Views
No views yet
| Parameter | Value |
|---|---|
| Image Size | 512x512 |
| Patch Size | 16x16 |
| Hidden Dim | 192 |
| Layers | 12 |
| Heads | 3 |
| MLP Dim | 768 |
best_coco_bbox_mAP_epoch_12.pth1from mmdet.apis import init_detector, inference_detector
2
3config_file = 'detection/configs/faster_rcnn_simple_vit_tiny_coco.py'
4checkpoint_file = 'best_coco_bbox_mAP_epoch_12.pth'
5
6model = init_detector(config_file, checkpoint_file, device='cuda:0')
7result = inference_detector(model, 'test.jpg')1@misc{vit_detection_coco,
2 title={Vision Transformer Object Detection with Simple ViT},
3 year={2026},
4 publisher={Hugging Face},
5}