Upload 11 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+leukemia_streamlit/saved_leukemia_ensemble/CustomCNN_model.keras filter=lfs diff=lfs merge=lfs -text
+leukemia_streamlit/saved_leukemia_ensemble/DenseNet121_model.keras filter=lfs diff=lfs merge=lfs -text
+leukemia_streamlit/saved_leukemia_ensemble/MobileNetV2_model.keras filter=lfs diff=lfs merge=lfs -text
+leukemia_streamlit/saved_leukemia_ensemble/VGG16_model.keras filter=lfs diff=lfs merge=lfs -text

leukemia_streamlit/.gitattributes

@@ -0,0 +1,2 @@
+*.keras filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text

leukemia_streamlit/app.py

@@ -0,0 +1,140 @@
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+
+import streamlit as st
+import numpy as np
+import os
+import pickle
+import zipfile
+import matplotlib.pyplot as plt
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+
+# --- CONFIG ---
+st.set_page_config(page_title="Leukemia Subtype Detector", layout="centered")
+
+st.markdown("""
+    <div style='background-color:#57068c;padding:20px;border-radius:10px'>
+    <h2 style='color:white;text-align:center'>🧬 Leukemia Subtype Detection</h2>
+    <p style='color:white;text-align:center'>
+        Uses an ensemble of 4 models: <b>DenseNet121</b>, <b>MobileNetV2</b>, <b>VGG16</b>, and <b>Custom CNN</b>.<br>
+        Predicts: <i>Benign</i>, <i>Pre</i>, <i>Pro</i>, <i>Early</i>.
+    </p>
+    </div>
+""", unsafe_allow_html=True)
+
+# --- CONSTANTS ---
+IMG_HEIGHT, IMG_WIDTH = 224, 224
+CLASS_NAMES = ['Benign', 'Pre', 'Pro', 'Early']
+SAVE_DIR = 'saved_leukemia_ensemble'
+MODEL_ZIPS = {
+    "DenseNet121": "DenseNet121_model.zip",
+    "MobileNetV2": "MobileNetV2_model.zip",
+    "VGG16": "VGG16_model.zip",
+    "CustomCNN": "CustomCNN_model.zip"
+}
+ENSEMBLE_WEIGHTS = {
+    "DenseNet121": 0.28,
+    "MobileNetV2": 0.30,
+    "VGG16": 0.22,
+    "CustomCNN": 0.20
+}
+HISTORY_PATHS = {
+    name: os.path.join(SAVE_DIR, f"{name}_history.pkl") for name in MODEL_ZIPS
+}
+
+# --- UTIL FUNCTION ---
+def extract_model_if_needed(zip_path, output_path):
+    if not os.path.exists(output_path):
+        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+            zip_ref.extractall(os.path.dirname(output_path))
+
+# --- LOAD MODELS ---
+@st.cache_resource
+def load_all_models():
+    models = {}
+    for name, zip_file in MODEL_ZIPS.items():
+        zip_path = os.path.join(SAVE_DIR, zip_file)
+        keras_path = zip_path.replace(".zip", ".keras")
+
+        extract_model_if_needed(zip_path, keras_path)
+
+        if os.path.exists(keras_path):
+            models[name] = load_model(keras_path, compile=False)
+        else:
+            st.warning(f"❌ Model not found: {keras_path}")
+    return models
+
+models = load_all_models()
+
+# --- UPLOAD IMAGE ---
+uploaded_file = st.file_uploader("📁 Upload a blood smear image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    st.image(uploaded_file, caption="Uploaded Image", use_container_width=True)
+    
+    if st.button("🔍 Enter"):
+        with st.spinner("⏳ Please wait while results are being computed..."):
+            try:
+                img = image.load_img(uploaded_file, target_size=(IMG_HEIGHT, IMG_WIDTH))
+                img_array = image.img_to_array(img) / 255.0
+                img_array = np.expand_dims(img_array, axis=0)
+
+                st.markdown("### 🧪 Model Predictions:")
+                col1, col2 = st.columns(2)
+                individual_preds = {}
+
+                for i, (name, model) in enumerate(models.items()):
+                    pred = model.predict(img_array)
+                    individual_preds[name] = pred
+                    cls = CLASS_NAMES[np.argmax(pred)]
+                    conf = pred[0][np.argmax(pred)]
+                    with [col1, col2][i % 2]:
+                        st.info(f"**{name}** ➜ `{cls}` ({conf:.2%})")
+
+                ensemble_pred = sum(ENSEMBLE_WEIGHTS[name] * pred for name, pred in individual_preds.items())
+                final_class = CLASS_NAMES[np.argmax(ensemble_pred)]
+                final_conf = float(np.max(ensemble_pred))
+
+                st.markdown(f"""
+                    <div style="background-color:#c6f6d5;padding:15px;border-radius:10px">
+                    <h4 style="color:#2f855a">✅ Ensemble Prediction: <b>{final_class}</b></h4>
+                    <p style="font-size:16px;color:#22543d">Confidence: <b>{final_conf:.2%}</b></p>
+                    </div>
+                """, unsafe_allow_html=True)
+
+                st.bar_chart({CLASS_NAMES[i]: float(ensemble_pred[0][i]) for i in range(4)})
+
+            except Exception as e:
+                st.error(f"⚠️ Error: {e}")
+else:
+    st.info("👈 Please upload an image to begin.")
+
+# --- OPTIONAL TRAINING VISUALIZATION ---
+st.markdown("---")
+st.subheader("📈 Model Training History")
+
+if st.checkbox("Show training curves"):
+    for name, path in HISTORY_PATHS.items():
+        if os.path.exists(path):
+            with open(path, "rb") as f:
+                hist = pickle.load(f)
+                acc = hist['accuracy']
+                val_acc = hist['val_accuracy']
+                loss = hist['loss']
+                val_loss = hist['val_loss']
+
+                fig, ax = plt.subplots(1, 2, figsize=(12, 4))
+                ax[0].plot(acc, label='Train Acc')
+                ax[0].plot(val_acc, label='Val Acc')
+                ax[0].set_title(f'{name} Accuracy')
+                ax[0].legend()
+
+                ax[1].plot(loss, label='Train Loss')
+                ax[1].plot(val_loss, label='Val Loss')
+                ax[1].set_title(f'{name} Loss')
+                ax[1].legend()
+
+                st.pyplot(fig)
+        else:
+            st.warning(f"No training history found for {name}")

