder and a LSTM Decoder to generate captions for a given image.
This project is an implementation of SLAM (Simultaneous Localization and Mapping) for a 2 dimensional world. We can create a map of the environment of the robot through the combination of motion and sensor data that was gathered over time.