Loading repository data…
RISHIKREDDYL / repository
This is a fruit and vegetable classification project that uses a Convolutional Neural Network (CNN) with the Google Inception pre-trained model. The model is trained using Stochastic Gradient Descent and tested on a validation set to achieve 100% accuracy.
This code implements a fruit and vegetable classification using a pre-trained Google Inception neural network. The dataset used consists of 33 different fruits and vegetables classes. The validation and test accuracy of this model are both 100%.
The dataset used in this project can be found at Kaggle.
The code starts by loading the image data and then reducing all labels to 200 images, before splitting the dataset between training, validation, and testing sets. The pre-trained GoogleNet is then loaded, and the last layers are replaced for the classification task. The new feature learner and classifier layer are defined, and the layer graph is replaced with the new layers.
The model is trained using stochastic gradient descent with momentum (SGDM) as the optimization algorithm. The training options include a learn rate schedule, a learn rate drop factor, a learn rate drop period, a mini-batch size, and a maximum number of epochs. The model is trained for five epochs, and the validation data is used to validate the model every 50 iterations.
After training the model, it is saved along with the training progress. The test set is then classified, and a confusion matrix is created to show the performance of the model. The accuracy is calculated and displayed on the test set.
To use this code, download the dataset from the Kaggle link mentioned above and modify the path in the code to point to the correct location of the dataset on your system. The code can then be run on any platform that supports MATLAB.
Selected from shared topics, language and repository description—not editorial ratings.
mathworks-robotics /
This is a list of awesome demos, tutorials, utilities and overall resources for the robotics community that use MATLAB and Simulink.
USNavalResearchLaboratory /
This is a collection of Matlab functions that are useful in the development of target tracking algorithms.
This is a workshop on implementing model predictive control (MPC) and moving horizon estimation (MHE) on Matlab. The implementation is based on the Casadi Package which is used for numerical optimization. A non-holonomic mobile robot is used as a system for the implementation. The workshop video recording can be found here https://www.youtube.com/playlist?list=PLK8squHT_Uzej3UCUHjtOtm5X7pMFSgAL ... Casadi can be downloaded here https://web.casadi.org/
This tutorial is a companion volume of Matlab versionm but add more. Main objective is the transference of know-how in practical applications and management of statistical tools commonly used to explore meteorological time series, focusing on applications to study issues related with the climate variability and climate change. This tutorial starts with some basic statistic for time series analysis as estimation of means, anomalies, standard deviation, correlations, arriving the estimation of particular climate indexes (Niño 3), detrending single time series and decomposition of time series, filtering, interpolation of climate variables on regular or irregular grids, leading modes of climate variability (EOF or HHT), signal processing in the climate system (spectral and wavelet analysis). In addition, this tutorial also deals with different data formats such as CSV, NetCDF, Binary, and matlab'mat, etc. It is assumed that you have basic knowledge and understanding of statistics and Python.
chenjoya /
This is a Matlab lesson design for vehicle detection and recognition. Using cifar-10Net to training a RCNN, and finetune AlexNet to classify. Thanks to Cars Dataset:http://ai.stanford.edu/~jkrause/cars/car_dataset.html
tomcattiger1230 /
This repository is an implementation of the work from Mohamed W. Mehrez. I convert the original code in MATLAB to the Python