Kerang

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run diabetes_app.py

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+
+st.set_option('deprecation.showfileUploaderEncoding', False)
+
+@st.cache(allow_output_mutation=True)
+def load_model():
+	model = tf.keras.models.load_weights('kerang_model_trained.h5')
+	return model
+
+
+def predict_class(image, model):
+
+	image = tf.cast(image, tf.float32)
+	image = tf.image.resize(image, [180, 180])
+
+	image = np.expand_dims(image, axis = 0)
+
+	prediction = model.predict(image)
+
+	return prediction
+
+
+model = load_model()
+st.title('Kerang Classifier')
+
+file = st.file_uploader("Upload an image of a kerang", type=["jpg", "png"])
+
+
+if file is None:
+	st.text('Waiting for upload....')
+
+else:
+	slot = st.empty()
+	slot.text('Running inference....')
+
+	test_image = Image.open(file)
+
+	st.image(test_image, caption="Input Image", width = 400)
+
+	pred = predict_class(np.asarray(test_image), model)
+
+	class_names = ['kerang bulu', 'kerang darah']
+
+	result = class_names[np.argmax(pred)]
+
+	output = 'The image is a ' + result
+
+	slot.text('Done')
+
+	st.success(output)
+

kerang_model_trained.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d50a67f82ea63f883d0d5a32de88fb5393380b30758d133a1568f341c3cdf8
+size 15980944

requirements.txt

@@ -0,0 +1,4 @@
+numpy==1.23.1
+Pillow==9.3.0
+streamlit==1.12.0
+tensorflow==2.9.1

setup.sh

@@ -0,0 +1,11 @@
+mkdir -p ~/.streamlit/
+echo "\
+[general]\n\
+email = \"your-email@domain.com\"\n\
+" > ~/.streamlit/credentials.toml
+echo "\
+[server]\n\
+headless = true\n\
+enableCORS=false\n\
+port = $PORT\n\
+" > ~/.streamlit/config.toml