Update app.py

app.py

@@ -2,24 +2,50 @@ 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
 
-checkpoint_path = "fasterRCNN_resnet18_Raccoons.pth"
-model = models.torchvision.faster_rcnn.model(backbone=models.torchvision.faster_rcnn.backbones.resnet18_fpn(pretrained=True),
-                                       num_classes=2)
+class_map = ['raccoon']
 
-state_dict = torch.load(checkpoint_path, map_location=torch.device('cpu'))
-model.load_state_dict(state_dict)
+presize = 512
+size = 384
 
-infer_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(384),tfms.A.Normalize()])
+train_tfms = tfms.A.Adapter(
+    [*tfms.A.aug_tfms(size=size, presize=presize), tfms.A.Normalize()]
+)
+valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(size), 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.torchvision.faster_rcnn.end2end_detect(img, infer_tfms, model.to("cpu"), class_map=ClassMap(['raccoon']), 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.Image(type="pil", label="VFNet Inference")],
-             examples=['raccoon1.jpg','raccoon2.jpg']).launch(share=False)
+model1 = models.torchvision.faster_rcnn.model(backbone=models.torchvision.faster_rcnn.backbones.resnet18_fpn(pretrained=True), num_classes=len(class_map))
+state_dict = torch.load('fasterRCNN_resnet18_Raccoons.pth', map_location=torch.device('cpu'))
+model1.load_state_dict(state_dict)
+
+def show_preds(input_image, display_label, display_bbox, detection_threshold):
+
+    if detection_threshold==0: detection_threshold=0.5
+
+    img = PIL.Image.fromarray(input_image, 'RGB')
+
+    pred_dict  = models.torchvision.faster_rcnn.end2end_detect(img, valid_tfms, model1, class_map=class_map, detection_threshold=detection_threshold,
+                                           display_label=display_label, display_bbox=display_bbox, return_img=True, 
+                                           font_size=16, label_color="#FF59D6")
+
+    return pred_dict['img']
+
+# display_chkbox = gr.inputs.CheckboxGroup(["Label", "BBox"], label="Display", default=True)
+display_chkbox_label = gr.inputs.Checkbox(label="Label", default=True)
+display_chkbox_box = gr.inputs.Checkbox(label="Box", default=True)
+
+detection_threshold_slider = gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5, label="Detection Threshold")
+
+outputs = gr.outputs.Image(type="pil")
+
+# Option 1: Get an image from local drive
+gr_interface = gr.Interface(fn=show_preds, inputs=["image", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, examples=['raccoon1.jpg','raccoon2.jpg'])
+
+# #  Option 2: Grab an image from a webcam
+# gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=False)
+
+# #  Option 3: Continuous image stream from the webcam
+# gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=True)
+
+
+gr_interface.launch(inline=False, share=False, debug=True)