Designing Network Design Spaces

Open paper
Benchmark Model Rank Results
image-classification-on-imagenet-v2RegNetY-8.0GF#44Top 1 Accuracy: 68.7
image-classification-on-imagenetRegNetY-8.0GF#767Top 1 Accuracy: 79.9%Number of params: 39.2MGFLOPs: 8
image-classification-on-imagenetRegNetY-4.0GF#793Top 1 Accuracy: 79.4%Number of params: 20.6MGFLOPs: 4
image-classification-on-imagenetRegNetY-1.6GF#891Top 1 Accuracy: 78%Number of params: 11.2MGFLOPs: 1.6
image-classification-on-imagenetRegNetY-800MF#960Top 1 Accuracy: 76.3%Number of params: 6.3MGFLOPs: 0.8
image-classification-on-imagenetRegNetY-600MF#986Top 1 Accuracy: 75.5%Number of params: 6.1MGFLOPs: 0.6
image-classification-on-imagenetRegNetY-400MF#1023Top 1 Accuracy: 74.1%Number of params: 4.3MGFLOPs: 0.4

Rank counts only results with a code link.