skumarlabs
Data Scientist | Neural networks are my main area of interest. I work with Python, TensorFlow, Numpy, Pandas, Matplotlib, and Linux.
Bengaluru
Pinned Repositories
awesome-deep-vision
A curated list of deep learning resources for computer vision
skumarlabs's Repositories
skumarlabs/awesome-deep-vision
A curated list of deep learning resources for computer vision
skumarlabs/Blender-FLIP-Fluids
FLIP Fluids is a powerful liquid simulation plugin that gives you the ability to create high quality fluid effects all within Blender, the free and open source 3D creation suite.
skumarlabs/cpp
C++ in action
skumarlabs/data_visualisation
skumarlabs/DataflowTemplates
Google-provided Cloud Dataflow template pipelines for solving simple in-Cloud data tasks
skumarlabs/deep_learning
skumarlabs/hindinlp
skumarlabs/jagran-scrapper
skumarlabs/leetcode-submissions
Contains my submissions for LeetCode (https://leetcode.com)
skumarlabs/LLV
CLI tool for recording or replaying Epic Games' live link face capture frames.
skumarlabs/machine_learning
skumarlabs/MB-Lab
MB-Lab is a character creation tool for Blender 2.80+, based off ManuelBastioniLAB
skumarlabs/ML-From-Scratch
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
skumarlabs/ml-resources
skumarlabs/MocapNET
We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
skumarlabs/nlp
skumarlabs/parallel-programming
Everything at once
skumarlabs/quickstart-js
Firebase Quickstart Samples for Web
skumarlabs/Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
skumarlabs/Review_Miner
A project to build corpus from Play Store App reviews
skumarlabs/safari-video-downloader
Download videos from Safari Books Online at ease.
skumarlabs/SDV
Synthetic Data Generation for tabular, relational and time series data.
skumarlabs/skumarlabs.github.io
skumarlabs/snapshots
This repo contains cheatsheets for reference purposes. Credit goes to respective authors.
skumarlabs/sql_queries
skumarlabs/TamingPython
Getting a fang of Python!
skumarlabs/tensorflow-compiled-from-source
Contains Tensorflow package compiled from source to use AVX, SSE4.1 and SSE4.2 instructions available on CPU
skumarlabs/tensorflow-vgg
VGG19 and VGG16 on Tensorflow
skumarlabs/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
skumarlabs/YASP
Yet Another Speech Parser (YASP), uses pocketsphinx to parse speech and output a JSON file describing the timing