This is a mini but function completed neural networks framework
Project description
ABOUT
This is a mini deep learning framework created by Kaikeba @ Beijing
Features
- Define Dynamic Computing Graph
- Define Neural Network Operator
- Define Linear, Sigmoid, L2_loss
- Auto-Diff Computing
- Auto-Feedforward and Backward
Remain
- Classification
- Cross-Entropy
- CNN, RNN
Connection
wechat: fortymiles Mail: minchiuan@zju.edu.cn
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
kaikeba_flow-0.0.1.tar.gz
(3.5 kB
view hashes)
Built Distribution
Close
Hashes for kaikeba_flow-0.0.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | e55af6f84ed9b6bab2caff581f9b97040025b9f3c75dbb6ee8573168fd86e8e4 |
|
| MD5 | f3d1ffec38cdefc7c7c30adb98a29122 |
|
| BLAKE2b-256 | cd287bb52896a65eb282a853143072c3b1dc71ee4808c082c124c5abf1718939 |
