NAS-quantization
April 10, 2019 ยท View on GitHub
The code for Joint Neural Architecture Search and Quantization
Requirements
- pytorch 0.4.1
- python 3.6
- tensorboardX
Search
python train_search.py --data 'path_to_dataset'
After search
For CIFAR-10 models, we rely on the traing code from DARTS to train and evaluate the searched network.
For ImageNet models, we rely on the traing code from RENASNet to train and evaluate the searched network.
Acknowledgements
Our implementation about quantization highly replies on the quantized_distillation.
We also thanks for the inspiring work DARTS.