FBNet Block is an image model block used in the FBNet architectures discovered through DNAS neural architecture search. The basic building blocks employed are depthwise convolutions and a residual connection.
Source: FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 3 | 15.79% |
Script Generation | 2 | 10.53% |
Semantic Segmentation | 2 | 10.53% |
Meta-Learning | 1 | 5.26% |
Point Cloud Completion | 1 | 5.26% |
Autonomous Driving | 1 | 5.26% |
Image Segmentation | 1 | 5.26% |
Scene Segmentation | 1 | 5.26% |
Quantization | 1 | 5.26% |