Marco-Christiani / Zigrad
A deep learning framework built on an autograd engine with high level abstractions and low level control.
Why this job: says: deep learning framework; topics: neural-network, autograd, tensor, deep-learning, machine-learning
What it does
- *Input:* Batch of images 28x28 pixel samples.
- Flatten. 28x28 -> 784
- FC1. Linear layer 784 -> 128
- FC2. Linear layer 128 -> 64
- FC3. Linear layer 64 -> 10
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 49 days ago
- Stars
- 198
- +1 this week
- Licence
- LGPL-3.0
- Share-alike for changes
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Zig
- 76% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 70% closed
- 11 still open
- Pull requests
- 38 merged
- 3 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| tracel-ai / burn | 16,268 | yesterday | Apache-2.0 | No downloads |
| ARM-software / armnn | 1,319 | 4 months ago | MIT | Linux |
| jaywyawhare / C-ML | 119 | 12 days ago | Custom | No downloads |
More: languages, topics and project record
Languages
- Zig 76%
- Cuda 13%
- Python 8%
- C 1%
Topics
- autograd
- deep-learning
- machine-learning
- neural-network
- tensor
- zig
- zig-package
- ziglang
Project record
- JobAI libraries and models
- StatusListed
- Commits583
- Forks13
- Watching4
- Stars in 28 days+1
- CreatedDec 1, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026