Name: Mahesh Khadatare
Type: User
Bio: Aiming to apply professional experience of scientific research & software development using image processing, machine learning & computer vision, in the product
Location: Santa Clara, CA
Mahesh Khadatare's Projects
Caffe: a fast open framework for deep learning.
CBIR with wavelet transform and feedback relevance using matlab
Example pybind11 module built with a CMake-based build system
Emotiv SDK Community Edition
Basic Image Processing Operations
GPU-accelerated LIBSVM is a modification of the original LIBSVM that exploits the CUDA framework to significantly reduce processing time while producing identical results. The functionality and interface of LIBSVM remains the same. The modifications were done in the kernel computation, that is now performed using the GPU.
Automatically exported from code.google.com/p/cuda-convnet2
A CUDA implementation of SIFT for NVidia GPUs (2.6 ms on a GTX 1060)
A CUDNN minimal deep learning training code sample using LeNet.
Convolutional Neural Networks
Real-time dense visual SLAM system
Facial Emotion Recognition
Face Recognition Neural Network MATLAB
Hand Gesture Recognition using Neural Network in MATLAB
Human Activity Recognition - Predicting weight-lifting styles
Image transformation, compression, and decompression codecs. Forked from https://pypi.org/project/imagecodecs
C# based Image Segmentation for Tiff Images
IRIS Gaze Tracking using Neural Network in MATLAB
MATLAB based Machine Learning assignments
Models and examples built with TensorFlow
The MongoDB Database
Automatically exported from code.google.com/p/nupar-bench
Open-source implementation of JPEG2000 Part-15 (or JPH or HTJ2K)
Compute the exact Euclidean Distance Transform and Voronoi Diagram for 2D and 3D binary images using the GPU.
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
CUDA Code for SAR Image Processing
Stationary Wavelet Transform (SWT) in C# matching with MATLAB SWT Time Invariant
The Swift Programming Language
Computation using data flow graphs for scalable machine learning