RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything
730
stars
55
forks
source link
How to train your own dataset? What is the structure and form of the composition of the dataset? #17
Closed
lucy11111111 closed 11 months ago
Thanks. You can arrange your dataset like ImageNet, and then set --data-path to your own dataset.