readme

bearpaw · bearpaw · commit fa48c6b9c746 · 2017-06-08T16:19:51.000+08:00
diff --git a/README.md b/README.md
@@ -7,11 +7,10 @@ Classification on CIFAR10/100 with PyTorch.
   ```
   git clone --recursive https://github.com/bearpaw/pytorch-classification.git
   ```
-* Run experiments by following the [Training recipes](#training-recipes)
 
 ## Results
 
-Top1 error.
+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 (%)      |
 | -------------------  | ------------------ | ------------------ | ------------------ |
@@ -23,20 +22,19 @@ Top1 error.
 | ResNeXt-29, 16x64    | 68.16              | 164              |             10137  |
 | WRN-28-10 (drop 0.3) | 36.48              | 179              |             10137  |
 
-## Datasets
+## Supported Architectures
 
 ### CIFAR-10 / CIFAR-100
 Since the size of images in CIFAR dataset is `32x32`, popular network structures for ImageNet need some modifications to adapt this input size. The modified models is located in the subfolder `models`:
 - [x] [AlexNet](https://arxiv.org/abs/1404.5997)
 - [x] [VGG](https://arxiv.org/abs/1409.1556) (Imported from [pytorch-cifar](https://github.com/kuangliu/pytorch-cifar))
-- [ ] [ResNet](https://arxiv.org/abs/1512.03385)
+- [x] [ResNet](https://arxiv.org/abs/1512.03385)
 - [x] [ResNeXt](https://arxiv.org/abs/1611.05431) (Imported from [ResNeXt.pytorch](https://github.com/prlz77/ResNeXt.pytorch))
 - [x] [Wide Residual Networks](http://arxiv.org/abs/1605.07146) (Imported from [WideResNet-pytorch](https://github.com/xternalz/WideResNet-pytorch))
 - [ ] [DenseNet](https://arxiv.org/abs/1608.06993)
 
 ## Training recipes
 Please see the [Training recipes](TRAINING.md) for how to train the models.
 
-```
 ## TODO
 - [ ] Add ImageNet
