Atul Sahay's repositories
Understanding-The-Deepfakes-using-Keras
Coursera hand held project to understand the deepfakes using keras (DCGAN)
awesome-interview-questions
:octocat: A curated awesome list of lists of interview questions. Feel free to contribute! :mortar_board:
Banck-Cheque-OCR-and-MICR-Detection
Bank Cheque OCR using Pytesseract and MICR detection using contour detection and pattern recognition
awesome-low-level-design
This repository contains low level design resources to improve coding skills and prepare for interviews.
Data-Extractor
Deep Neural Network to automatically extract the particular field of data from the network
Decision_tree
A Step by Step Gradient Boosting Decision Tree Example
DeepLearningFlappyBird
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
Grammar-Correction
Grammar Correction Module using seq2seq model with the attentive decoder
HandWritten-Digit-Recognition-GUI
GUI based handwritten Digit Recognition
Parse-Tree-Visualisation-Helping-Files-For-RLSPINN-Model-
How to convert the action vectors into a Parse Tree and other helping functions for the tree metrics
PDF-QnA
Problem Statement Create an AI agent that leverages the capabilities of a large language model. This agent should be able to extract answers based on the content of a large PDF document and post the results on Slack.
PiazzaVirtualAssistant
Targeting the Piazza platform to automate the process of answering of queries.
PyTorch-Programming-CNN-FASHION_MNIST
CNN network implemented using the Pytorch Framework from the scratch for classifying the Fashion - MNIST data set, activation layer of RELU is used for the nolinearity and cross entropy for the final backward error propagation, for better visualisation Tensorboard is also incorporated which helped in fine tuning of the hyper params
scikit-learn-tips
:robot::zap: Daily scikit-learn tips
supervision
We write your reusable computer vision tools. 💜
Titanic_survival_learning
Learning survival stats on titanic dataset
TopicClassificationChallenge
Long english text passages are given, a genuine topic is needed to be assigned to the particular text passage. After cleaning the dataset, features were learnt using thidf approach, Linear SVC is used to get the final prediction
TransformerTTS
🤖💬 Implementation of a Transformer based neural network for text to speech.