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...

Täydet tiedot

Bibliografiset tiedot

Päätekijät:	Xinyu Zhang, Ian Colbert, Srinjoy Das
Aineistotyyppi:	Artigo
Kieli:	Inglês
Julkaistu:	MDPI AG 2022-08-01
Sarja:	Applied Sciences
Aiheet:	channel pruning layerwise pruning quantization joint pruning
Linkit:	https://www.mdpi.com/2076-3417/12/15/7829
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!