|
功能模块
|
算法
|
教程与文档
|
剪裁
|
-
Sensitivity Pruner: Li H , Kadav A , Durdanovic I , et al. Pruning Filters for Efficient ConvNets[J]. 2016.
-
AMC Pruner: He, Yihui , et al. "AMC: AutoML for Model Compression and Acceleration on Mobile Devices." (2018).
-
FPGM Pruner: He Y , Liu P , Wang Z , et al. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration[C]// IEEE/CVF Conference on Computer Vision & Pattern Recognition. IEEE, 2019.
-
Slim Pruner: Liu Z , Li J , Shen Z , et al. Learning Efficient Convolutional Networks through Network Slimming[J]. 2017.
-
Opt Slim Pruner: Ye Y , You G , Fwu J K , et al. Channel Pruning via Optimal Thresholding[J]. 2020.
|
|
|
量化
|
|
|
|
蒸馏
|
-
Knowledge Distillation: Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. "Distilling the knowledge in a neural network." arXiv preprint arXiv:1503.02531 (2015).
-
FSP Knowledge Distillation: Yim, Junho, et al. "A gift from knowledge distillation: Fast optimization, network minimization and transfer learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.
-
YOLO Knowledge Distillation: Mehta, Rakesh, and Cemalettin Ozturk. "Object detection at 200 frames per second." Proceedings of the European Conference on Computer Vision (ECCV). 2018.
-
DML: Zhang, Ying, et al. "Deep mutual learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
|
|
|
模型结构搜索(NAS)
|
|
|