Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep Learning Projects that Build Themselves
| Date | Stars |
|---|---|
| 2026-07-31 | 360 |
| 2026-08-03 | 360 |
| 2026-08-06 | 360 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# MagNet: Deep Learning Projects that Build Themselves
<div align="center">
<img src="docs/source/_static/img/logo-full.png" alt="MagNet Logo"/>
</div>
<br>
[](https://github.com/svaisakh/magnet/blob/master/LICENSE)
[](https://travis-ci.org/MagNet-DL/magnet)
[](https://magnet-dl.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/svaisakh/magnet/releases)
[](https://gitter.im/MagNet-DL/Lobby/?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[](https://github.com/svaisakh/magnet/pulls)
[](https://codecov.io/gh/MagNet-DL/magnet)
[](https://www.codacy.com/app/svaisakh/magnet?utm_source=github.com&utm_medium=referral&utm_content=MagNet-DL/magnet&utm_campaign=Badge_Grade)
[](https://www.openhub.net/p/magnet)
MagNet is a high-level Deep Learning API, wrapped around PyTorch.
It was developed with the aim of reducing boilerplate code and writing Deep Learning architectures with more grace.
You should take a look at it if you need something that is:
- **Intelligent.** MagNet's ``Node``s are _self-aware_. Intelligent.
They attach to each other like magnets (hence the name).
This enables you to build complex architectures easily.
- **Simple.** MagNet's API enables a simplistic workflow.
Get the data. Define the model. Train. Debug. Test. Deploy.
- **Extensible.** Written on top of the awesome PyTorch library,
MagNet can also mix with lower-level details.
- **Ready.** The ``Trainer`` can accommodate **any training logic**, however complex.
This means that you can do almost any experiment / research with
all the features that MagNet has to offer.
<hr>
# Getting started: 30 seconds to MagNetize
The core idea of MagNet is the ``Node``.
Nodes are PyTorch modules that can change their properties dynamically based on the computational graph.
This way, they attach to each other... like magnets!
Here, we define a simple 3-layer CNN.
Note that you only need to specify the bare essentials.
No need to specify the strides, paddings, input sizes, or even flatten the output before feeding it to the final layer.
```python
model = nn.Sequential(mn.Conv(32), *mn.Conv() * 2, mn.Linear(10, act=None))
summarize(model, x=torch.randn(1, 1, 28, 28))
"""
+----------+------------+----------------------+
| Node | Shape | Trainable Parameters |
+----------+------------+----------------------+
| input | 1, 28, 28 | 0 |
+----------+------------+----------------------+
| Conv | 32, 14, 14 | 320 |
+----------+------------+----------------------+
| Conv | 64, 7, 7 | 18,496 |
+----------+------------+----------------------+
| Conv | 128, 4, 4 | 73,856 |
+----------+------------+----------------------+
| Linear | 10 | 20,490 |
+----------+------------+----------------------+
Total Trainable Parameters: 113,162
"""
```
Now, we'll get the dataset in a ``Data`` container.
``Data`` is a class that abstracts away the different sets (training, validation, test) and provides easy access to loaders.
```python
data = Data.get('mnist')
```
Next, we'll create a ``Trainer``.
MagNet's ``Trainer`Excerpt of 13,994 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:34ad11dbcb2769a1, topic:deep-learning