Algorithms for classification written in pytorch

I tried to implement algorithms used for classification using the pytorch library. I implemented the following algorithms

1. AlexNet (https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf)

2. VGGNet (https://arxiv.org/abs/1409.1556)

3. EfficientNet (https://arxiv.org/abs/1905.11946)

4. InceptionNet (https://arxiv.org/abs/1409.4842)

5. ResNet (https://arxiv.org/abs/1512.03385v1)

6. PreActResNet (https://arxiv.org/abs/1603.05027v3)

7. WideResNet (https://arxiv.org/abs/1605.07146v4)

8. ResNeXt (https://arxiv.org/abs/1611.05431v2)

9. DenseNet (https://arxiv.org/abs/1608.06993v4)

Requirements for PyTorch

For most experiments, one or two K40(~11G of memory) gpus is enough cause PyTorch is very memory efficient. However, to train DenseNet on cifar(10 or 100), you need at least 4 K40 gpus.

1. Clone this repository

git clone https://github.com/Ti-Oluwanimi/Classification-Algorithms-Pytorch.git

2. Edit main.py and run.sh

In the main.py, you can specify the network you want to train(for example):

model = resnet20_cifar(num_classes=10)

##Note
Please contact me if there are issues within the codebase.