RepVGG is a VGG-style convolutional architecture. It has the following advantages:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 3 | 23.08% |
Quantization | 2 | 15.38% |
Computational Efficiency | 1 | 7.69% |
Object Detection | 1 | 7.69% |
Speaker Recognition | 1 | 7.69% |
Classification | 1 | 7.69% |
Image Segmentation | 1 | 7.69% |
Multi-Task Learning | 1 | 7.69% |
Network Pruning | 1 | 7.69% |