Create app.py

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+import os
+
+# === Fix font/matplotlib warnings for Hugging Face ===
+os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
+os.environ["XDG_CACHE_HOME"] = "/tmp"
+
+# === Custom loss and metrics ===
+def weighted_dice_loss(y_true, y_pred):
+    smooth = 1e-6
+    y_true_f = tf.reshape(y_true, [-1])
+    y_pred_f = tf.reshape(y_pred, [-1])
+    intersection = tf.reduce_sum(y_true_f * y_pred_f)
+    return 1 - ((2. * intersection + smooth) /
+                (tf.reduce_sum(y_true_f) + tf.reduce_sum(y_pred_f) + smooth))
+
+def iou_metric(y_true, y_pred):
+    y_true = tf.cast(y_true > 0.5, tf.float32)
+    y_pred = tf.cast(y_pred > 0.5, tf.float32)
+    intersection = tf.reduce_sum(y_true * y_pred)
+    union = tf.reduce_sum(y_true) + tf.reduce_sum(y_pred) - intersection
+    return intersection / (union + 1e-6)
+
+def bce_loss(y_true, y_pred):
+    return tf.keras.losses.binary_crossentropy(y_true, y_pred)
+
+# === Load model ===
+model_path = "final_model_after_third_iteration_WDL0.07_0.5155/"
+@st.cache_resource
+def load_model():
+    return tf.keras.models.load_model(
+        model_path,
+        custom_objects={
+            "weighted_dice_loss": weighted_dice_loss,
+            "iou_metric": iou_metric,
+            "bce_loss": bce_loss
+        }
+    )
+
+model = load_model()
+
+# === Streamlit UI ===
+st.title("🕳️ Sinkhole Segmentation with EffV2-UNet")
+
+uploaded_image = st.file_uploader("Upload an image", type=["png", "jpg", "jpeg"])
+if uploaded_image:
+    image = Image.open(uploaded_image).convert("RGB")
+    st.image(image, caption="Original Image", use_column_width=True)
+
+    # Preprocess and predict
+    resized = image.resize((512, 512))
+    x = np.expand_dims(np.array(resized) / 255.0, axis=0)
+    y = model.predict(x)[0, :, :, 0]
+
+    y_norm = (y - y.min()) / (y.max() - y.min() + 1e-6)
+    mask = (y_norm * 255).astype(np.uint8)
+    result = Image.fromarray(mask)
+
+    st.image(result, caption="Predicted Segmentation", use_column_width=True)