Zero-Shot Image Classification
OpenCLIP
ONNX
English
clip
vision
aerial
drone
tracking
re-identification
Instructions to use llama-farm/llama-thunderdome-clip-aerial-vit-b16-v3-drone-fleet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use llama-farm/llama-thunderdome-clip-aerial-vit-b16-v3-drone-fleet with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:llama-farm/llama-thunderdome-clip-aerial-vit-b16-v3-drone-fleet') tokenizer = open_clip.get_tokenizer('hf-hub:llama-farm/llama-thunderdome-clip-aerial-vit-b16-v3-drone-fleet') - Notebooks
- Google Colab
- Kaggle
llama-thunderdome-clip-aerial-vit-b16-v3-drone-fleet / clip-aerial-vit-b16-v3-224.onnx.manifest.json
| { | |
| "source_checkpoint": "/tmp/v3-export/best.pt", | |
| "source_sha256": "cb65a3e7766453ef1282f7e2a9ffeb26f31e4c70307ccaffbb0aacf8b1434e33", | |
| "output_path": "/tmp/v3-export/clip-aerial-vit-b16-v3-224.onnx", | |
| "output_sha256": "2fdd5b46e33e11c42bc18ef0a35af9f1a4591027485a26ae8552650e57ceb3b3", | |
| "base_model": "ViT-B-16", | |
| "pretrained_baseline": "openai", | |
| "imgsz": 224, | |
| "opset": 14, | |
| "input_shape": [ | |
| 1, | |
| 3, | |
| 224, | |
| 224 | |
| ], | |
| "output_dim": null, | |
| "normalization": { | |
| "scheme": "CLIP", | |
| "mean_0_1": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "std_0_1": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "mean_0_255": [ | |
| 122.7709383, | |
| 116.7460125, | |
| 104.09373615 | |
| ], | |
| "std_0_255": [ | |
| 68.5005327, | |
| 66.6321579, | |
| 70.32316305 | |
| ] | |
| }, | |
| "exporter_version": "thunderdome.clip.export_onnx.v1", | |
| "exported_at": "2026-05-26T17:33:27.778970Z" | |
| } |