Instructions to use Thomasboosinger/owlvit-base-patch32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Thomasboosinger/owlvit-base-patch32 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-object-detection", model="Thomasboosinger/owlvit-base-patch32")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection processor = AutoProcessor.from_pretrained("Thomasboosinger/owlvit-base-patch32") model = AutoModelForZeroShotObjectDetection.from_pretrained("Thomasboosinger/owlvit-base-patch32") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -29,7 +29,7 @@ class EndpointHandler():
|
|
| 29 |
candidate_labels=inputs["candidates"]
|
| 30 |
|
| 31 |
# Correctly passing the image and candidate labels to the pipeline
|
| 32 |
-
detection_results = self.pipeline(image=image, candidate_labels=inputs["candidates"]
|
| 33 |
|
| 34 |
# Adjusting the return statement to match the expected output structure
|
| 35 |
return detection_results
|
|
|
|
| 29 |
candidate_labels=inputs["candidates"]
|
| 30 |
|
| 31 |
# Correctly passing the image and candidate labels to the pipeline
|
| 32 |
+
detection_results = self.pipeline(image=image, candidate_labels=inputs["candidates"])
|
| 33 |
|
| 34 |
# Adjusting the return statement to match the expected output structure
|
| 35 |
return detection_results
|