open proxydet

app.py

@@ -1,9 +1,12 @@
 import torch
 import cv2
+import os
 import gradio as gr
 import numpy as np
 from transformers import OwlViTProcessor, OwlViTForObjectDetection
 
+def setup():
+    os.system("python3 -m pip install 'git+https://github.com/facebookresearch/detectron2.git'")
 
 # Use GPU if available
 if torch.cuda.is_available():
@@ -48,29 +51,31 @@ def query_image(img, text_queries, score_threshold):
             )
     return img
 
+if __name__ == "__main__":
+    setup()
 
-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. You
-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: *"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",
-    title="Zero-Shot Object Detection with OWL-ViT",
-    description=description,
-    examples=[
-        ["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()
+    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. You
+    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: *"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",
+        title="Zero-Shot Object Detection with OWL-ViT",
+        description=description,
+        examples=[
+            ["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()