Instructions to use HichTala/draw2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HichTala/draw2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="HichTala/draw2")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("HichTala/draw2") model = AutoModelForImageClassification.from_pretrained("HichTala/draw2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add ONNX exports for the browser demo
#3
by AmineTorki - opened
Adds the ONNX exports used by the browser demo
Files
| file | size | notes |
|---|---|---|
onnx/ygo_yolo.onnx |
39 MB | YOLO-OBB detector |
onnx/vit_fp16.onnx |
193 MB | ViT classifier, FP16 |
onnx/vit_fp32.onnx |
386 MB | ViT classifier, FP32 |
onnx/cardnames_onnx.json |
2.2 MB | names keyed by ViT output index |
All are exported from the weights already in this repo, reproducibly, by docs/export_models.py in the website demo PR. |
Not included
HichTala changed pull request status to merged