Update app.py

app.py

@@ -1,19 +1,49 @@
 from fastai.vision.all import *
 import gradio as gr
-
+import torchvision.transforms as transforms
 
 # Cargamos el learner
-learn = load_learner('export.pkl')
+learn = load_learner('best_model.pkl')
 
 # Definimos las etiquetas de nuestro modelo
 labels = learn.dls.vocab
 
+def transform_image(image, device):
+    my_transforms = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize(
+                                            [0.485, 0.456, 0.406],
+                                            [0.229, 0.224, 0.225])])
+    image_aux = image
+    return my_transforms(image_aux).unsqueeze(0).to(device)
+
+def mask_to_img(mask):
+  mask[mask == 1] = 255 # grape
+  mask[mask == 2] = 150 # leaves
+  mask[mask == 3] = 74 # pole
+  mask[mask == 4] = 25 # wood
+  mask=np.reshape(mask,(480,640))
+
+  return mask
 
 # Definimos una función que se encarga de llevar a cabo las predicciones
 def predict(img):
-    img = PILImage.create(img)
-    pred,pred_idx,probs = learn.predict(img)
-    return {labels[i]: float(probs[i]) for i in range(len(labels))}
+  device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
+  model = learn.cpu()
+  model.eval()
+
+  image = transforms.Resize((480,640))(img)
+  tensor = transform_image(image, device)
+
+  model.to(device)
+  with torch.no_grad():
+      outputs = model(tensor)
+
+  outputs = torch.argmax(outputs,1)
+  
+  mask = np.array(outputs.cpu())
+  mask = mask_to_img(mask)
+
+  return Image.fromarray(mask.astype('uint8'))
     
 # Creamos la interfaz y la lanzamos. 
-gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=gr.outputs.Label(num_top_classes=3),examples=['1002_5866_6582.jpg','1038_31199_2068.jpg']).launch(share=False)
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=gr.outputs.Image(shape=(128,128)),examples=['1002_5866_6582.jpg','1038_31199_2068.jpg']).launch(share=False)