Spaces:

Jfink09
/

TCA

Sleeping

App Files Files Community

Jfink09 commited on Apr 28, 2024

Commit

e9fb974

verified ·

1 Parent(s): dccf1b6

Update app.py

Browse files

Files changed (1) hide show

app.py +82 -38

app.py CHANGED Viewed

@@ -1,15 +1,17 @@
 import streamlit as st
 import torch
 import torch.nn as nn
-# Define your model architecture here (same as before)
 class RegressionModel2(nn.Module):
     def __init__(self, input_dim2, hidden_dim2, output_dim2):
         super(RegressionModel2, self).__init__()
         self.fc1 = nn.Linear(input_dim2, hidden_dim2)
-        self.relu1 = nn.ReLU()  # ReLU activation function
         self.fc2 = nn.Linear(hidden_dim2, output_dim2)
-        self.batch_norm1 = nn.BatchNorm1d(hidden_dim2)  # Batch normalization
     def forward(self, x2):
         out = self.fc1(x2)
@@ -18,39 +20,81 @@ class RegressionModel2(nn.Module):
         out = self.fc2(out)
         return out
-input_dim2 = X2_train.shape[1] # change to [1] for pentacam dataset X_train.shape[1]
-hidden_dim2 = 32 # Was 16
-output_dim2 = 1
-# Load your saved model state dictionary (assuming 'model.pt' is uploaded)
-model2 = RegressionModel2(input_dim2, hidden_dim2, output_dim2)
 model2.load_state_dict(torch.load('model.pt'))
-model2.eval()  # Set the model to evaluation mode
-def predict(age, aca, axis):
-  """
-  This function takes three arguments (age, axis, aca) as input,
-  prepares the data, makes a prediction using the loaded model,
-  and returns the predicted value.
-  """
-  # Prepare the input data
-  data = torch.tensor([[age, aca, axis]], dtype=torch.float32)
-  # Make prediction
-  with torch.no_grad():
-    prediction = model2(data)
-  # Return the predicted value
-  return prediction.item()
-# Streamlit App
-st.title("Astigmatism Prediction App")
-st.write("Enter the patient's information:")
-age = st.number_input("Age", min_value=0)
-aca = st.number_input("ACA Magnitude", min_value=0)
-axis = st.number_input("ACA Axis", min_value=0)
-if st.button("Predict"):
-  predicted_value = predict(age, aca, axis)
-  st.write(f"Predicted Astigmatism Value: {predicted_value}")

 import streamlit as st
+import pandas as pd
 import torch
 import torch.nn as nn
+import torch.optim as optim
+from sklearn.metrics import r2_score
 class RegressionModel2(nn.Module):
     def __init__(self, input_dim2, hidden_dim2, output_dim2):
         super(RegressionModel2, self).__init__()
         self.fc1 = nn.Linear(input_dim2, hidden_dim2)
+        self.relu1 = nn.ReLU()
         self.fc2 = nn.Linear(hidden_dim2, output_dim2)
+        self.batch_norm1 = nn.BatchNorm1d(hidden_dim2)
     def forward(self, x2):
         out = self.fc1(x2)
         out = self.fc2(out)
         return out
+# Load the trained model
+model2 = RegressionModel2(3, 32, 1)
 model2.load_state_dict(torch.load('model.pt'))
+model2.eval()
+def predict_astigmatism(age, aca_magnitude, aca_axis):
+    input_data = torch.tensor([[age, aca_magnitude, aca_axis]], dtype=torch.float32)
+    output = model2(input_data)
+    return output.item()
+def main():
+    st.set_page_config(page_title='Astigmatism Prediction', page_icon=':eyeglasses:', layout='wide')
+    st.markdown(
+        """
+        <style>
+        .navbar {
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            background-color: #f2f2f2;
+            padding: 10px;
+        }
+        .logo img {
+            height: 50px;
+        }
+        .menu {
+            list-style-type: none;
+            display: flex;
+        }
+        .menu li {
+            margin-left: 20px;
+        }
+        .text-content {
+            margin-top: 50px;
+            text-align: center;
+        }
+        .button {
+            margin-top: 20px;
+            padding: 10px 20px;
+            font-size: 16px;
+        }
+        </style>
+        """,
+        unsafe_allow_html=True
+    )
+    st.markdown(
+        """
+        <body>
+        <header>
+        <nav class="navbar">
+        <div class="logo"><img src="iol.png" alt="Image description"></div>
+        <ul class="menu">
+        <li><a href="#">Home</a></li>
+        <li><a href="#">About</a></li>
+        <li><a href="#">Contact</a></li>
+        </ul>
+        </nav>
+        <div class="text-content">
+        <h2>Enter Variables</h2>
+        <br>
+        </div>
+        </header>
+        </body>
+        """,
+        unsafe_allow_html=True
+    )
+    age = st.number_input('Enter Patient Age:', min_value=0, step=1)
+    aca_magnitude = st.number_input('Enter ACA Magnitude:', min_value=0.0, step=0.1)
+    aca_axis = st.number_input('Enter ACA Axis:', min_value=0, max_value=180, step=1)
+    if st.button('Predict!'):
+        astigmatism = predict_astigmatism(age, aca_magnitude, aca_axis)
+        st.success(f'Predicted Astigmatism: {astigmatism:.4f}')
+if __name__ == '__main__':
+    main()