facebookresearch/mixup-cifar10 排名第 11,206，有 1,195 个星标。
同类别比较
facebookresearch/mixup-cifar10 排名第 11,206，此处有 8 个同类条目；autonomousvision/stylegan-t 排名第 11,205。
同类别比较| 名称 | 排名 | 指标 |
|---|
| danielgross/LlamaAcademy | 11,194 | - 语言:
- Python
- 星标数:
- 1,197
- 分叉数:
- 73
- 简介:
- A school for camelids
|
|---|
| kexinhuang12345/DeepPurpose | 11,195 | - 语言:
- Jupyter Notebook
- 星标数:
- 1,197
- 分叉数:
- 307
- 简介:
- A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
|
|---|
| huggingface/hmtl | 11,201 | - 语言:
- Python
- 星标数:
- 1,196
- 分叉数:
- 143
- 简介:
- 🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
|
|---|
| autonomousvision/stylegan-t | 11,205 | - 语言:
- Python
- 星标数:
- 1,195
- 分叉数:
- 60
- 简介:
- [ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
|
|---|
| openai/procgen | 11,207 | - 语言:
- C++
- 星标数:
- 1,195
- 分叉数:
- 225
- 简介:
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
|
|---|
| shallowdream204/DreamClear | 11,218 | - 语言:
- Python
- 星标数:
- 1,193
- 分叉数:
- 44
- 简介:
- [NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
|
|---|
| flow-project/flow | 11,222 | - 语言:
- Python
- 星标数:
- 1,192
- 分叉数:
- 395
- 简介:
- Computational framework for reinforcement learning in traffic control
|
|---|
| jankrepl/deepdow | 11,230 | - 语言:
- Python
- 星标数:
- 1,190
- 分叉数:
- 171
- 简介:
- Portfolio optimization with deep learning.
|
|---|
关键参数与规格
关键参数与规格| 参数 | 值 |
|---|
| 语言 | Python |
|---|
| 类别 | Model Development |
|---|
| 子类别 | Dataset engineering |
|---|
| 星标数 | 1,195 |
|---|
| 分叉数 | 231 |
|---|
| 贡献者 | 3 |
|---|
| 创建日期 | 2018-02-19 |
|---|
| 更新日期 | 2026-09-08 |
|---|
| 1 天星标数 | 0 |
|---|
| 7 天星标数 | 0 |
|---|
| 排名 | 11,206 |
|---|
| 上次排名 | 11,159 |
|---|
| 排名变化 | -47 |
|---|
| 7 天星标排名 | 12,926 |
|---|
| 上次 7 天星标排名 | 12,942 |
|---|
| 7 天星标排名变化 | 16 |
|---|
| 总星标排名 | 9,745 |
|---|
| 上次总星标排名 | 9,737 |
|---|
| 总星标排名变化 | -8 |
|---|
| 国家 | USA |
|---|
README 摘录
Mixup-CIFAR10 By Hongyi Zhang, Moustapha Cisse, Yann Dauphin, David Lopez-Paz. Facebook AI Research Introduction Mixup is a generic and straightforward data augmentation principle. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. This repository contains the implementation used for the results in our paper ( Citation If you use this method or this code
in your paper, then please cite it: Requirements and Installation A computer running macOS or Linux For training new models, you'll also need a NVIDIA GPU and NCCL Python version 3. 6 A PyTorch installation Training Use to train a new model. Here is an example setting: License This project is CC-BY-NC-licensed. Acknowledgement The CIFAR-10 reimplementation of _mixup_ is adapted from the pytorch-cifar repository by kuangliu.
常见问题
记录了多少星标和分叉？
facebookresearch/mixup-cifar10 有 1,195 个星标和 231 个分叉。
仓库排名是多少？
facebookresearch/mixup-cifar10 排名第 11,206。
记录的语言和类别是什么？
facebookresearch/mixup-cifar10 有 1,195 个星标，语言为 Python，类别为 Model Development。
哪个仓库排名最接近？
facebookresearch/mixup-cifar10 与 autonomousvision/stylegan-t 比较，后者排名第 11,205，有 1,195 个星标。
Mixup-CIFAR10
By Hongyi Zhang, Moustapha Cisse, Yann Dauphin, David Lopez-Paz.
Facebook AI Research
Introduction
Mixup is a generic and straightforward data augmentation principle.
In essence, mixup trains a neural network on convex combinations of pairs of
examples and their labels. By doing so, mixup regularizes the neural network to
favor simple linear behavior in-between training examples.
This repository contains the implementation used for the results in
our paper (https://arxiv.org/abs/1710.09412).
Citation
If you use this method or this code in your paper, then please cite it:
@article{
zhang2018mixup,
title={mixup: Beyond Empirical Risk Minimization},
author={Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz},
journal={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=r1Ddp1-Rb},
}
Requirements and Installation
- A computer running macOS or Linux
- For training new models, you'll also need a NVIDIA GPU and NCCL
- Python version 3.6
- A PyTorch installation
Training
Use python train.py to train a new model.
Here is an example setting:
$ CUDA_VISIBLE_DEVICES=0 python train.py --lr=0.1 --seed=20170922 --decay=1e-4
License
This project is CC-BY-NC-licensed.
Acknowledgement
The CIFAR-10 reimplementation of mixup is adapted from the pytorch-cifar repository by kuangliu.