Create app.py

app.py

@@ -0,0 +1,44 @@
+from transformers import DetrImageProcessor, DetrForObjectDetection
+from PIL import Image, ImageDraw
+import torch
+import gradio as gr
+
+# Load model and processor
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
+
+FACE_CLASS_INDEX = 1  # COCO class ID for 'person'
+
+def detect_faces(img: Image.Image):
+    # Make a copy to draw on
+    img_draw = img.copy()
+    draw = ImageDraw.Draw(img_draw)
+
+    # Preprocess and predict
+    inputs = processor(images=img, return_tensors="pt")
+    outputs = model(**inputs)
+
+    # Get results
+    target_sizes = torch.tensor([img.size[::-1]])
+    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.8)[0]
+
+    count = 0
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        if label.item() == FACE_CLASS_INDEX:
+            count += 1
+            box = [round(i, 2) for i in box.tolist()]
+            draw.rectangle(box, outline="lime", width=3)
+            draw.text((box[0], box[1] - 10), f"{score:.2f}", fill="lime")
+
+    return img_draw, f"Total Persons Detected: {count}"
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=detect_faces,
+    inputs=gr.Image(type="pil"),
+    outputs=[gr.Image(type="pil"), gr.Text()],
+    title="Person Detection with DETR",
+    description="Uses DETR model to detect people (class 1 - COCO dataset). Note: not specialized for face detection."
+)
+
+iface.launch()