Update app.py

app.py

@@ -1,23 +1,19 @@
 from fastai.vision.all import *
 from icevision.all import *
-import PIL
 import gradio as gr
 
-# Cargamos el learner
-learn = load_learner('model.pth')
-
 # Definimos una función que se encarga de llevar a cabo las predicciones
 def predict(img):
-    class_map = ['Kangaroo']
+    class_map = ClassMap(['Kangaroo'])
     model = models.torchvision.faster_rcnn.model(backbone=models.torchvision.faster_rcnn.backbones.resnet18_fpn, num_classes=len(class_map))
     state_dict = torch.load('model.pth')
     model.load_state_dict(state_dict)
     
-    infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(size),tfms.A.Normalize()])
+    infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(384),tfms.A.Normalize()])
     
-    img = PIL.Image.open('kangarooc.jpg')
+    img = PILImage.create(img)
     pred_dict  = models.torchvision.faster_rcnn.end2end_detect(img, infer_tfms, model.to("cpu"), class_map=class_map, detection_threshold=0.5)
     return pred_dict['img']
     
 # 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=['kangarooc.jpg']).launch(share=False)
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=gr.outputs.Image(shape=(128, 128)),examples=['kangarooc.jpg']).launch(share=False)