Upload 9 files

app.py

@@ -0,0 +1,15 @@
+# Import Library
+import streamlit as st
+
+# Import halaman streamlit yang sudah dibuat
+import eda
+import prediction
+
+
+# Tombol navigasi
+navigasi = st.sidebar.selectbox('Choose page :', ('EDA', 'Model Prediction'))
+
+if navigasi == 'Model Prediction':
+    prediction.run()
+else:
+    eda.run()

eda.py

@@ -0,0 +1,46 @@
+# import library
+import streamlit as st
+import pandas as pd
+import numpy as np 
+from PIL import Image
+
+def run():
+    # Set Title
+    st.title('BRAIN MRI VISUALIZATION')
+
+    # memasukkan gambar
+    st.image ('https://cdn.systematic.com/media/g0sj1tbg/hospital-building-001-global.jpg?mode=crop&width=1200&height=630&center=')
+
+    # menampilkan EDA
+    st.markdown('## Exploratory Data Analysis (EDA)')
+    st.markdown ('---')
+ 
+ 
+    # EDA 1
+    st.markdown("<h3 style='text-align: center;'>Gambar MRI</h3>", unsafe_allow_html=True)
+
+    image = Image.open('EDA3.png')
+    st.image(image)
+    
+    st.write('---')
+
+
+    # EDA 2
+    st.markdown("<h3 style='text-align: center;'>Distribusi Data Train</h3>", unsafe_allow_html=True)
+
+    image = Image.open('EDA1.png')
+    st.image(image)
+
+    st.write('---')
+
+    # EDA 3
+    st.markdown("<h3 style='text-align: center;'>Distribusi Data Val</h3>", unsafe_allow_html=True)
+
+    image = Image.open('EDA2.png')
+    st.image(image)
+
+    st.write('---')
+
+if __name__ == "__main__":
+    run()
+    

model_tl.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a568b10ffff426b8c27d71f06a5a72dbfd34df5000e9e0b2a9afa4c2c99c953
+size 213086560

prediction.py

@@ -0,0 +1,49 @@
+#import library
+import pandas as pd
+import numpy as np
+import streamlit as st
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+import matplotlib.pyplot as plt
+from PIL import Image
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+import tensorflow_hub as hub
+
+#import pickle
+import pickle
+
+#load model
+def run():
+    file = st.file_uploader("Upload an image", type=["jpg", "png"])
+
+    model = load_model('model_transfer.h5', custom_objects={'KerasLayer': hub.KerasLayer})
+    target_size=(224, 224)
+
+    def import_and_predict(image_data, model):
+        image = tf.keras.utils.load_img(image_data, target_size=(224, 224))
+        x = tf.keras.utils.img_to_array(image)
+        x = np.expand_dims(x, axis=0)
+
+        plt.imshow(image)
+        plt.axis('off')
+        plt.show()
+
+        # Make prediction
+        classes = model.predict(x)
+        result_pred = np.where(classes < 0.7, 0, 1)
+        if result_pred == 1:
+            result = 'Brain Tumor'
+        else:
+            result = 'Healthy'
+
+        return f"Prediction: {result}"
+
+    if file is None:
+        st.text("Please upload an image file")
+    else:
+        result = import_and_predict(file, model)
+        st.image(file)
+        st.write(result)
+        
+if __name__ == "__main__":
+    run()

requirements.txt

@@ -0,0 +1,10 @@
+pandas
+numpy
+matplotlib
+seaborn
+pickleshare
+plotly
+scikit.learn==1.4.0
+tensorflow==2.15.0
+tensorflow-hub==0.16.1
+pillow