A Re-implementation of Fixed-update Initialization
☆155Jun 9, 2019Updated 7 years ago
Alternatives and similar repositories for Fixup
Users that are interested in Fixup are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆34Mar 1, 2019Updated 7 years ago
- Odds and Ends and Things I've implemented.☆78Jan 31, 2019Updated 7 years ago
- Gradually Updated Neural Networks for Large-Scale Image Recognition at ICML 2018☆10Jun 25, 2018Updated 7 years ago
- Delta Orthogonal Initialization for PyTorch☆18Jun 27, 2018Updated 7 years ago
- Embedding language models in probability space via log-likelihood vectors☆19Jun 10, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆182Feb 23, 2023Updated 3 years ago
- Code for reproducing Manifold Mixup results (ICML 2019)☆490Mar 31, 2024Updated 2 years ago
- Implementation for <Regularizing Neural Networks via Minimizing Hyperspherical Energy> in CVPR'20.☆24Jun 23, 2020Updated 5 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆159Mar 26, 2020Updated 6 years ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated 11 months ago
- An adaptive training algorithm for residual network☆17Aug 22, 2020Updated 5 years ago
- Standardizing weights to accelerate micro-batch training☆548Feb 26, 2022Updated 4 years ago
- Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)☆48Jan 10, 2022Updated 4 years ago
- ☆16Jun 11, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official PyTorch implementation of Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation (ICLR 2019)☆94Jul 25, 2024Updated last year
- Simple distribute job scheduler for multiple servers with only SSH. No additions.☆10Dec 8, 2022Updated 3 years ago
- mixup: Beyond Empirical Risk Minimization☆1,196Oct 12, 2021Updated 4 years ago
- ML Reproducibility Challenge 2020: Electra reimplementation using PyTorch and Transformers☆12Apr 16, 2021Updated 5 years ago
- ICLR 2018 reproducibility challenge - Multi-Scale Dense Convolutional Networks for Efficient Prediction☆132May 27, 2018Updated 8 years ago
- Optimized Utilities for PyTorch☆26Jan 19, 2020Updated 6 years ago
- [ECCV 2018] Sparsely Aggreagated Convolutional Networks https://arxiv.org/abs/1801.05895☆124Oct 10, 2018Updated 7 years ago
- Efficient HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs☆44May 12, 2019Updated 7 years ago
- offical seesawfacenet pytorch implement, https://arxiv.org/abs/1908.09124☆119Nov 22, 2022Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Repo for my blogs explaining swish activation function☆13Dec 17, 2017Updated 8 years ago
- Light-weight GPU kernel interface for graph operations☆15May 20, 2020Updated 6 years ago
- Implementation of "Fully Learnable Group Convolution for Acceleration of Deep Neural Networks", CVPR'19☆33Mar 23, 2020Updated 6 years ago
- pip install antialiased-cnns to improve stability and accuracy☆1,686Apr 8, 2024Updated 2 years ago
- The Search for Sparse, Robustness Neural Networks☆11Mar 24, 2023Updated 3 years ago
- 🧀 Pytorch code for the Fromage optimiser.☆129Jul 14, 2024Updated last year
- Implementation of the mixup training method☆469Jun 12, 2018Updated 8 years ago
- Code for the implemenation of the Patch Augmentation technique☆10Nov 28, 2019Updated 6 years ago
- A drop-in replacement for CIFAR-10.☆246Mar 7, 2021Updated 5 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Stochastic Weight Averaging in PyTorch☆983Aug 1, 2021Updated 4 years ago
- An optimizer that trains as fast as Adam and as good as SGD.☆2,904Jul 23, 2023Updated 2 years ago
- repo that holds code for improving on dropout using Stochastic Delta Rule☆141Feb 10, 2019Updated 7 years ago
- "Learning Rate Dropout" in PyTorch☆34Dec 6, 2019Updated 6 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆26Jan 7, 2025Updated last year
- ☆225Feb 21, 2023Updated 3 years ago
- Torch implementation of the paper "ShakeDrop regularization" (https://arxiv.org/abs/1802.02375).☆21Feb 8, 2018Updated 8 years ago