scumechanics

Adventures-in-TensorFlow-Lite

This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

android_tflite

GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer

AndroidML-1-Concrete-Strength-Predictor-App

Anomaly_Detection

awesome-remote-sensing-change-detection

List of datasets, codes, and contests related to remote sensing change detection

awesome-semantic-segmentation

:metal: awesome-semantic-segmentation

Landslide-Susceptibility-Prediction-Using-Machine-Learning-Algorithms

Landslide Susceptibility Prediction and Identification of Most Significant Factors that best describe an area is susceptible to Landslides or not based on Explainable Artificial Intelligence to solve the challenging BlackBox problem of state art Artificial Intelligence based methods.

Landslide_detection_using_Mask_RCNN_new

ML_Projrct_Concrete_Strength_Prediction

Perform These algorithms: - Linear Regression - Lasso Regression - Ridge Regression - Decision Tree Regressor - Random Forest Regressor - KNN Regressor - SVM Regressor AND Pick each of the algorithm and perform These steps: o Split your data between train and test steps. Build your model List down the evaluation metrics you would use to evaluate the performance of the model? Evaluate the model on training data o Predict the response variables for the test data How are the two scores? Are they significantly different? Are they the same? Is the test score better than training score?

XGB-SHAP-concrete-interface-shear-strength

Accurate prediction of the shear strength of the interface between old and new concrete (cold joints) is essential for the design or assessment of precast and retrofitted concrete structures. The XGBoost and Shapley Additive exPlanations technique were used to develop an explainable ML-model for interface shear strength prediction of the cold joints. This package contains the code of the model and the collected database.

scumechanics/PINN-elastodynamics

physics-informed neural network for elastodynamics problem

scumechanics/Neural-Structural-Optimization-Study

scumechanics/MMUU-Net

MMUU-Net：A Robust and Effective Network for Farmland Segmentation of Satellite Imagery

scumechanics/Crack-Detection-System-Based-on-Drone-Vision

Crack-Detection-System-Based-on-Drone-Vision

scumechanics/Finite_Element_Method_Li-ion_battery

Discharge of Li-ion using FEA

scumechanics/bayesgrad

BayesGrad: Explaining Predictions of Graph Convolutional Networks

scumechanics/Crack_Detection_MASK-RCNN

Cracks in concrete structures create lots of problems especially in old buildings; timely identification and curing the cracks which has occurred on concrete can help in increasing the life time of the buildings. We have develop a system to identify and spot crack(s) in civil structures.

scumechanics/UNOSAT-AI-Based-Rapid-Mapping-Service

This GitHub repository contains the machine learning models described in Edoardo Nemnni, Joseph Bullock, Samir Belabbes, Lars Bromley Fully Convolutional Neural Network for Rapid Flood Segmentation in Synthetic Aperture Radar Imagery.

scumechanics/Crack-Semantic-Segmentation

Real time crack segmentation using PyTorch, OpenCV and ONNX runtime

scumechanics/Instance-Segmentation-using-Mask-RCNN-with-different-backbones-on-Crack-Data

Instance Segmentation using Mask-RCNN with different backbones (Resnet-101 & MobileNet) on Crack Data and also created a Rest-API for it using Flask.

scumechanics/CCAs-HEAs-machine-learning-model-using-TensorFlow

Machine learning model for complex concentrated alloys/high entropy alloys using TensorFlow

scumechanics/Detectron2toMobile

scumechanics/Surface_Crack_Segmentation

detect surface crack and segment it by my own rect

scumechanics/LandSlide_Detection_Faster-RCNN

利用faster-rcnn目标检测网络实现滑坡的提取

scumechanics/how_to_convert_h5_model_to_tflite

How to convert h5 model to tflite model

scumechanics/Crack-Segmentation-1

scumechanics/Semantic-Segmentation-Severstal

Semantic Image Segmentation - Severstal Steel Defect Detection Kaggle

scumechanics/drama

Main component extraction for outlier detection

scumechanics/Surface-Defect-Detection

Segmentation-Based Deep-Learning Approach for Surface-Defect Detection

scumechanics/satellite-Image-Semantic-Segmentation-Unet-Tensorflow-keras

Collection of different Unet Variant suchas VggUnet, ResUnet, DenseUnet, Unet. AttUnet, MobileNetUnet, NestedUNet, R2AttUNet, R2UNet, SEUnet, scSEUnet, Unet_Xception_ResNetBlock

scumechanics/ssl_detection

Semi-supervised learning for object detection

scumechanics/Predicting_Concrete_Compressive_Strength

How would you predict the compressive strength of concrete as a function of its constituent materials and curing time? In this portfolio project, I optimize a model for determining concrete compressive strength using a deep neural network in Tensorflow 2.0 and compare its performance to linear models.

scumechanics/graph2nn

code for paper "Graph Structure of Neural Networks"

scumechanics/Change-Detection-in-Remote-Sensing-Images

scumechanics/ESPNet

ESPNet is an efficient scalable scene segmentation model which uses Pyramid Pooling Module (PPM) as a global contextual prior for feature extraction.

scumechanics/Change-Point-Detection-Model

Change Point Detection on Wind Turbine Gearbox Sensors

scumechanics/Steel-Defect-Detection-1

identify steel defects using CNN framework. novel system for identifying cracks , defect on steel surface .

scumechanics/Concrete-Crack-Segmentation

scumechanics/BayesianOnlineChangepointDetection

scumechanics/Revealing-Ferroelectric-Switching-Character-Using-Deep-Recurrent-Neural-Networks

The ability to manipulate domains and domain walls underpins function in a range of next-generation applications of ferroelectrics. While there have been demonstrations of controlled nanoscale manipulation of domain structures to drive emergent properties, such approaches lack an internal feedback loop required for automation. Here, using a deep sequence-to-sequence autoencoder we automate the extraction of features of nanoscale ferroelectric switching from multichannel hyperspectral band-excitation piezoresponse force microscopy of tensile-strained PbZr0.2Ti0.8O3 with a hierarchical domain structure. Using this approach, we identify characteristic behavior in the piezoresponse and cantilever resonance hysteresis loops, which allows for the classification and quantification of nanoscale-switching mechanisms. Specifically, we are able to identify elastic hardening events which are associated with the nucleation and growth of charged domain walls. This work demonstrates the efficacy of unsupervised neural networks in learning features of the physical response of a material from nanoscale multichannel hyperspectral imagery and provides new capabilities in leveraging multimodal in operando spectroscopies and automated control for the manipulation of nanoscale structures in materials.