leukemia_streamlit/saved_leukemia_ensemble/CustomCNN_history.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6748fd7226aa4a81dde727f88fec29d61850ca6b445202a3bfcf6b4918e36f39
+size 996

leukemia_streamlit/saved_leukemia_ensemble/CustomCNN_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e1de995fef5c6dbfd630d1b86726263eb6ca8d2e593129cc5e4c664c3ab25b
+size 309466994

leukemia_streamlit/saved_leukemia_ensemble/DenseNet121_history.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5957e0c87de6deb1dcdd62703c84515cb807b37d5530ddaaa14ef121d5a9b128
+size 996

leukemia_streamlit/saved_leukemia_ensemble/DenseNet121_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145449086ddc01f1d1262c3e743be985a80ed2a2e58170f97be5c26d903a9769
+size 29708210

leukemia_streamlit/saved_leukemia_ensemble/MobileNetV2_history.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3fb78ebd25d43e9504a7c53ef2ddcf5653e1056ceffce1f687255bf4670041
+size 996

leukemia_streamlit/saved_leukemia_ensemble/MobileNetV2_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dc9b4510775f9d4f7f6a1a1b70f42db3c5ea1e4730decc3ce07b0dcb2b2b18
+size 9674100

leukemia_streamlit/saved_leukemia_ensemble/VGG16_history.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf4705734735de96652202338d018fe7b9186d11ca60eec9a18f9a6b17959d1
+size 996

