Use only image urls

main.py

@@ -11,6 +11,7 @@ import io
 import numpy as np
 from io import BytesIO
 from pydantic import BaseModel
+import os
 
 
 # Logging
@@ -22,7 +23,6 @@ description = """
 """
 
 class ImageRequest(BaseModel):
-    image: str
     imageURL:str
     lang: int
 
@@ -49,23 +49,23 @@ async def home():
 # red palm oil classification endpoint
 @app.post("/predict")
 async def predict(image_request: ImageRequest):
-    logging.info("Loading image")
+    # logging.info("Loading image")
 
-    # Decode base64 image string
-    decoded_image = base64.b64decode(image_request.image)
+    # # Decode base64 image string
+    # decoded_image = base64.b64decode(image_request.image)
 
-    # Create a BytesIO object to read the image data
-    image_bytes = BytesIO(decoded_image)
+    # # Create a BytesIO object to read the image data
+    # image_bytes = BytesIO(decoded_image)
 
     try:
         # Pre-classify image
-        is_palm_oil = pre_classification(image_request.imageURL)
+        is_palm_oil, image_path = pre_classification(image_request.imageURL)
 
         logging.info("Pre-classification successful")
         
         if is_palm_oil:
             model = AfroPalmModel()
-            prediction,confidence = model.predict(image_bytes)
+            prediction,confidence = model.predict(image_path)
             logging.debug(f"Prediction: {prediction}, Confidence: {confidence*100:.2f}%")
 
             # Generate audio
@@ -79,6 +79,9 @@ async def predict(image_request: ImageRequest):
             
         # model = AfroPalmModel()
         # prediction,confidence = model.predict(image_bytes)
+        if os.path.isfile(image_path):
+            # Remove the file after processing
+            os.remove(image_path) 
 
         return {
             "status": "success",

utils/image_preclassification.py

@@ -49,20 +49,17 @@ def pre_classification(imageURL):
                     class_name = result["class"]
                     confidence = result["confidence"]
 
-                    
-            if os.path.isfile(image_path):
-                # Remove the file after processing
-                os.remove(image_path) 
+          
                 
             if class_name == "palmoil":
-                return True
+                return True , image_path
                 
             else: 
-                return False
+                return False, image_path
 
 
         else:
-            return False
+            return False, image_path
         
     else:
         logging.error("Error loading the image for pre-classification")

utils/palmoil_classification.py

@@ -36,7 +36,7 @@ class AfroPalmModel:
 
 
 
-    def predict(self, image):
+    def predict(self, image_path):
         """
         Make a prediction on the image
         :param image: image to make prediction on
@@ -45,7 +45,7 @@ class AfroPalmModel:
 
         logging.info("Making prediction")
 
-        img = preprocess_image(image)
+        img = preprocess_image(image_path)
 
         logging.debug(f'Image preprocessed with shape {np.array(img).shape}')
 
@@ -56,4 +56,5 @@ class AfroPalmModel:
 
         logging.info("Classification successful")
 
+
         return predictions.index(max(predictions)), max(predictions)

utils/preprocessing.py

@@ -27,8 +27,10 @@ def preprocess_image(image):
         if img.shape[-1] == 1:  # Grayscale image
             img = np.stack([img, img, img], axis=-1)
         elif img.shape[-1] != 3:  # Not RGB or Grayscale
+            logging.error("Input image must be in RGB or Grayscale format")
             raise ValueError("Input image must be in RGB or Grayscale format")
     else:
+        logging.error("Unsupported image type")
         raise ValueError("Unsupported image type")
 
     # Define the transformations