Nabarun Barua's repositories
ATCC_Yolov5
ATCC Yolov5
Meta_Learning
Meta Learning the Huggingface way
CML_with_DVC_on_Transformer_NLP
Continous Machine Learning Pipline Implementation with DVC on Transformers with WANDB
onnx_model_size_compression
Just a simple pythonic way of reducing the onnx converted model. This implementation is based on a tip by the Team ONNX .
Vehicle-Collision-Detection
Vehicle Collision Detection
AIOps-mlflow-pytorch-multistep-workflow
AIOps-mlflow-pytorch-multistep-workflow
awesome-mlops
A curated list of references for MLOps
BasicSR
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, etc. Also support StyleGAN2, DFDNet.
bert-extractive-summarizer
Easy to use extractive text summarization with BERT
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
GPU-Docker-Deployment-Text-Summarization
Text Summarization using Transformer on GPU Docker Deployment
Hybrid-Compute-Python-Manage-VM
Getting Started with Compute - Manage Virtual Machines using Python on Azure Stack hybrid cloud https://docs.microsoft.com/en-us/python/azure
kernl
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
Kubernetes-Setup-for-Production
Some Guides to setup Kubernetes for Production Environment
nabarunbaruaAIML
About Nabarun Barua
NLP_CML_Deployment_Pipeline_On_Kubernetes
This is a continuation to the repository (https://github.com/nabarunbaruaAIML/CML_with_DVC_on_Transformer_NLP) with the deployment pipeline on EC2/Azure using Docker and Kubernetes.
OCR_From_Image
OCR From Images
olm-datasets
Pipeline for pulling and processing online language model pretraining data from the web
project-template-with-DVC
Project-Template-with-DVC
Streamlit_DataScience_Apps
Streamlit Data Science and ML Apps in Python
The-Complete-FAANG-Preparation
This repository contains all the DSA (Data-Structures, Algorithms, 450 DSA by Love Babbar Bhaiya, FAANG Questions), Technical Subjects (OS + DBMS + SQL + CN + OOPs) Theory+Questions, FAANG Interview questions, and Miscellaneous Stuff (Programming MCQs, Puzzles, Aptitude, Reasoning). The Programming languages used for demonstration are C++, Python, and Java.
trl
Train transformer language models with reinforcement learning.
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)