Update prediction.py

prediction.py

@@ -1,53 +1,53 @@
-import streamlit as st
-import numpy as np
-import cv2
-from PIL import Image
-import tensorflow as tf
-import os
-
-# Load model yang telah dilatih (ganti 'model.h5' dengan file model kamu)
- model = load_model('model_aug.keras', custom_objects={'KerasLayer': KerasLayer})
-
-# Kelas target (ubah sesuai dengan model kamu)
-CLASS_NAMES = ['oily', 'dry', 'normal']
-
-def run():
-    # Set judul aplikasi
-    st.title('Skin Type Classification')
-    st.write('---')
-
-    # Tambahkan deskripsi
-    st.write('Upload an image of skin, and this app will predict the skin type.')
-
-    # Gambar ilustrasi (opsional)
-    link_gambar = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQntnqn33t_1jWqaFszEgEdMCQjGNNtWLxv8A&s'  # Ganti dengan URL gambar
-    st.image(link_gambar, caption='Know your skin type!', use_container_width=True)
-
-    # Form untuk upload gambar
-    uploaded_file = st.file_uploader('Upload an image:', type=['jpg', 'png', 'jpeg'])
-
-    if uploaded_file is not None:
-        # Tampilkan gambar yang di-upload
-        image = Image.open(uploaded_file)
-        st.image(image, caption='Uploaded Image', use_column_width=True)
-
-        # Convert gambar ke format yang diterima model
-        img_array = np.array(image)
-        img_resized = cv2.resize(img_array, (220, 220))  # Ubah ukuran ke input model
-        img_normalized = img_resized / 255.0  # Normalisasi
-        img_expanded = np.expand_dims(img_normalized, axis=0)  # Tambahkan batch dimension
-
-        # Prediksi menggunakan model
-        prediction = model.predict(img_expanded)
-        predicted_class = CLASS_NAMES[np.argmax(prediction)]
-        confidence = np.max(prediction) * 100
-
-        # Tampilkan hasil prediksi
-        st.write(f"### Predicted Skin Type: {predicted_class}")
-        st.write(f"### Confidence: {confidence:.2f}%")
-
-    else:
-        st.write('Please upload an image to get a prediction.')
-
-if __name__ == '__main__':
-    run()
+import streamlit as st
+import numpy as np
+import cv2
+from PIL import Image
+import tensorflow as tf
+import os
+
+# Load model yang telah dilatih (ganti 'model.h5' dengan file model kamu)
+model = load_model('model_aug.keras', custom_objects={'KerasLayer': KerasLayer})
+
+# Kelas target (ubah sesuai dengan model kamu)
+CLASS_NAMES = ['oily', 'dry', 'normal']
+
+def run():
+    # Set judul aplikasi
+    st.title('Skin Type Classification')
+    st.write('---')
+
+    # Tambahkan deskripsi
+    st.write('Upload an image of skin, and this app will predict the skin type.')
+
+    # Gambar ilustrasi (opsional)
+    link_gambar = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQntnqn33t_1jWqaFszEgEdMCQjGNNtWLxv8A&s'  # Ganti dengan URL gambar
+    st.image(link_gambar, caption='Know your skin type!', use_container_width=True)
+
+    # Form untuk upload gambar
+    uploaded_file = st.file_uploader('Upload an image:', type=['jpg', 'png', 'jpeg'])
+
+    if uploaded_file is not None:
+        # Tampilkan gambar yang di-upload
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image', use_column_width=True)
+
+        # Convert gambar ke format yang diterima model
+        img_array = np.array(image)
+        img_resized = cv2.resize(img_array, (220, 220))  # Ubah ukuran ke input model
+        img_normalized = img_resized / 255.0  # Normalisasi
+        img_expanded = np.expand_dims(img_normalized, axis=0)  # Tambahkan batch dimension
+
+        # Prediksi menggunakan model
+        prediction = model.predict(img_expanded)
+        predicted_class = CLASS_NAMES[np.argmax(prediction)]
+        confidence = np.max(prediction) * 100
+
+        # Tampilkan hasil prediksi
+        st.write(f"### Predicted Skin Type: {predicted_class}")
+        st.write(f"### Confidence: {confidence:.2f}%")
+
+    else:
+        st.write('Please upload an image to get a prediction.')
+
+if __name__ == '__main__':
+    run()