Update app.py

app.py

@@ -5,7 +5,7 @@ from pathlib import Path
 import gradio as gr
 from transformers import DetrImageProcessor, DetrForObjectDetection
 import torch
-from PIL import Image
+from PIL import Image, ImageDraw
 import requests
 
 # Load environment variables from .env file
@@ -78,6 +78,25 @@ def upload_file(files):
     response = generate_gemini_response(input_prompt, file_paths[0])
     return file_paths[0], response
 
+# Object detection part
+def detect_objects(image):
+    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)
+
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
+
+    draw = ImageDraw.Draw(image)
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        box = [round(i, 2) for i in box.tolist()]
+        draw.rectangle(box, outline="red", width=3)
+        draw.text((box[0], box[1]), f"{model.config.id2label[label.item()]}: {round(score.item(), 2)}", fill="red")
+    
+    return image
+
 with gr.Blocks() as demo:
     header = gr.Label("RADARPICK: Vous avez été radarisé!")
     image_output = gr.Image()
@@ -89,33 +108,12 @@ with gr.Blocks() as demo:
     def process_generate(files):
         if not files:
             return None, "Image not uploaded"
-        return upload_file(files)
+        file_path = files[0].name
+        image = Image.open(file_path)
+        detected_image = detect_objects(image)
+        return detected_image, upload_file(files)[1]
     
     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()
-
-
-
-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}"
-    )