Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization
Pruning and quantization are core techniques used to reduce the inference costs of deep neural networks. Among the state-of-the-art pruning techniques, magnitude-based pruning algorithms have demonstrated consistent success in the reduction of both weight and feature map complexity. However, we find...
I tiakina i:
| Ngā kaituhi matua: | , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
MDPI AG
2022-08-01
|
| Rangatū: | Applied Sciences |
| Ngā marau: | |
| Urunga tuihono: | https://www.mdpi.com/2076-3417/12/15/7829 |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|