Update app.py

app.py

@@ -1,21 +1,27 @@
 from huggingface_hub import from_pretrained_fastai
 import gradio as gr
 from fastai.vision.all import *
-
-
+from PIL import ImageFile
+from icevision.all import *
 
 # repo_id = "YOUR_USERNAME/YOUR_LEARNER_NAME"
 repo_id = "el-filatova/Practica2"
 
 learner = from_pretrained_fastai(repo_id)
 labels = learner.dls.vocab
+class_map = ClassMap(['kangaroo'])
+state_dict = torch.load('fasterRCNNFkangaroo.pth')
+model = models.torchvision.faster_rcnn.model(num_classes=len(class_map))
+model.load_state_dict(state_dict)
 
 # Definimos una función que se encarga de llevar a cabo las predicciones
 def predict(img):
-    #img = PILImage.create(img)
-    pred,pred_idx,probs = learner.predict(img)
-    return {labels[i]: float(probs[i]) for i in range(len(labels))}
+    img = PILImage.create(img)
+    infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(size),tfms.A.Normalize()])
+    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
+
     
 # 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=['image.jpg','image1.jpg', 'image2.jpg']).launch(share=False)
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=gr.outputs.Label(num_top_classes=3),examples=['image.jpg']).launch(share=False)