adding app

XRay_app/app.py

@@ -0,0 +1,27 @@
+# app.py
+import streamlit as st
+from PIL import Image
+import torch
+from utils.model_utils import load_model, predict
+from utils.preprocessing import preprocess_image
+
+st.set_page_config(page_title="X-ray Diagnosis Demo", layout="centered")
+st.title("🩻 X-ray Multi-Label Diagnosis App (CheXNet)")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model_path = "model/dannynet-55-best_model_20250422-211522.pth"
+model = load_model(model_path, device)
+
+uploaded_file = st.file_uploader("Upload a chest X-ray", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded X-ray", use_column_width=True)
+
+    img_tensor = preprocess_image(image)
+
+    probs = predict(model, img_tensor, device)
+
+    st.subheader("Predictions")
+    for disease, prob in probs.items():
+        st.write(f"**{disease}**: {prob:.4f}")

XRay_app/utils/model_utils.py

@@ -0,0 +1,41 @@
+# utils/model_utils.py
+import torch
+import torch.nn as nn
+from torchvision.models import densenet121, DenseNet121_Weights
+
+# Disease labels
+DISEASE_LIST = [
+    'Atelectasis', 'Cardiomegaly', 'Consolidation', 'Edema', 'Effusion',
+    'Emphysema', 'Fibrosis', 'Hernia', 'Infiltration', 'Mass',
+    'Nodule', 'Pleural_Thickening', 'Pneumonia', 'Pneumothorax'
+]
+
+# Load trained CheXNet model
+class CheXNet(nn.Module):
+    def __init__(self, num_classes=14):
+        super().__init__()
+        base_model = densenet121(weights=DenseNet121_Weights.IMAGENET1K_V1)
+        self.features = base_model.features
+        self.classifier = nn.Linear(base_model.classifier.in_features, num_classes)
+
+    def forward(self, x):
+        x = self.features(x)
+        x = nn.functional.adaptive_avg_pool2d(x, (1, 1))
+        x = torch.flatten(x, 1)
+        return self.classifier(x)
+
+def load_model(url, device):
+    model_path = "dannynet.pth"
+    torch.hub.download_url_to_file(url,model_path)
+    model = torch.load(model_path, map_location = device)
+    model.eval()
+    return model
+
+def predict(model, img_tensor, device):
+    with torch.no_grad():
+        output = model(img_tensor.unsqueeze(0).to(device))
+        probs = torch.sigmoid(output[0]).cpu().numpy()
+    return dict(zip(DISEASE_LIST, probs))
+
+
+

XRay_app/utils/preprocessing.py

@@ -0,0 +1,11 @@
+# utils/preprocessing.py
+from torchvision import transforms
+
+def preprocess_image(img):
+    transform = transforms.Compose([
+        transforms.Resize(256),
+        transforms.CenterCrop(224),
+        transforms.ToTensor(),
+        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+    return transform(img)