Name Entity Recognition
Built a NER system with custom built neural model.
In building neural model Embedding vector, Bi-LSTM, CNN have been used.
Dataset used is called CoNLL2003++.
Python
ChatBot using Reformer
Used Reformer known as efficient Transformer to generate
dialogue between two bots using Trax. Dataset used in this project is called
MultiWoz dataset.
Python
Image caption generator using CNN-LSTM
An image caption generator project using architecture.
The dataset which is used in this project is the COCO dataset. CNN is used as an encoder to extract features from a
given batch of images using pre-trained ResNet-50 architecture and give input to the LSTM layer to generate an image
caption. LSTM used as a decoder to generate a caption.
Python
Disaster Response Pipeline Project
A data set containing real messages that were sent during
disaster events is used in this project. A Machine Learning pipeline is created to categorize these events
so that people can send messages to an appropriate disaster relief agency.
Python
Facial Keypoint detection
Different computer vision techniques and deep learning
architectures are used to build a facial keypoint detection system. Facial keypoints include points around the
eyes, nose, and mouth on a face and are used in many applications. These applications include
tracking, facial pose recognition, facial filters, and emotion recognition.
Python
Libraries, Frameworks & Tools
Tensorflow
PyTorch
For more projects visit the following github link!