update appp

app.py

@@ -6,55 +6,69 @@ from PIL import Image
 model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
-# Define the BMI classes
-bmi_classes = ["underweight", "normal weight", "overweight", "obesity"]
+# Define the broad BMI classes for Model 1
+bmi_classes_model1 = [
+    "underweight (x < 18.5 BMI)", 
+    "normal weight (18.5 < x < 25 BMI)", 
+    "overweight (25 BMI < x < 30)",  
+    "obesity (x > 30 BMI)"
+]
 
-# Define the secondary models for BMI predictions and midpoints
-bmi_ranges = {
-    "underweight": {
-        "BMI < 16.0": (0, 16.0, 8.0),
-        "16.0 ≤ BMI ≤ 16.99": (16.0, 16.99, 16.5),
-        "17.0 ≤ BMI ≤ 18.49": (17.0, 18.49, 17.75)
-    },
-    "normal weight": {
-        "18.5 ≤ BMI ≤ 20.4": (18.5, 20.4, 19.45),
-        "20.5 ≤ BMI ≤ 22.4": (20.5, 22.4, 21.45),
-        "22.5 ≤ BMI ≤ 24.9": (22.5, 24.9, 23.7)
-    },
-    "overweight": {
-        "25.0 ≤ BMI ≤ 26.9": (25.0, 26.9, 25.95),
-        "27.0 ≤ BMI ≤ 28.9": (27.0, 28.9, 27.95),
-        "29.0 ≤ BMI ≤ 29.9": (29.0, 29.9, 29.45)
-    },
-    "obesity": {
-        "30.0 ≤ BMI ≤ 34.9": (30.0, 34.9, 32.5),
-        "35.0 ≤ BMI ≤ 39.9": (35.0, 39.9, 37.45),
-        "BMI ≥ 40.0": (40.0, 100, 40.0)  # Assuming 100 as the upper limit for BMI
-    }
+# Define the finer BMI ranges for Model 2
+bmi_ranges_model2 = {
+    "underweight (x < 18.5 bmi)": [
+        "BMI less than 16.0", 
+        "BMI between 16.0 and 16.99",  
+        "BMI between 17.0 and 18.49"
+    ],
+    "normal weight (18.5 < x < 25 bmi)": [
+        "BMI between 18.5 and 20.4", 
+        "BMI between 20.5 and 22.4",  
+        "BMI between 22.5 and 24.9"
+    ],
+    "overweight (25 bmi < x < 30)": [
+        "BMI between 25.0 and 26.9", 
+        "BMI between 27.0 and 28.9",  
+        "BMI between 29.0 and 29.9"
+    ],
+    "obesity (x > 30 bmi)": [
+        "BMI between 30.0 and 34.9", 
+        "BMI between 35.0 and 39.9",  
+        "BMI 40.0 and above"
+    ]
 }
 
-def predict_bmi(image):
-    # Prepare the inputs
-    inputs = processor(text=bmi_classes, images=image, return_tensors="pt", padding=True)
-    # Get model outputs
-    outputs = model(**inputs)
-    logits_per_image = outputs.logits_per_image  # Image-text similarity scores
-    probs = logits_per_image.softmax(dim=1)  # Convert to probabilities
+def predict_bmi(image, height_in_inches):
+    # Prepare inputs for Model 1
+    inputs_model1 = processor(text=bmi_classes_model1, images=image, return_tensors="pt", padding=True)
+    outputs_model1 = model(**inputs_model1)
+    probs_model1 = outputs_model1.logits_per_image.softmax(dim=1)
+    
+    # Get the broad category prediction from Model 1
+    max_prob_index_model1 = probs_model1.argmax().item()
+    predicted_bmi_class = bmi_classes_model1[max_prob_index_model1]
+
+    # Select class names for Model 2 based on Model 1's prediction
+    model2_classes = bmi_ranges_model2[predicted_bmi_class.lower()]
+    
+    # Prepare inputs for Model 2
+    inputs_model2 = processor(text=model2_classes, images=image, return_tensors="pt", padding=True)
+    outputs_model2 = model(**inputs_model2)
+    probs_model2 = outputs_model2.logits_per_image.softmax(dim=1)
 
-    # Find the class with the highest probability
-    max_prob_index = probs.argmax().item()
-    predicted_bmi_class = bmi_classes[max_prob_index]
+    # Get the finer range prediction from Model 2
+    max_prob_index_model2 = probs_model2.argmax().item()
+    finer_bmi_range = model2_classes[max_prob_index_model2]
 
-    # Use the midpoint BMI for the predicted class
-    bmi_prediction = get_midpoint_bmi(predicted_bmi_class)
+    # Determine the BMI prediction based on the range
+    bmi_prediction = get_adjusted_bmi(predicted_bmi_class, finer_bmi_range)
     
-    # Assume height is input by the user or extracted somehow
-    height_in_inches = 75  # Example height; replace with actual input or extraction
+    # Calculate weight using user-provided height
     predicted_weight = calculate_weight(bmi_prediction, height_in_inches)
 
     # Create the JSON output
     result = {
-        "weightCategory": f"{predicted_bmi_class} - {bmi_prediction}",
+        "weightCategory": f"{predicted_bmi_class} - {finer_bmi_range}",
         "bmiPrediction": f"{bmi_prediction:.2f}",
         "height": str(height_in_inches),
         "predictedWeight": f"{predicted_weight:.2f} lbs"
@@ -62,27 +76,33 @@ def predict_bmi(image):
 
     return result
 
-def get_midpoint_bmi(weight_category):
-    """Return the midpoint BMI for the given weight category."""
+def get_adjusted_bmi(weight_category, finer_range):
+    """Return the appropriate BMI value for the given finer range within the weight category."""
     category_ranges = bmi_ranges.get(weight_category.lower())
     for range_label, (low, high, mid) in category_ranges.items():
-        return mid  # Return the first midpoint found in the given range
+        if "BMI <" in range_label or "BMI ≥" in range_label:
+            return high if "BMI <" in range_label else low
+        elif range_label == finer_range:
+            return mid
+    return None
 
 def calculate_weight(bmi, height_in_inches):
     """Calculate the weight from BMI and height (in inches)."""
-    height_in_meters = height_in_inches * 0.0254  # Convert height to meters
-    weight_kg = bmi * (height_in_meters ** 2)  # BMI formula to calculate weight
-    weight_lbs = weight_kg * 2.20462  # Convert kg to lbs
+    height_in_meters = height_in_inches * 0.0254
+    weight_kg = bmi * (height_in_meters ** 2)
+    weight_lbs = weight_kg * 2.20462
     return weight_lbs
 
-# Create Gradio interface with updated components
+# Create Gradio interface with updated input components
 interface = gr.Interface(
     fn=predict_bmi,
-    inputs=gr.Image(type="pil"),
+    inputs=[
+        gr.Image(type="pil"),
+        gr.Number(label="Height in inches", default=75)  # Allow user to enter height
+    ],
     outputs="json",
     title="BMI Prediction",
-    description="Upload an image to predict BMI category (underweight, normal weight, overweight, obesity) and receive a detailed prediction."
+    description="Upload an image and enter your height to predict BMI category and receive a detailed prediction."
 )
 
-# Launch the interface
-interface.launch(share=True)
+interface.launch()