Update app.py

app.py

@@ -3,6 +3,10 @@ from dotenv import load_dotenv
 import google.generativeai as genai
 from pathlib import Path
 import gradio as gr
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
+from PIL import Image
+import requests
 
 # Load environment variables from .env file
 load_dotenv()
@@ -90,4 +94,28 @@ with gr.Blocks() as demo:
     upload_button.upload(fn=lambda files: files[0].name if files else None, inputs=[upload_button], outputs=image_output)
     generate_button.click(fn=process_generate, inputs=[upload_button], outputs=[image_output, file_output])
 
-demo.launch()
+demo.launch()
+
+
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# you can specify the revision tag if you don't want the timm dependency
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+
+# convert outputs (bounding boxes and class logits) to COCO API
+# let's only keep detections with score > 0.9
+target_sizes = torch.tensor([image.size[::-1]])
+results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
+
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+            f"Detected {model.config.id2label[label.item()]} with confidence "
+            f"{round(score.item(), 3)} at location {box}"
+    )