hysts / Pytorch_shake_shake
Licence: mit
A PyTorch implementation of shake-shake
Stars: ✭ 101
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pytorch shake shake
Tensorflow Cifar 10
Cifar-10 CNN implementation using TensorFlow library with 20% error.
Stars: ✭ 85 (-15.84%)
Mutual labels: cifar10
Image classification cifar 10
Image Classification on CIFAR-10 Dataset using Multi Layer Perceptrons in Python from Scratch.
Stars: ✭ 18 (-82.18%)
Mutual labels: cifar10
Relativistic Average Gan Keras
The implementation of Relativistic average GAN with Keras
Stars: ✭ 36 (-64.36%)
Mutual labels: cifar10
Ali Pytorch
PyTorch implementation of Adversarially Learned Inference (BiGAN).
Stars: ✭ 61 (-39.6%)
Mutual labels: cifar10
Autogan
[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang
Stars: ✭ 388 (+284.16%)
Mutual labels: cifar10
Virtual Adversarial Training
Pytorch implementation of Virtual Adversarial Training
Stars: ✭ 94 (-6.93%)
Mutual labels: cifar10
Knowledge Distillation Pytorch
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Stars: ✭ 986 (+876.24%)
Mutual labels: cifar10
Bsconv
Reference implementation for Blueprint Separable Convolutions (CVPR 2020)
Stars: ✭ 84 (-16.83%)
Mutual labels: cifar10
Randwire tensorflow
tensorflow implementation of Exploring Randomly Wired Neural Networks for Image Recognition
Stars: ✭ 29 (-71.29%)
Mutual labels: cifar10
Pytorch image classification
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
Stars: ✭ 795 (+687.13%)
Mutual labels: cifar10
Neural Backed Decision Trees
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Stars: ✭ 411 (+306.93%)
Mutual labels: cifar10
One Pixel Attack Keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
Stars: ✭ 1,097 (+986.14%)
Mutual labels: cifar10
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-0.99%)
Mutual labels: cifar10
Neural Api
CAI NEURAL API - Pascal based neural network API optimized for AVX, AVX2 and AVX512 instruction sets plus OpenCL capable devices including AMD, Intel and NVIDIA.
Stars: ✭ 94 (-6.93%)
Mutual labels: cifar10
PyTorch Implementation of shake-shake
Usage
$ python train.py --depth 26 --base_channels 32 --shake_forward True --shake_backward True --shake_image True --outdir results
Results on CIFAR-10
| Model | Test Error (median of 3 runs) | Test Error (in paper) | Training Time |
|---|---|---|---|
| shake-shake-26 2x32d (S-S-I) | 3.68 | 3.55 (average of 3 runs) | 11h16m |
| shake-shake-26 2x64d (S-S-I) | 2.88 (1 run) | 2.98 (average of 3 runs) | 19h43m |
| shake-shake-26 2x96d (S-S-I) | 2.90 (1 run) | 2.86 (average of 5 runs) | 32h10m |
Notes
- Tesla V100 was used in these experiments.
References
- Gastaldi, Xavier. "Shake-Shake regularization." In International Conference on Learning Representations, 2017. arXiv:1705.07485, Torch implementation
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].