Instructions to use PekingU/rtdetr_r34vd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PekingU/rtdetr_r34vd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="PekingU/rtdetr_r34vd")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("PekingU/rtdetr_r34vd") model = AutoModelForObjectDetection.from_pretrained("PekingU/rtdetr_r34vd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update freezing
Browse filesFreezing disabled by default :
https://github.com/huggingface/transformers/issues/32604
- config.json +1 -0
config.json
CHANGED
|
@@ -28,6 +28,7 @@
|
|
| 28 |
4
|
| 29 |
]
|
| 30 |
},
|
|
|
|
| 31 |
"backbone_kwargs": null,
|
| 32 |
"batch_norm_eps": 1e-05,
|
| 33 |
"box_noise_scale": 1.0,
|
|
|
|
| 28 |
4
|
| 29 |
]
|
| 30 |
},
|
| 31 |
+
"freeze_backbone_batch_norms": false,
|
| 32 |
"backbone_kwargs": null,
|
| 33 |
"batch_norm_eps": 1e-05,
|
| 34 |
"box_noise_scale": 1.0,
|