Neural networks implementation in Java, based on Stanford cs231n
-
Updated
Jun 11, 2018 - Java
Neural networks implementation in Java, based on Stanford cs231n
Varying classifier and data processing techniques for the CIFAR-10 dataset.
Transfer Learning with CIFAR-10 dataset
Estudo de técnicas de deep learning para classificação do conjunto de dados cifar-10
CIFAR-10 is an image dataset which contains 60000 tiny color images with the size of 32 by 32 pixels. The dataset consists of 10 different classes (i.e. airplane, automobile, bird, cat, deer, dog, frog, horse, ship and truck), in which each of those classes consists of 6000 images.
Cifar-10 CNN implementation using TensorFlow library
High Accuracy ResNet Model under 5 Million parameters.
A CNN model trained on 50,000 images for classification of images on 10 different classes.
Image Reconstruction and Classification with Autoencoder and SVM.
Implementing an ANN using PyTorch (under 800,000 parameters) to achieve +92% accuracy in under 100 epochs.
classifying CIFAR-10 images using CNN in Tensorflow and Keras
The code does image classification using the CIFAR-10 dataset. Two models, ANN and CNN, are trained on 32x32 color images across 10 classes. Following data preprocessing, the models are constructed and trained. Their classification performance is assessed on test images, highlighting their effectiveness in identifying objects within the dataset.
Using Machine Learning Models to classify images of CIFAR10
A basic implementation of CNN (LeNet) both without libraries and with Tensorflow, Keras.
keras_CNN models_with_cifar10
Implement clustering and PCA and apply them to CIFAR-10!
Building CIFAR10 with Keras
Add a description, image, and links to the cifar-10 topic page so that developers can more easily learn about it.
To associate your repository with the cifar-10 topic, visit your repo's landing page and select "manage topics."