leukemia_streamlit/saved_leukemia_ensemble/VGG16_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8298c14acb7a5a6e81904417c0a603d6ee0d27ee030781fe067410d03a4f39fa
+size 58967202

leukemia_streamlit/streamlit.py

@@ -0,0 +1,83 @@
+import streamlit as st
+import os
+import requests
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+import numpy as np
+from PIL import Image
+
+# 🔧 Configure the Streamlit page
+st.set_page_config(page_title="Leukemia Subtype Detection", layout="centered")
+st.markdown("<h1 style='text-align: center; color: #d6336c;'>🎗️ Leukemia Subtype Detection</h1>", unsafe_allow_html=True)
+st.markdown("<p style='text-align: center; font-size:18px;'>Upload a blood smear image and detect the leukemia subtype using deep learning models.</p>", unsafe_allow_html=True)
+
+# 🔗 Hugging Face Base URL (confirmed valid)
+HF_BASE = "https://huggingface.co/GarimaSharma75/Leukemia_Subtype/resolve/main/"
+SAVE_DIR = "models"
+
+# 📌 Class labels
+CLASS_NAMES = ["Early Pre-B ALL", "Pre-B ALL", "Pro-B ALL", "Healthy"]
+
+# 🔢 Model files hosted on Hugging Face
+model_files = {
+    "DenseNet121": "DenseNet121_model.keras",
+    "MobileNetV2": "MobileNetV2_model.keras",
+    "VGG16": "VGG16_model.keras",
+    "CustomCNN": "CustomCNN_model.keras"
+}
+
+# 📥 Download the model file from Hugging Face if it's not saved locally
+def download_if_not_exists(filename):
+    os.makedirs(SAVE_DIR, exist_ok=True)
+    filepath = os.path.join(SAVE_DIR, filename)
+    if not os.path.exists(filepath):
+        url = HF_BASE + filename
+        with st.spinner(f"📥 Downloading `{filename}`..."):
+            response = requests.get(url)
+            if response.status_code == 200:
+                with open(filepath, "wb") as f:
+                    f.write(response.content)
+            else:
+                st.error(f"❌ Failed to download {filename} from Hugging Face.")
+                st.stop()
+    return filepath
+
+# 🧼 Image preprocessing
+def preprocess(img):
+    img = img.resize((224, 224))
+    img_array = np.array(img) / 255.0
+    return np.expand_dims(img_array, axis=0)
+
+# 📍 Sidebar: Model selection and info
+with st.sidebar:
+    st.markdown("## 🧠 Select Model")
+    selected_model = st.selectbox("Choose one model to run", list(model_files.keys()))
+    st.markdown("### ℹ️ About the Models")
+    st.info("""
+    • **DenseNet121** – Deep CNN with dense connections  
+    • **MobileNetV2** – Lightweight CNN  
+    • **VGG16** – Classic 16-layer CNN  
+    • **CustomCNN** – Custom-built architecture
+    """)
+    st.markdown("---")
+    st.markdown("Made by **Garima Sharma** 💖")
+
+# 📤 Upload image
+uploaded_file = st.file_uploader("📤 Upload a blood smear image (JPG/PNG)", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    img = Image.open(uploaded_file).convert("RGB")
+    st.image(img, caption="Uploaded Image", use_container_width=True)
+
+    if st.button("🔍 Run Detection"):
+        with st.spinner("⏳ Please wait while the model is downloading and predicting..."):
+            input_data = preprocess(img)
+            model_path = download_if_not_exists(model_files[selected_model])
+            model = load_model(model_path)
+            preds = model.predict(input_data)
+            pred_class = CLASS_NAMES[np.argmax(preds)]
+            prob = np.max(preds) * 100
+
+        st.success(f"✅ **{selected_model}** predicts: **{pred_class}** with `{prob:.2f}%` confidence")
+else:
+    st.warning("📎 Please upload an image to get started.")