Network Pruning On Imagenet Resnet 50 90

Métriques

Top-1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Feather	76.93	Feather: An Elegant Solution to Effective DNN Sparsification
Spartan	76.17	Spartan: Differentiable Sparsity via Regularized Transportation
ST-3	76.03	Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?
AC/DC	75.64	AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
CS	75.5	Winning the Lottery with Continuous Sparsification
ProbMask	74.68	Effective Sparsification of Neural Networks with Global Sparsity Constraint
STR	74.31	Soft Threshold Weight Reparameterization for Learnable Sparsity
DNW	74	Discovering Neural Wirings
GMP	73.91	Soft Threshold Weight Reparameterization for Learnable Sparsity

0 of 9 row(s) selected.