Commit
·
bb36f8e
1
Parent(s):
6e74e31
update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,13 @@ This repository provides five pretrained variants — Nano, Small, Medium, Large
|
|
| 30 |
|
| 31 |
</div>
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## D-FINE Variants
|
| 34 |
|
| 35 |
The D-FINE family includes five model sizes trained on the [L&A Pucks Dataset](https://huggingface.co/datasets/Laudando-Associates-LLC/pucks), each offering a different balance between model size and detection accuracy.
|
|
@@ -72,7 +79,7 @@ model = AutoModel.from_pretrained(f"Laudando-Associates-LLC/d-fine-nano", trust_
|
|
| 72 |
# Process the image, reize and pad
|
| 73 |
inputs = processor(image)
|
| 74 |
|
| 75 |
-
# Run
|
| 76 |
outputs = model(**inputs, conf_threshold=0.4)
|
| 77 |
|
| 78 |
# Get outputs
|
|
|
|
| 30 |
|
| 31 |
</div>
|
| 32 |
|
| 33 |
+
## Try it in the Browser
|
| 34 |
+
|
| 35 |
+
You can test the model using our interactive Gradio demo:
|
| 36 |
+
|
| 37 |
+
[](https://huggingface.co/spaces/Laudando-Associates-LLC/d-fine-demo)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
## D-FINE Variants
|
| 41 |
|
| 42 |
The D-FINE family includes five model sizes trained on the [L&A Pucks Dataset](https://huggingface.co/datasets/Laudando-Associates-LLC/pucks), each offering a different balance between model size and detection accuracy.
|
|
|
|
| 79 |
# Process the image, reize and pad
|
| 80 |
inputs = processor(image)
|
| 81 |
|
| 82 |
+
# Run inference
|
| 83 |
outputs = model(**inputs, conf_threshold=0.4)
|
| 84 |
|
| 85 |
# Get outputs
|