Numpy-based deep learning library
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.
Systematic learning convolution neural network has been nearly half a year.Using librarys such as pytorch can't understand the implementation in depth. So I plan to complete a deep learning framework from scratch.The initial implementation will refer to the operation of cs231n, and then we will implement it in the form of computational graphs. I hope this project can improve my programming ability and help others at the same time.
If you use PyNet, add the following Badge
To add in Markdown format, use this code:
[](https://github.com/zjZSTU/PyNet)
PyNet need the following prerequisites
- python3.x
- numpy
- opencv3.x
Refer to the sample code under the example folder
Full version reference releases
Realized Network Model（Located in pynet/models folder）：
- 2-Layer Neural Network
- 3-Layer Neural Network
- LeNet-5
- AlexNet
- NIN
Realized Network Layer（Located in pynet/nn folder）：
- 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)
see the CHANGELOG on this repository.
- Realization of batch normalization
- Realization of Computational Graph
- zhujian - Initial work - zjZSTU
Anyone's participation is welcome! Open an issue or submit PRs.
Small note:
- Git submission specifications should be complied with Conventional Commits
- If versioned, please conform to the Semantic Versioning 2.0.0 specification
- If editing the README, please conform to the standard-readme specification.
Apache License 2.0 © 2019 zjZSTU