Update app.py

app.py

@@ -42,7 +42,8 @@ configs = {
     "MEAN": (0.485, 0.456, 0.406),
     "STD":  (0.229, 0.224, 0.225),
 
-    "DEFAULT_BACKBONE": "EfficientNet(b3)"
+    "DEFAULT_BACKBONE": "EfficientNet(b3)",
+    "THRESHOLD": 0.5
     }
 
 """### Define helper functions"""
@@ -210,7 +211,7 @@ class modelModule(torch_light.LightningModule):
 
 """### Create function for running inference (i.e., assistive medical diagnosis)"""
 
-def run_diagnosis(backbone_name, input_image, preprocess_fn = None, Idx2labels=None):
+def run_diagnosis(backbone_name, input_image, preprocess_fn = None, Idx2labels=None, threshold = configs["THRESHOLD"]):
 
     input_tensor = preprocess_fn(input_image)
     input_tensor = input_tensor.unsqueeze(dim = 0)
@@ -263,7 +264,7 @@ example_list = [
 # example_list = [['/content/new_labels.csv',"ResNet50"]]
 
 gradio_app = gradio.Interface(
-    fn     = partial(run_diagnosis, preprocess_fn = preprocess_fxn, Idx2labels = labels_dict),
+    fn     = partial(run_diagnosis, preprocess_fn = preprocess_fxn, Idx2labels = labels_dict, threshold = configs["THRESHOLD"]),
 
     inputs = [gradio.Dropdown(["ConvNeXt(small)", "ConvNeXt(tiny)", "EfficientNet(v2_small)", "EfficientNet(b3)", "RegNet(x3_2GF)","ResNet50"], value="EfficientNet(b3)", label="Select Backbone Model"),
               gradio.Image(type="pil", label="Load chest-X-ray image here")],