scumechanics's repositories
Bearing-Anomaly-Detection-using-Machine-Learning
Showcase how machine learning can help operators monitor equipment conditions through correctly analyzing measurement data collected from many sensors.
corrosion-monitoring-using-UNET
In order to avoid regulatory violations, downtime, or fatal disasters, industrial assets must be maintained in a timely manner. One of the biggest factors for timely maintenance is corrosion of the assets. Corrosion causes generation of irregular surface that looks bad in appearance and can produce serious problems. To avoid corrosion problems, timely maintenance must be scheduled well in advance. For this, images-based corrosion detection can be a useful tool with respect to real time corrosion tests. In this work, images-based corrosion detection is performed using Deep-learning UNET-8layer architecture. More than 400 images of corrosion data with their binary ground truth or labels are trained to analyze and classify the corroded region in the images. After training, the model is tested, and it is found that the prediction over corroded part of original image data can be done with the model with binary accuracy of 95.28% and validation binary accuracy of 96.87%.
Deep-Learning-High-Entropy-Alloys
High Entropy Alloys (HEAs) are multi-chemical elements alloys with exceptional physical properties. HEAs have sparked the interest in engineering applications such as energy storage, catalysis and bio/plasmonic imaging. The understanding of the structural of composition of HEAs is paramount for the appropriate tuning of their properties. Scanning Transmission Electron Microscopy (STEM) is typically used to acquire images of various materials at the atomic scale resolution. including HEAs. In this repository it is demonstrated how computer vision analysis based on Deep Learning (DL) could be used to extract structural information from STEM images of HEAs. In particular a Fully Convolutional Neural Network (FCN) is trained to recognize the number of atoms of different chemical species in the atomic columns of HEA (i.e., column heights CHs) through semantic segmentation of simulated and experimental STEM images. As a benchmark case, equiatomic PtNiPdCoFe HEAs are considered. This project represent a first attempt for the identification of chemical species in 3D materials. Thus, in addition to the estimation of the structural properties of HEAs, this work establish an advancement of DL applied to microscopy image which could be useful for a broad area of nano-science applications.
GPR-Object-Detection
This repository contains code to train object detection models like FRCNN for identifying objects in Ground Penetrating Radar scans. It also contains code to generate fake data using GANs.
Image_segmentation_with_U-net
Image segmentation using vanilla Unets with batch normalization.
Rainfall_predictor
Use rainfall data predict landslide occur or not
similarity_measures
Quantify the difference between two arbitrary curves in space
ThymeBoost
Forecasting with Gradient Boosted Time Series Decomposition
android-demo-app
PyTorch android examples of usage in applications
google-research
Google Research
GroundingDINO
The official implementation of "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Impeller-stress-prediction
Calculate stress and natural frequency of centrifugal fan's impeller
LLDE
This is the code repo of our ICIP2023 work that proposes a novel approach to low-light image enhancement using the diffusion model (LLDE).
notebooks
Set of Jupyter Notebooks linked to Roboflow Blogpost and used in our YouTube videos.
pykan
Kolmogorov Arnold Networks
Research-on-Solving-Partial-Differential-Equations-of-Solid-Mechanics-Based-on-PINN
This is the code of my master thesis.
Rheology_PINNs
Repository holding the physics informed machine learning codes to characterize unknown rheology of thermal greases
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
vibrations-of-mindlin-plates
A collection of Python codes to find the natural frequencies of Reissner-Mindlin (thick) plates.
Visualize-Yolo-annotations
A simple tool that will help visualize bounding boxes in darknet/yolo format
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything and other awesome models.
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > iOS
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors