Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,28 @@
+# streamlit_app/app.py
+
+import streamlit as st
+import requests
+from PIL import Image
+
+# Define FastAPI backend URL
+backend_url = "http://localhost:7384"
+
+def main():
+    st.title("SETI Signals Classifier")
+
+    # Example: Upload file and send POST request to FastAPI endpoint
+    uploaded_file = st.file_uploader("Choose an image to predict...", type=["png"])
+    st.markdown("You can get sample images from [here](https://github.com/bhuvaneshprasad/End-to-End-SETI-Classification-using-CNN-MLFlow-DVC/tree/main/assets/test_images) to predict.")
+    if uploaded_file is not None:
+        with st.spinner('Predicting...'):
+            files = {"file": uploaded_file}
+            response = requests.post(f"{backend_url}/predict", files=files)
+            if response.status_code == 200:
+                st.json(response.json())
+                image = Image.open(uploaded_file)
+                st.image(image, caption="Uploaded Image", use_column_width=True)
+            else:
+                st.error("Failed to predict")
+
+if __name__ == "__main__":
+    main()

model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bb6494fb9ef5a65353aafea4100b93620a51671b2430fc7b6fc17f9145ff31
+size 658923582

prediction.py

@@ -0,0 +1,47 @@
+import os
+from pathlib import Path
+from dotenv import load_dotenv
+import numpy as np
+import tensorflow as tf
+
+load_dotenv()
+
+class PredictionPipeline:
+    """
+    A class representing a pipeline for making predictions using a pre-trained model.
+
+    Attributes:
+        filename (str): The filename of the image to predict.
+
+    Methods:
+        predict() -> int:
+            Loads a pre-trained model, processes an image, and predicts its class.
+    """
+    def __init__(self,filename):
+        """
+        Initialize the PredictionPipeline class.
+
+        Args:
+            filename (str): The filename of the image to predict.
+        """
+        self.filename =filename
+    
+    def predict(self) -> int:
+        """
+        Perform prediction on the image specified by the filename.
+
+        Returns:
+            int: The predicted class label.
+        """
+        model = tf.keras.models.load_model(os.path.join(os.getcwd(),Path(os.getenv('MODEL_URI'))))
+        class_labels = ['brightpixel','narrowband',
+                 'narrowbanddrd','noise',
+                 'squarepulsednarrowband','squiggle',
+                 'squigglesquarepulsednarrowband']
+
+        imagename = self.filename
+        test_image = tf.keras.preprocessing.image.load_img(imagename, target_size = (256,256))
+        test_image = tf.keras.preprocessing.image.img_to_array(test_image)
+        test_image = np.expand_dims(test_image, axis = 0)
+        result = np.argmax(model.predict(test_image), axis=1)
+        return class_labels[int(result)]