Published February 12, 2024
| Version a2q_cifar10_r1
Software
Open
Xilinx/brevitas: A2Q+ CIFAR10 model release
Creators
- 1. @AMD
- 2. Zama.ai
- 3. AMD
- 4. @Quansight
- 5. @AMD Research Labs
- 6. National University of Science and Technology
- 7. unpaired.
- 8. @zama-ai
- 9. UC San Diego
Description
This release contains training code and pre-trained weights to demonstrate accumulator-aware quantization (A2Q) on an image classification task. Code is also provided to demonstrate Euclidean projection-based weight initialization (EP-init) as proposed in our paper "A2Q+: Improving Accumulator-Aware Weight Quantization".
Find the associated docs at https://github.com/Xilinx/brevitas/tree/a2q_cifar10_r1/src/brevitas_examples/imagenet_classification/a2q.
Files
Xilinx/brevitas-a2q_cifar10_r1.zip
Files
(3.3 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:9b79bd1f69aae77875a9a9121c7d53ad
|
3.3 MB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/Xilinx/brevitas/tree/a2q_cifar10_r1 (URL)