Spaces:
Runtime error
Runtime error
add slider
Browse files
app.py
CHANGED
|
@@ -16,7 +16,8 @@ model.eval()
|
|
| 16 |
processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
|
| 17 |
|
| 18 |
|
| 19 |
-
def query_image(img, text_queries):
|
|
|
|
| 20 |
text_queries = text_queries.split(",")
|
| 21 |
inputs = processor(text=text_queries, images=img, return_tensors="pt").to(device)
|
| 22 |
|
|
@@ -30,8 +31,6 @@ def query_image(img, text_queries):
|
|
| 30 |
boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
|
| 31 |
|
| 32 |
img = cv2.resize(img, (768, 768), interpolation = cv2.INTER_AREA)
|
| 33 |
-
score_threshold = 0.11
|
| 34 |
-
|
| 35 |
font = cv2.FONT_HERSHEY_SIMPLEX
|
| 36 |
|
| 37 |
for box, score, label in zip(boxes, scores, labels):
|
|
@@ -55,15 +54,17 @@ Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_
|
|
| 55 |
introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
|
| 56 |
with Vision Transformers</a>.
|
| 57 |
\n\nYou can use OWL-ViT to query images with text descriptions of any object.
|
| 58 |
-
To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for.
|
|
|
|
| 59 |
\n\n<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab demo</a>
|
| 60 |
"""
|
| 61 |
demo = gr.Interface(
|
| 62 |
query_image,
|
| 63 |
-
inputs=[gr.Image(shape=(768, 768)), "text"],
|
| 64 |
outputs="image",
|
| 65 |
title="Zero-Shot Object Detection with OWL-ViT",
|
| 66 |
description=description,
|
| 67 |
-
examples=[["assets/astronaut.png", "human face, rocket, flag, nasa badge"], ["assets/coffee.png", "coffee mug, spoon, plate"]]
|
|
|
|
| 68 |
)
|
| 69 |
demo.launch(debug=True)
|
|
|
|
| 16 |
processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
|
| 17 |
|
| 18 |
|
| 19 |
+
def query_image(img, text_queries, score_threshold):
|
| 20 |
+
text_queries = text_queries
|
| 21 |
text_queries = text_queries.split(",")
|
| 22 |
inputs = processor(text=text_queries, images=img, return_tensors="pt").to(device)
|
| 23 |
|
|
|
|
| 31 |
boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
|
| 32 |
|
| 33 |
img = cv2.resize(img, (768, 768), interpolation = cv2.INTER_AREA)
|
|
|
|
|
|
|
| 34 |
font = cv2.FONT_HERSHEY_SIMPLEX
|
| 35 |
|
| 36 |
for box, score, label in zip(boxes, scores, labels):
|
|
|
|
| 54 |
introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
|
| 55 |
with Vision Transformers</a>.
|
| 56 |
\n\nYou can use OWL-ViT to query images with text descriptions of any object.
|
| 57 |
+
To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for. You
|
| 58 |
+
can also use the score threshold slider to set a threshold to filter out low probability prediction.
|
| 59 |
\n\n<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab demo</a>
|
| 60 |
"""
|
| 61 |
demo = gr.Interface(
|
| 62 |
query_image,
|
| 63 |
+
inputs=[gr.Image(shape=(768, 768)), "text", gr.Slider(0, 1, value=0.1),],
|
| 64 |
outputs="image",
|
| 65 |
title="Zero-Shot Object Detection with OWL-ViT",
|
| 66 |
description=description,
|
| 67 |
+
examples=[["assets/astronaut.png", "human face, rocket, flag, nasa badge"], ["assets/coffee.png", "coffee mug, spoon, plate"]],
|
| 68 |
+
live=True
|
| 69 |
)
|
| 70 |
demo.launch(debug=True)
|