Utilities and baselines for fast neural network training on CIFAR-10
Project description
CIFAR-10 Airbench 💨
This repo contains utilities and baselines for fast neural network training on CIFAR-10.
| Script | Mean accuracy | Time | PFLOPs |
|---|---|---|---|
airbench94_compiled.py |
94.01% | 3.29s | 0.36 |
airbench94.py |
94.01% | 3.83s | 0.36 |
airbench95.py |
95.01% | 10.4s | 1.4 |
airbench96.py |
96.05% | 46.3s | 7.5 |
How to run
git clone https://github.com/KellerJordan/cifar10-airbench.git && cd airbench && python airbench94.py
or
pip install airbench && python -c "import airbench; airbench.train94()"
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
airbench-0.1.1.tar.gz
(9.7 kB
view details)
File details
Details for the file airbench-0.1.1.tar.gz.
File metadata
- Download URL: airbench-0.1.1.tar.gz
- Upload date:
- Size: 9.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
168f53d08454870ecae488265d01792be647e50fddd06dfe87895982dd53931f
|
|
| MD5 |
f6081676a2acd59ce6a21490992e0c9c
|
|
| BLAKE2b-256 |
a3baf65e18556bf58d2e0cd351d0e30fca0f0e07b1e5064392a616ca63d4d743
|
