Update app.py

app.py

@@ -5,8 +5,10 @@ import torch
 import numpy as np
 
 # Load the pre-trained model and preprocessor (feature extractor)
-model_name = "runaksh/chest_xray_pneumonia_detection"
-model = ViTForImageClassification.from_pretrained(model_name)
+model_name_pneumonia = "runaksh/chest_xray_pneumonia_detection"
+model_name_tuberculosis = "runaksh/chest_xray_tuberculosis_detection"
+model_pneumonia = ViTForImageClassification.from_pretrained(model_name_pneumonia)
+model_tuberculosis = ViTForImageClassification.from_pretrained(model_name_tuberculosis)
 feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
 
 def classify_image(image):
@@ -16,10 +18,10 @@ def classify_image(image):
     inputs = feature_extractor(images=image, return_tensors="pt")
     # Make prediction
     with torch.no_grad():
-        outputs = model(**inputs)
-        logits1 = outputs.logits
+        outputs_pneumonia = model_pneumonia(**inputs)
+        logits_pneumonia = outputs_pneumonia.logits
     # Retrieve the highest probability class label index
-    predicted_class_idx = logits1.argmax(-1).item()
+    predicted_class_idx_pneumonia = logits_pneumonia.argmax(-1).item()
     # Define a manual mapping of label indices to human-readable labels
     index_to_label = {
         0: "NORMAL",
@@ -27,9 +29,9 @@ def classify_image(image):
     }
 
     # Convert the index to the model's class label
-    label = index_to_label.get(predicted_class_idx, "Unknown Label")
+    label_pneumonia = index_to_label.get(predicted_class_idx_pneumonia, "Unknown Label")
 
-    return label
+    return label_pneumonia
 
 # Create title, description and article strings
 title = "Classification Demo"