Upload 3 files

README.md

@@ -1,13 +1,8 @@
----
-title: Image Object Detection
-emoji: 💻
-colorFrom: purple
-colorTo: red
-sdk: gradio
-sdk_version: 4.36.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+title: Image Object Detection
+emoji: 🚀
+colorFrom: green
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.28.3
+app_file: app.py
+pinned: false

app.py

@@ -0,0 +1,32 @@
+from base64 import b64decode
+from io import BytesIO
+
+import gradio as gr
+import spaces
+from PIL import Image
+from transformers import pipeline
+
+model = pipeline(
+    task="zero-shot-object-detection",
+    model="google/owlvit-large-patch14",
+)
+
+
+@spaces.GPU
+def predict(base64: str, texts: str):
+    decoded_img = b64decode(base64)
+    image_stream = BytesIO(decoded_img)
+    img = Image.open(image_stream)
+    predictions = model(img, text_queries=["".join(list(term)).strip() for term in texts.split(",")])
+    return predictions
+
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Text(label="Image (B64)"),
+        gr.Text(label="Queries", placeholder="A photo of a dog,A photo of a cat")
+    ],
+    outputs=gr.JSON(label="Predictions"),
+)
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+loguru
+torch==2.2.0
+transformers==4.40.1
+pillow==10.3.0