test

app.py

@@ -1,26 +1,20 @@
 import gradio as gr
 from diffusers import DDPMPipeline
+from transformers import pipeline
 import torch
 
-# Cargar el modelo DDPM preentrenado
-ddpm = DDPMPipeline.from_pretrained("google/ddpm-cat-256", use_safetensors=True).to("cuda")
+pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
 
-def generate_cat_image(num_inference_steps):
-    # Generar una imagen de gato
-    with torch.no_grad():
-        image = ddpm(num_inference_steps=num_inference_steps)["sample"][0]
-    
-    # Convertir la imagen de tensor a PIL para mostrarla en Gradio
-    image = image.permute(1, 2, 0).cpu().numpy()
-    
-    return image
+def predict(input_img):
+    predictions = pipeline(input_img)
+    return input_img, {p["label"]: p["score"] for p in predictions} 
 
-# Interfaz de Gradio
-gr_interface = gr.Interface(fn=generate_cat_image, 
-                            inputs=gr.inputs.Slider(minimum=10, maximum=100, step=1, default=50, label="Número de Pasos de Inferencia"), 
-                            outputs="image", 
-                            title="Generador de Imágenes de Gatos",
-                            description="Modelo DDPM para generar imágenes de gatos.")
+gradio_app = gr.Interface(
+    predict,
+    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
+    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
+    title="Hot Dog? Or Not?",
+)
 
 if __name__ == "__main__":
-    gr_interface.launch()
+    gradio_app.launch()

requirements.txt

@@ -1,3 +1,4 @@
 diffusers
 gradio
-torch
+torch
+transformers