Sourish Dey's repositories
car-damage-detection-using-CNN
Automated car damage detection using Instance Segmentation(Mask R-CNN)
Neural-Style-Transfer-on-video-data
Neural Style Transfer-Real Time Video Augmentation
hybrid_recommendation_engine
Mix of MF and CF(Item similarity) based approach
Photo-Caption-Generator
Caption generation is a challenging artificial intelligence problem where a textual description must be generated for a given photograph. It requires both methods from computer vision to understand the content of the image and a language model from the field of natural language processing to turn the understanding of the image into words in the right order. Recently, deep learning methods have achieved state-of-the-art results on examples of this problem. Deep learning methods have demonstrated state-of-the-art results on caption generation problems. What is most impressive about these methods is a single end-to-end model can be defined to predict a caption, given a photo, instead of requiring sophisticated data preparation or a pipeline of specifically designed models. In this tutorial, you will discover how to develop a photo captioning deep learning model from scratch. After completing this tutorial, you will know: How to prepare photo and text data for training a deep learning model. How to design and train a deep learning caption generation model. How to evaluate a train caption generation model and use it to caption entirely new photographs.
Video-content-analysis
Deep Learning approach to Calculate the Screen Time of Actors in any Video (with Python codes)
Real-Time-Fraud-Detection
This solution contains Real Time Fraud Detection with jupyter notebook , python scripts, table creation in postgresql(PG) database,subsequent loading with data,data retrieving, deep dive in the data provided for Revolut challenge to do data preparation,feature engineering, exploratory analysis and build ML classification model to predict propensity to fraud in user level and action against each user. Throughout this notebook we will mainly do following task(Not always in the order)
nlp_classification
This jupyter notebook contains deep dive in the service description data to do data discovery, exploratory analysis and build multiclass classifier to predict correct serviceid category:¶
NLP_serviceID
contains deep dive in the to do data discovery, exploratory analysis and build multiclass classifier to predict correct serviceid category
TF2_callbacks-
TensorFlow 2.0 Custom Callback in Practice:An Utility for Data Products
AmazonSageMakerCourse
SageMaker Course Material
Collaborative-Filtering-ALS
ALS method collaborative filtering-Alternating Least Squares (ALS) is a the model we’ll use to fit our data and find similarities. But before we dive into how it works we should look at some of the basics of matrix factorization which is what we aim to use ALS to accomplish.
deploying-machine-learning-models
Example Repo for the Udemy Course "Deployment of Machine Learning Models"
bolt_ride_value_prediction
End end implementation including containerized deployment
deploy_MLModel
ML model
dockerized-model-training
model training and inference in docker container
git-commands-you-should-know-3021325
8 Git Commands You Should Know
github-actions-course-resources
Resources (code, slides) for our GitHub Actions course (https://acad.link/gh-actions)
mlops-on-gcp
gcp-mlops
mmm_stan
Python/STAN Implementation of Multiplicative Marketing Mix Model, with deep dive into Adstock (carry-over effect), ROAS, and mROAS
neptune-action-cIcd
Continuous Integration with GitHub Actions and Neptune
nlp_api_cicd_docker
Complete demonstration of creating NLP API with CICD workflow to build and push image to Docker registry
Recommender_system_via_deep_RL
The implemetation of Deep Reinforcement Learning based Recommender System from the paper Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling by Liu et al.
simulation-of-sales
A Monte-Carlo simulation of real world sales from derived estimated demand using Numerical Methods.
Time-Series-forecasting-Bayesian-and-Transformer
Time series forecasting for new items for fashion retailer
ubuntu-wsl2-systemd-script
Script to enable systemd support on current Ubuntu WSL2 images [Unsupported, no longer updated]
Verve-Group_Case-Study
Verve Group Data Science Case Study