Use gr.AnnotatedImage (#1)

- Use gr.AnnotatedImage (d758ed068747f853c3c1918c0f5f402ad1816f79)


Co-authored-by: hysts <hysts@users.noreply.huggingface.co>

app.py

@@ -1,7 +1,5 @@
 import torch
-import cv2
 import gradio as gr
-import numpy as np
 from transformers import OwlViTProcessor, OwlViTForObjectDetection
 
 
@@ -26,52 +24,43 @@ def query_image(img, text_queries, score_threshold):
 
     with torch.no_grad():
         outputs = model(**inputs)
-    
+
     outputs.logits = outputs.logits.cpu()
-    outputs.pred_boxes = outputs.pred_boxes.cpu() 
+    outputs.pred_boxes = outputs.pred_boxes.cpu()
     results = processor.post_process_object_detection(outputs=outputs, target_sizes=target_sizes)
     boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
 
-    font = cv2.FONT_HERSHEY_SIMPLEX
-
+    result_labels = []
     for box, score, label in zip(boxes, scores, labels):
         box = [int(i) for i in box.tolist()]
-
-        if score >= score_threshold:
-            img = cv2.rectangle(img, box[:2], box[2:], (255,0,0), 5)
-            if box[3] + 25 > 768:
-                y = box[3] - 10
-            else:
-                y = box[3] + 25
-                
-            img = cv2.putText(
-                img, text_queries[label], (box[0], y), font, 1, (255,0,0), 2, cv2.LINE_AA
-            )
-    return img
+        if score < score_threshold:
+            continue
+        result_labels.append((box, text_queries[label.item()]))
+    return img, result_labels
 
 
 description = """
-Try this demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlv2">OWLv2</a>, 
-introduced in <a href="https://arxiv.org/abs/2306.09683">Scaling Open-Vocabulary Object Detection</a>. 
-\n\n Compared to OWLVIT, OWLv2 performs better both in yield and performance (average precision). 
-You can use OWLv2 to query images with text descriptions of any object. 
+Try this demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlv2">OWLv2</a>,
+introduced in <a href="https://arxiv.org/abs/2306.09683">Scaling Open-Vocabulary Object Detection</a>.
+\n\n Compared to OWLVIT, OWLv2 performs better both in yield and performance (average precision).
+You can use OWLv2 to query images with text descriptions of any object.
 To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for. You
-can also use the score threshold slider to set a threshold to filter out low probability predictions. 
+can also use the score threshold slider to set a threshold to filter out low probability predictions.
 \n\nOWL-ViT is trained on text templates,
-hence you can get better predictions by querying the image with text templates used in training the original model: e.g. *"photo of a star-spangled banner"*, 
+hence you can get better predictions by querying the image with text templates used in training the original model: e.g. *"photo of a star-spangled banner"*,
 *"image of a shoe"*. Refer to the <a href="https://arxiv.org/abs/2103.00020">CLIP</a> paper to see the full list of text templates used to augment the training data.
 \n\n<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab demo</a>
 """
 demo = gr.Interface(
-    query_image, 
-    inputs=[gr.Image(), "text", gr.Slider(0, 1, value=0.1)], 
-    outputs="image",
+    query_image,
+    inputs=[gr.Image(), "text", gr.Slider(0, 1, value=0.1)],
+    outputs="annotatedimage",
     title="Zero-Shot Object Detection with OWLv2",
     description=description,
     examples=[
-        ["assets/astronaut.png", "human face, rocket, star-spangled banner, nasa badge", 0.11], 
+        ["assets/astronaut.png", "human face, rocket, star-spangled banner, nasa badge", 0.11],
         ["assets/coffee.png", "coffee mug, spoon, plate", 0.1],
         ["assets/butterflies.jpeg", "orange butterfly", 0.3],
     ],
 )
-demo.launch()
+demo.launch()

requirements.txt

@@ -2,5 +2,4 @@ numpy>=1.18.5
 torch>=1.7.0
 torchvision>=0.8.1
 git+https://github.com/nielsrogge/transformers@add_owlv2
-opencv-python
 scipy