Update app.py

app.py

@@ -1,23 +1,25 @@
 from huggingface_hub import from_pretrained_fastai
 import gradio as gr
 from fastai.vision.all import *
+from icevision import models
 from icevision.all import *
 from icevision.models.checkpoint import *
 import PIL
 
 checkpoint_path = "efficientdetMapaches.pth"
-checkpoint_and_model = model_from_checkpoint(checkpoint_path, map_location=torch.device('cpu'))
-model = checkpoint_and_model["model"]
-model_type = checkpoint_and_model["model_type"]
-class_map = checkpoint_and_model["class_map"]
+model = models.ross.efficientdet.model(backbone=models.ross.efficientdet.backbones.tf_lite0(pretrained=True),
+                                       num_classes=2,
+                                       img_size=384)
 
-img_size = checkpoint_and_model["img_size"]
-valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(img_size), tfms.A.Normalize()])
+state_dict = torch.load('fasterRCNNkangaroo.pth')
+model.load_state_dict(state_dict)
+
+infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(384),tfms.A.Normalize()])
 
 # Definimos una función que se encarga de llevar a cabo las predicciones
 def predict(img):
     img = PIL.Image.open(img)
-    pred_dict  = model_type(img, valid_tfms, model.to("cpu"), class_map=class_map, detection_threshold=0.5)
+    pred_dict  = model_type(img, infer_tfms, model.to("cpu"), class_map=ClassMap(['raccoon']), detection_threshold=0.5)
     return pred_dict["img"]
     
 # Creamos la interfaz y la lanzamos.