Name: Souradeep Ghosh
Type: User
Company: CNS at Indiana University
Bio: Creative, dynamic, and efficient Computer Science Student who excels in programming languages, web development and is a fanatic of Databases, and AI/ML.
Location: Bloomington
Blog: https://sourolio10.github.io/
Souradeep Ghosh's Projects
Comparing and flagging the CT-IDs and labels that don't align with ASCTB and vice-versa for next-step action items.
HuBMAP CCF Homepage
Face anti-spoofing using MobileNet
Code for 3rd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019,model only 0.35M!!! 1.88ms(CPU)
Proposal for generative travel chatbot using seq2seq model research paper
Project-Genie for Morgan Stanley Code-to-Give hackathon
Models and examples built with TensorFlow
In recent years, deep learning techniques are achieving state-of-the-art results for object detection, such as on standard benchmark datasets and in computer vision competitions. Notable is the “You Only Look Once,” or YOLO, family of Convolutional Neural Networks that achieve near state-of-the-art results with a single end-to-end model that can perform object detection in real-time. The approach involves a single deep convolutional neural network (originally a version of GoogLeNet, later updated and called DarkNet based on VGG) that splits the input into a grid of cells and each cell directly predicts a bounding box and object classification. The result is a large number of candidate bounding boxes that are consolidated into a final prediction by a post-processing step. There are three main variations of the approach, at the time of writing; they are YOLOv1, YOLOv2, and YOLOv3. The first version proposed the general architecture, whereas the second version refined the design and made use of predefined anchor boxes to improve bounding box proposal, and version three further refined the model architecture and training process.
Tool for mapping (uncontrolled) terms to ontology terms
Time-series forecasts of stock data
Word Wise Webapp