Instructions to use jozhang97/deta-swin-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jozhang97/deta-swin-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="jozhang97/deta-swin-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForObjectDetection model = AutoModelForObjectDetection.from_pretrained("jozhang97/deta-swin-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload config.json
Browse files- config.json +4 -3
config.json
CHANGED
|
@@ -6,8 +6,9 @@
|
|
| 6 |
"DetaForObjectDetection"
|
| 7 |
],
|
| 8 |
"assign_first_stage": true,
|
|
|
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
-
"auxiliary_loss":
|
| 11 |
"backbone_config": {
|
| 12 |
"_name_or_path": "",
|
| 13 |
"add_cross_attention": false,
|
|
@@ -322,6 +323,6 @@
|
|
| 322 |
"torch_dtype": "float32",
|
| 323 |
"transformers_version": null,
|
| 324 |
"two_stage": true,
|
| 325 |
-
"two_stage_num_proposals":
|
| 326 |
"with_box_refine": true
|
| 327 |
-
}
|
|
|
|
| 6 |
"DetaForObjectDetection"
|
| 7 |
],
|
| 8 |
"assign_first_stage": true,
|
| 9 |
+
"assign_second_stage": true,
|
| 10 |
"attention_dropout": 0.0,
|
| 11 |
+
"auxiliary_loss": true,
|
| 12 |
"backbone_config": {
|
| 13 |
"_name_or_path": "",
|
| 14 |
"add_cross_attention": false,
|
|
|
|
| 323 |
"torch_dtype": "float32",
|
| 324 |
"transformers_version": null,
|
| 325 |
"two_stage": true,
|
| 326 |
+
"two_stage_num_proposals": 900,
|
| 327 |
"with_box_refine": true
|
| 328 |
+
}
|