Classification-with-Adaboost-and-NaiveGoogLeNet-Frameworks: A Python repository from kuangzijian

Classification with Adaboost and NaiveGoogLeNet frameworks

This project focuses on topics:

AdaBoost
Pytorch autograd
Mnist data classification with original GoogLeNet and NaiveGoogLeNet frameworks.

Built With

Pytorch

Prerequisites

1. Clone the repo
2. pip install -r requirements.txt

1 Classification with the Adaboost algorithm

cd Q2_AdaBoost
python Q2_test.py

2 Classification with the following network (with i1=0.05, i2=0.1, b1=0.35, o1=0.01, o2=0.99)

cd Q3_NN_with_Autograd
python NN_with_Autograd.py

3 Mnist data classification with original GoogLeNet and NaiveGoogLeNet frameworks.

cd Q4_mnist_googlenet
python train_googlenet.py
python train_naive_googlenet.py

NaiveGoogLeNet and GoogLeNet model training and test outputs analysis report can be found under:

NaiveGoogLeNet and GoogLeNet model Report

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

Fork the Project
Create your Feature Branch (git checkout -b feature/AmazingFeature)
Commit your Changes (git commit -m 'Add some AmazingFeature')
Push to the Branch (git push origin feature/AmazingFeature)
Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

References

MNIST Data example. https://github.com/pytorch/examples/tree/master/mnist

PyTorch GoogLeNet implementation. https://github.com/pytorch/vision/blob/master/torchvision/models/googlenet.py

kuangzijian/Classification-with-Adaboost-and-NaiveGoogLeNet-Frameworks