- Notifications
You must be signed in to change notification settings - Fork560
Classification with PyTorch.
License
NotificationsYou must be signed in to change notification settings
bearpaw/pytorch-classification
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Classification on CIFAR10/100 with PyTorch.
- InstallPyTorch
- Clone recursively
git clone --recursive https://github.com/bearpaw/pytorch-classification.git
Top1 error rate on CIFAR10/100 are reported. You may get different results when training your models with different initialization.
| Model | Params (M, CIFAR10) | CIFAR-10 (%) | CIFAR-100 (%) |
|---|---|---|---|
| alexnet | 2.47 | 22.78 | 56.13 |
| vgg19_bn | 20.04 | 6.66 | 28.05 |
| Resnet-110 | 1.70 | 6.11 | 28.86 |
| WRN-28-10 (drop 0.3) | 36.48 | 3.79 | 18.14 |
| ResNeXt-29, 8x64 | 34.43 | 3.69 | 17.38 |
| ResNeXt-29, 16x64 | 68.16 | 3.53 | 10137 |
Single-crop (224x224) validation error rate
| Model | Params (M) | Top-1 Error (%) | Top-5 Error (%) |
|---|---|---|---|
| Resnet-101 | 44.55 |
Since the size of images in CIFAR dataset is32x32, popular network structures for ImageNet need some modifications to adapt this input size. The modified models is located in the subfoldermodels:
- AlexNet
- VGG (Imported frompytorch-cifar)
- ResNet
- ResNeXt (Imported fromResNeXt.pytorch)
- Wide Residual Networks (Imported fromWideResNet-pytorch)
- DenseNet
- All models in
torchvision.models(alexnet, vgg, resnet, densenet, inception_v3, squeezenet) - ResNeXt
- Wide Residual Networks
Please see theTraining recipes for how to train the models.
About
Classification with PyTorch.
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
No releases published
Packages0
No packages published
Uh oh!
There was an error while loading.Please reload this page.
Contributors4
Uh oh!
There was an error while loading.Please reload this page.