Update app.py

app.py

@@ -1,21 +1,25 @@
+from huggingface_hub import from_pretrained_fastai
 import gradio as gr
 from fastai.vision.all import *
 from icevision.all import *
 from icevision.models.checkpoint import *
 import PIL
 
-class_map = ClassMap(['kangaroo'])
+checkpoint_path = "fasterRCNNKangaroo.pth"
 model = models.torchvision.faster_rcnn.model(backbone=models.torchvision.faster_rcnn.backbones.resnet50_fpn,
-                                             num_classes=len(class_map))
-state_dict = torch.load('fasterRCNNKangaroo.pth')
+                                             num_classes=2)
+
+state_dict = torch.load(checkpoint_path, map_location=torch.device('cpu'))
 model.load_state_dict(state_dict)
 
-infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(size),tfms.A.Normalize()])
-size = 384
-def predict(img):
-    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']
+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.fromarray(img, "RGB")
+    pred_dict =  models.ross.efficientdet.end2end_detect(img, infer_tfms, model.to("cpu"), class_map=ClassMap(['kangaroo']), 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(type="pil"),examples=['00004.jpg','00083.jpg', '00119.jpg']).launch(share=False)
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=[gr.outputs.Image(type="pil", label="VFNet Inference")],
+             examples=['00004.jpg','00083.jpg', '00119.jpg']).launch(share=False)