Create app.py

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
+import torch
+from PIL import Image
+import requests
+import torchvision.transforms as T
+
+# Cargar modelo
+checkpoint = "PablitoGil14/Practica2"
+processor = AutoImageProcessor.from_pretrained(checkpoint)
+model = AutoModelForObjectDetection.from_pretrained(checkpoint)
+
+# Función de predicción
+def detectar_canguros(imagen):
+    inputs = processor(images=imagen, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # Filtrar predicciones con una confianza > 0.7
+    target_sizes = torch.tensor([imagen.size[::-1]])
+    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.05)[0]
+
+    draw = Image.fromarray(imagen).convert("RGB")
+    draw_ctx = ImageDraw.Draw(draw)
+    
+    for box, score, label in zip(results["boxes"], results["scores"], results["labels"]):
+        box = [round(i, 2) for i in box.tolist()]
+        draw_ctx.rectangle(box, outline="red", width=3)
+        draw_ctx.text((box[0], box[1]), f"{model.config.id2label[label.item()]}: {round(score.item(), 2)}", fill="red")
+
+    return draw
+
+# Interfaz Gradio
+gr.Interface(
+    fn=detectar_canguros,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="Detector de Canguros",
+    description="Sube una imagen y detecta canguros usando el modelo YOLOS entrenado"
+).launch()