Implementation of deep learning based on numpy, modular design guarantees easy implementation of the model, which is suitable for the introduction of junior researchers in deep learning.
A PyTorch example is also included.
Realized Network Model（Located on the pynet/models）：
- 2-Layer Neural Network
- 3-Layer Neural Network
- LeNet-5
- AlexNet
- NIN
Realized Network Layer（Located on the pynet/nn）：
- Convolution Layer (Conv2d)
- Fully-Connected Layer (FC)
- Max-Pooling layer (MaxPool)
- ReLU Layer (ReLU)
- Random Dropout Layer (Dropout/Dropout2d)
- Softmax
- Cross Entropy Loss
- Gloabl Average Pool (GAP)
.
├── examples # pynet use examples
│ ├── 2_nn_mnist.py
│ ├── 3_nn_cifar10.py
│ ├── 3_nn_iris.py
│ ├── 3_nn_mnist.py
│ ├── 3_nn_orl.py
│ ├── lenet5_mnist.py
│ └── nin_cifar10.py
├── imgs
│ ├── logo2.png
│ └── logo.png
├── LICENSE
├── plt # draw loss and acc
│ ├── draw_acc.py
│ ├── draw_loss.py
│ ├── __init__.py
│ └── __pycache__
├── pynet
│ ├── __init__.py
│ ├── models # model definition
│ ├── nn # layer definition
│ ├── optim # optimizer
│ ├── __pycache__
│ ├── solver.py # solver
│ └── vision # data correlation
├── pytorch
│ ├── examples
│ ├── __init__.py
│ ├── models
│ └── vision
├── README.md
└── README.zh-CN.md
We use SemVer for versioning. For the versions available, see the tags on this repository.
- zhujian - Initial work - zjZSTU
This project is licensed under the Apache License v2.0 - see the LICENSE file for details