Hyperbolic Learning Rate Scheduler
deep-learning image-classification time-series-forecasting operator-learning learning-rate-scheduler
-
Updated
Jun 12, 2026 - Python
#
learning-rate-scheduler
Here are 7 public repositories matching this topic...
This project modifies the classic VGG16 architecture to classify images into four distinct categories with high accuracy. It incorporates data augmentation, dynamic learning rate adjustments, and comprehensive performance evaluation using accuracy metrics and confusion matrices. Built with PyTorch and supported by a suite of powerful libraries
python machine-learning deep-learning numpy scikit-learn pil pytorch seaborn image-classification matplotlib vgg16 data-augmentation torchvision accuracy-evaluation learning-rate-scheduler
-
Updated
Dec 11, 2023 - Python
The Newton-like learning rate scheduler
machine-learning machine-learning-algorithms artificial-intelligence learning-rate second-order-optimization learning-rate-scheduler
-
Updated
Apr 29, 2025 - Python
Lightweight CNN for 28×28 grayscale multi-class image classification with augmentation & regularization.
computer-vision deep-learning cnn pytorch image-classification resnet regularization vgg16 augmentation ablation-study 64x64 28x28 learning-rate-scheduler
-
Updated
Oct 7, 2025 - Jupyter Notebook
PyTorch implementation of the generalized Newton's method for learning rate selection
machine-learning pytorch artificial-intelligence neural-networks learning-rate newtons-method learning-rate-scheduling learning-rate-scheduler
-
Updated
Feb 10, 2025 - Python
High-performance PyTorch LR schedulers with cosine annealing, flexible waypoints, plateau steps, and LR scaling. Unified API with pre-computed segments for zero runtime overhead.
training machine-learning deep-learning pytorch distributed-training cosine-annealing lr-scheduling learning-rate-scheduler waypoint-scheduler
-
Updated
Oct 13, 2025 - Python
🖼️A PyTorch-based Convolutional Neural Network (CNN) built from scratch to classify CIFAR-10 images. Achieves 82.93% test accuracy using Batch Normalization, Dropout, Data Augmentation, and a ReduceLROnPlateau scheduler. Includes detailed evaluation curves, confusion matrices, and per-class analyses.
python machine-learning computer-vision deep-learning numpy sklearn jupyter-notebook cnn data-visualization pytorch seaborn artificial-intelligence batch-normalization neural-networks image-classification matplotlib convolutional-neural-networks data-augmentation cifar-10 learning-rate-scheduler
-
Updated
Jul 24, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the learning-rate-scheduler topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the learning-rate-scheduler topic, visit your repo's landing page and select "manage topics."