fix bug

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/Helvatica.ttc filter=lfs diff=lfs merge=lfs -text

app.py

@@ -13,14 +13,14 @@ def query_image(img, text_queries):
     inputs = processor(text=text_queries, images=img, return_tensors="pt")
 
     with torch.no_grad():
-      outputs = model(**inputs)
+        outputs = model(**inputs)
 
     target_sizes = torch.Tensor([[768, 768]])
     results = processor.post_process(outputs=outputs, target_sizes=target_sizes)
     boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
 
     draw = ImageDraw.Draw(img)  
-    font = ImageFont.truetype("/System/Library/Fonts/Helvetica.ttc", size=22)
+    font = ImageFont.truetype("assets/Helvetica.ttc", size=22)
 
     score_threshold = 0.1
     for box, score, label in zip(boxes, scores, labels):
@@ -35,19 +35,20 @@ def query_image(img, text_queries):
     return img
 
 
-description = description = """
+description = """
 Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>, 
 introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
 with Vision Transformers</a>. 
 \n\nYou can use OWL-ViT 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. 
+\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(shape=(768, 768), type="pil"), "text"], 
     outputs="image",
     title="Zero-Shot Object Detection with OWL-ViT",
-    description="You can use OWL-ViT to query images with text descriptions of any object",
-    examples=[["astronaut.png", "human face, rocket, flag, nasa badge"], ["coffee.png", "coffee mug, spoon, plate"]]
+    description=description,
+    examples=[["assets/astronaut.png", "human face, rocket, flag, nasa badge"], ["assets/coffee.png", "coffee mug, spoon, plate"]]
 )
 demo.launch(debug=True)

assets/Helvatica.ttc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cb0b7e8b3e53b29d356bfae0663075fdd20e45ad94b56e1b77cca117e415e0
+size 2356684