MNIST-trained model to predict what the digit you draw!

Training MLP and CNN on MNIST dataset

A PyTorch implementation of "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".

Semi-supervised learning with Generative Adversarial Networks (GANs) using Kolmogorov-Arnold Network Layers (KANLs)

基于MNIST数据集，从零构建diffusion扩散模型

Explore this repository for a CNN-based handwritten digit classification project. Utilizes TensorFlow to train and evaluate models, providing a practical example of deep learning in image recognition.

Config files for my GitHub profile.

This project demonstrates MNIST model inference using Rust with the ONNX runtime (ort crate). The Rust code loads an ONNX model trained on MNIST and performs inference on a provided image file.

The MNIST dataset was used to train a neural network having a single linear layer with SoftMax employed in the criterion function (Cross Entropy Loss) to classify handwritten digits in classes 0 to 9. The model yielded a 92% accuracy on the MNIST test dataset in 10 training epochs.

Data and code for our analysis of DermaMNIST (MedMNIST), HAM10000, and Fitzpatrick17k datasets

introduction to neural networks - from scratch.

[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification

Train the MNIST dataset and a web UI.

A Neural Network made 'from scratch' using NumPy only, trained on the MNIST dataset of handwritten digits. Achieved 98.4% accuracy 🎉

MNIST image classification using LeNet-5

Forward-Forward algorithm on MNIST

Combine B-Spline (BS) and Radial Basic Function (RBF) in Kolmogorov-Arnold Networks (KANs)

A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset