first commit

app.py

@@ -0,0 +1,9 @@
+import streamlit as st 
+import eda
+import prediction
+
+# page = st.sidebar.selectbox('Pilih Halaman :', ('EDA', 'Prediction'))
+# if page == 'EDA':
+#     eda.run()
+# else:
+prediction.run()

model_cv.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92b77282cea264739caaf64b4b3679ff343219e5013e129388673f239b99f25
+size 600352

prediction.py

@@ -0,0 +1,81 @@
+import streamlit as st 
+import pandas as pd 
+import numpy as np 
+import tensorflow as tf
+import matplotlib.pyplot as plt 
+from PIL import Image
+
+
+def run():
+
+    # membuat title
+    st.title('Computer Vision Artificial Neural Network')
+
+    # membuat subheader
+    st.subheader('Prediction Between Daisy and Dandelion Flower')
+
+    # menambahkan gambar 
+    image = Image.open('header2.jpg')
+    st.image(image)
+        
+    # inference
+    model = tf.keras.models.load_model('model_cv.h5')    
+    
+    data_inf = st.file_uploader("Upload file image to predict", type=['jpg', 'png', 'jpeg'])
+
+    # submit button
+    submitted = st.button('Predict')
+
+    # logic ketika predict button ditekan
+    if submitted and data_inf:
+
+        img = Image.open(data_inf)
+        img = img.resize((150,150))
+
+
+        # img = tf.keras.utils.load_img(data_inf, target_size=(150, 150))
+        x = tf.keras.utils.img_to_array(img)/255
+
+        x = np.expand_dims(x, axis=0)
+
+        # menampilkan gambar upload
+        left_co, cent_co,last_co = st.columns(3)
+        with cent_co:
+                st.image(img, caption='Uploaded Image')
+
+        # prediksi
+        pred_inf = model.predict(x)[0,0]
+        threshold = 0.395
+
+        # menentukan kelas
+        if pred_inf >= threshold:
+            predicted_class = 0
+        else:
+            predicted_class = 1
+
+        clas = ['Daisy', 'Dandelion']
+        st.write('### Prediction :', clas[predicted_class])
+        st.write('#### Probability : {:.3f}'.format(pred_inf))
+        
+
+    #     images = np.vstack([x])
+    #     output = model.predict(images, batch_size=32)
+    #     probability = output[0, 0]
+    #     threshold = 0.395  # threshold untuk klasifikasi biner
+
+    #     if probability >= threshold:
+    #         predicted_class = 0
+    #     else:
+    #         predicted_class = 1
+
+    #     clas = ['daisy', 'dandelion']
+    #     print('Prediction is a {} with probability {:.3f}'.format(clas[predicted_class], probability))
+
+    # # predict
+    #     pred_inf = model.predict(data_inf)
+    #     st.write('##  Prediction :', str(int(pred_inf)))
+    #     st.write('### Positive : 1, Negative : 2')
+
+if __name__ == '__main__':
+    run()
+

requirements.txt

@@ -0,0 +1,9 @@
+streamlit==0.59.0
+pandas
+numpy
+matplotlib
+seaborn
+plotly
+Pillow
+tensorflow
+keras