adirik commited on
Commit
fbfcc0e
β€’
1 Parent(s): ecb7e39
.DS_Store ADDED
Binary file (6.15 kB). View file
 
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ assets/Helvatica.ttc filter=lfs diff=lfs merge=lfs -text
app.py CHANGED
@@ -13,14 +13,14 @@ def query_image(img, text_queries):
13
  inputs = processor(text=text_queries, images=img, return_tensors="pt")
14
 
15
  with torch.no_grad():
16
- outputs = model(**inputs)
17
 
18
  target_sizes = torch.Tensor([[768, 768]])
19
  results = processor.post_process(outputs=outputs, target_sizes=target_sizes)
20
  boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
21
 
22
  draw = ImageDraw.Draw(img)
23
- font = ImageFont.truetype("/System/Library/Fonts/Helvetica.ttc", size=22)
24
 
25
  score_threshold = 0.1
26
  for box, score, label in zip(boxes, scores, labels):
@@ -35,19 +35,20 @@ def query_image(img, text_queries):
35
  return img
36
 
37
 
38
- description = description = """
39
  Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>,
40
  introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
41
  with Vision Transformers</a>.
42
  \n\nYou can use OWL-ViT to query images with text descriptions of any object.
43
  To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for.
 
44
  """
45
  demo = gr.Interface(
46
  query_image,
47
  inputs=[gr.Image(shape=(768, 768), type="pil"), "text"],
48
  outputs="image",
49
  title="Zero-Shot Object Detection with OWL-ViT",
50
- description="You can use OWL-ViT to query images with text descriptions of any object",
51
- examples=[["astronaut.png", "human face, rocket, flag, nasa badge"], ["coffee.png", "coffee mug, spoon, plate"]]
52
  )
53
  demo.launch(debug=True)
 
13
  inputs = processor(text=text_queries, images=img, return_tensors="pt")
14
 
15
  with torch.no_grad():
16
+ outputs = model(**inputs)
17
 
18
  target_sizes = torch.Tensor([[768, 768]])
19
  results = processor.post_process(outputs=outputs, target_sizes=target_sizes)
20
  boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
21
 
22
  draw = ImageDraw.Draw(img)
23
+ font = ImageFont.truetype("assets/Helvetica.ttc", size=22)
24
 
25
  score_threshold = 0.1
26
  for box, score, label in zip(boxes, scores, labels):
 
35
  return img
36
 
37
 
38
+ description = """
39
  Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>,
40
  introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
41
  with Vision Transformers</a>.
42
  \n\nYou can use OWL-ViT to query images with text descriptions of any object.
43
  To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for.
44
+ \n\n<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab demo</a>
45
  """
46
  demo = gr.Interface(
47
  query_image,
48
  inputs=[gr.Image(shape=(768, 768), type="pil"), "text"],
49
  outputs="image",
50
  title="Zero-Shot Object Detection with OWL-ViT",
51
+ description=description,
52
+ examples=[["assets/astronaut.png", "human face, rocket, flag, nasa badge"], ["assets/coffee.png", "coffee mug, spoon, plate"]]
53
  )
54
  demo.launch(debug=True)
assets/.DS_Store ADDED
Binary file (6.15 kB). View file
 
assets/Helvatica.ttc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4cb0b7e8b3e53b29d356bfae0663075fdd20e45ad94b56e1b77cca117e415e0
3
+ size 2356684
astronaut.png β†’ assets/astronaut.png RENAMED
File without changes
coffee.png β†’ assets/coffee.png RENAMED
File without changes