Gradually-Warmup Learning Rate Scheduler for PyTorch
-
Updated
Oct 10, 2024 - Python
#
learning-rate-decay
Here are 14 public repositories matching this topic...
PyTorch implementation of CNNs for CIFAR benchmark
-
Updated
Feb 20, 2021 - Python
Cyclic learning rate TensorFlow implementation.
-
Updated
Mar 21, 2019 - Python
Polynomial Learning Rate Decay Scheduler for PyTorch
-
Updated
Dec 25, 2021 - Python
Pytorch cyclic cosine decay learning rate scheduler
-
Updated
May 31, 2021 - Jupyter Notebook
Short description for quick search
tensorflow dropout batch-normalization momentum softmax-regression l2-regularization rmsprop adam-optimizer mini-batch-gradient-descent bias-correction initialization gradient-check exponentially-weighted-averages learning-rate-decay
-
Updated
Jan 31, 2019 - Python
-
Updated
Apr 11, 2022
Source code for HTD (WACV 2019)
-
Updated
Sep 3, 2020 - Lua
Statistical Digital Signal Processing and Modeling
statistics algorithms dsp numpy linear-algebra statistical-inference statistical adaptive-filtering learning-rate kalman-filter statistical-models power-spectrum power-spectral-density adaptive-filters numpy-arrays signal-processing-algorithms wiener-filter learning-rate-decay
-
Updated
Apr 18, 2024 - Python
python code, notebooks and Images used for AI502 Midterm Project.
mnist adam-optimizer cifar100 learning-rate-decay sgd-optimizer batch-size resnet50 mobilenetv2 radam
-
Updated
May 25, 2020 - Jupyter Notebook
Shift Claude Code’s 5-hour window reset with a scheduled warmup message so you avoid dead time and keep working longer
deep-learning mcp pytorch embeddings developer-tools claude adam-optimizer multigpu memory-engine learning-rate-decay rag anthropic chromadb ai-memory claude-agents claude-agent-sdk claude-code-plugin
-
Updated
Apr 27, 2026
Kleines CNN zur Klassifizierung des CIFAR-10 Datensatzes.
machine-learning cnn convolutional-neural-networks cifar10 data-augmentation cifar100 cifar-10 learning-rate-decay machinelearning-python
-
Updated
Nov 21, 2023 - Jupyter Notebook
Provide a collection of flexible learning rate schedulers for PyTorch with presets, warmup wrappers, and research-based implementations.
deep-learning scheduler clr sam optimizer transformer muon large-scale-learning scion multinode lr triangular learning-rate-decay adamw cyclical-learning-rate radam learning-rate-warmup gradient-centralization adamp madgrad
-
Updated
Apr 27, 2026 - Python
Improve this page
Add a description, image, and links to the learning-rate-decay 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-decay topic, visit your repo's landing page and select "manage topics."