Updated pipepline predict

app.py

@@ -195,7 +195,7 @@ async def predict_pipeline_api(file: UploadFile = File(...)):
         rgb_array = np.array(img)
         logger.info(f"Converted to RGB array with shape: {rgb_array.shape}")
         
-        # Run the full pipeline
+        # Run the full pipeline (now includes resizing internally)
         results = predict_pipeline(ndvi_model, yolo_model, rgb_array)
         logger.info("Pipeline processing completed successfully")
         

yolo_predictor.py

@@ -7,6 +7,7 @@ import tifffile
 from rasterio.transform import from_bounds
 from ultralytics import YOLO
 from ndvi_predictor import normalize_rgb, predict_ndvi
+from resize_image import resize_image_optimized
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
@@ -119,26 +120,32 @@ def predict_pipeline(ndvi_model, yolo_model, rgb_array, conf=0.001):
     logger.info("Starting full prediction pipeline")
     logger.info(f"Input RGB array shape: {rgb_array.shape}, dtype: {rgb_array.dtype}")
     
-    # Step 1: Normalize RGB image
-    logger.info("Step 1: Normalizing RGB image")
-    normalized_rgb = normalize_rgb(rgb_array)
+    # Step 1: Resize RGB image to target size
+    logger.info("Step 1: Resizing RGB image to target size")
+    target_size = (640, 640)  # (height, width)
+    rgb_resized = resize_image_optimized(rgb_array, target_size)
+    logger.info(f"Resized RGB shape: {rgb_resized.shape}")
+    
+    # Step 2: Normalize RGB image
+    logger.info("Step 2: Normalizing RGB image")
+    normalized_rgb = normalize_rgb(rgb_resized)
     logger.info(f"Normalized RGB shape: {normalized_rgb.shape}, range: [{normalized_rgb.min():.3f}, {normalized_rgb.max():.3f}]")
     
-    # Step 2: Predict NDVI
-    logger.info("Step 2: Predicting NDVI from RGB")
+    # Step 3: Predict NDVI
+    logger.info("Step 3: Predicting NDVI from RGB")
     ndvi_prediction = predict_ndvi(ndvi_model, normalized_rgb)
     logger.info(f"NDVI prediction shape: {ndvi_prediction.shape}, range: [{ndvi_prediction.min():.3f}, {ndvi_prediction.max():.3f}]")
     
-    # Step 3: Create 4-channel TIFF file
-    logger.info("Step 3: Creating 4-channel TIFF file (RGB+NDVI)")
+    # Step 4: Create 4-channel TIFF file
+    logger.info("Step 4: Creating 4-channel TIFF file (RGB+NDVI)")
     
     # Create temporary file for the 4-channel TIFF
     with tempfile.NamedTemporaryFile(delete=False, suffix='.tiff') as tmp_file:
         tiff_path = tmp_file.name
     
     try:
-        # Create the 4-channel TIFF
-        create_4channel_tiff(rgb_array, ndvi_prediction, tiff_path)
+        # Create the 4-channel TIFF using resized RGB and predicted NDVI
+        create_4channel_tiff(rgb_resized, ndvi_prediction, tiff_path)
         
         # Verify the created file
         if not os.path.exists(tiff_path):
@@ -147,8 +154,8 @@ def predict_pipeline(ndvi_model, yolo_model, rgb_array, conf=0.001):
         file_size = os.path.getsize(tiff_path)
         logger.info(f"Created 4-channel TIFF file size: {file_size} bytes")
         
-        # Step 4: Run YOLO prediction on the 4-channel TIFF
-        logger.info("Step 4: Running YOLO prediction on 4-channel TIFF")
+        # Step 5: Run YOLO prediction on the 4-channel TIFF
+        logger.info("Step 5: Running YOLO prediction on 4-channel TIFF")
         results = predict_yolo(yolo_model, tiff_path, conf=conf)
         
         logger.info("Full pipeline completed successfully")