Upload 6 files

Chest Xray/chest-xray.py

@@ -4,35 +4,28 @@ import tensorflow as tf
 import streamlit as st
 from tensorflow.keras.models import load_model
 
-st.title("Pnuemonia")
-def load_img(path):
-    img = cv2.imread(path)
-    img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
-    img = cv2.resize(img,(224,224))
-    img = img.astype('float32')
-    img /= 255.0
-    return img
-
-imgs = ['person1676_virus_2892.jpeg','1-s2.0-S0263931909001811-gr3.jpg','43055_2020_296_Fig11_HTML.png','images.jpg']
+st.subheader("Pnuemonia Detection CNN")
 @st.cache_resource
 def load_cached_models():
-    model = load_model("pneumonia_vgg16.keras")
-    model1 = load_model("pnuemoniavgg16_1.keras")
-    model2 = load_model("pnuemoniavgg16_2.keras")
-    return model, model1, model2
+    model = load_model("Chest Xray/pneumonia.keras")
+    
+    return model
+
+model= load_cached_models()
+uploaded_file = st.file_uploader("Upload an X-ray image (JPEG/PNG)", type=["jpeg", "jpg", "png"])
+
+if uploaded_file is not None:
+    file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
+    img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  
+    img_resized = cv2.resize(img, (224, 224)).astype('float32') / 255.0
+    img_expanded = np.expand_dims(img_resized, axis=0)
 
-# Load the models once, cached in memory
-model, model1, model2 = load_cached_models()
-for img_p in imgs:
-    img = load_img(img_p)
-    img = np.expand_dims(img,axis=0)
-    pred = model.predict(img)
-    pred1 = model1.predict(img)
-    pred2 = model2.predict(img)
-    avg_pred = np.mean([pred, pred1, pred2])
-    st.subheader(img_p)
-    st.write("Prediction of model")
-    final_pred = round(avg_pred*100,2)
-    st.progress(int(round(avg_pred * 100)))
-    st.write(final_pred)
-    st.write("Pneumonia Detected" if avg_pred > .5 else "Your x-ray seems normal")
+    pred = model.predict(img_expanded)
+    pred = pred.flatten()[np.argmax(pred)]
+    st.image(img, caption="Uploaded X-ray", use_container_width=True)
+    st.subheader("Prediction")
+    final_pred = round(float(pred) * 100, 2)
+    st.progress(int(round(pred * 100)))
+    st.write(f"### Percentage: {final_pred}%")
+    st.write("#### Pneumonia Detected" if pred > 0.5 else "Your X-ray seems normal")