Soft Threshold Weight Reparameterization for Learnable Sparsity
Open paper
Benchmark
Model
Rank
Results
network-pruning-on-imagenet-resnet-50-90-sparsity
STR
#7
Top-1 Accuracy: 74.31
network-pruning-on-imagenet-resnet-50-90-sparsity
GMP
#9
Top-1 Accuracy: 73.91
Rank counts only results with a code link.