Upload folder using huggingface_hub

README.md

@@ -68,68 +68,9 @@ Overall accuracy: **98.6%**
 
 ## Usage
 
-### Python (TensorFlow Lite Runtime on Raspberry Pi)
+This model was intended to be used with the TensorFlow Lite (TFLite) runtimes and Python 3.11. TFLite has been deprecated. As the DCSkycam project has concluded, there will not be a migration to the newer LiteRT interpreter. 
 
-```python
-import tflite_runtime.interpreter as tflite
-import numpy as np
-from PIL import Image
-
-# Load model and labels
-interpreter = tflite.Interpreter(model_path="custom_heli.tflite")
-interpreter.allocate_tensors()
-
-with open("custom_heli-labels.txt", "r") as f:
-    labels = [line.strip() for line in f.readlines()]
-
-# Prepare image (224x224, normalized to [0, 1])
-img = Image.open("candidate.jpg").convert("RGB")
-img = img.resize((224, 224))
-input_data = np.expand_dims(np.array(img, dtype=np.float32) / 255.0, axis=0)
-
-# Run inference
-input_details = interpreter.get_input_details()[0]
-interpreter.set_tensor(input_details["index"], input_data)
-interpreter.invoke()
-
-# Get results
-output = interpreter.get_tensor(interpreter.get_output_details()[0]["index"])[0]
-pred_idx = int(np.argmax(output))
-confidence = float(np.max(output))
-
-print(f"Prediction: {labels[pred_idx]} (confidence: {confidence:.4f})")
-```
-
-### Python (TensorFlow on Desktop)
-
-```python
-import tensorflow as tf
-import numpy as np
-from PIL import Image
-
-# Load model
-interpreter = tf.lite.Interpreter(model_path="custom_heli.tflite")
-interpreter.allocate_tensors()
-
-# Load labels
-with open("custom_heli-labels.txt", "r") as f:
-    labels = [line.strip() for line in f.readlines()]
-
-# Prepare and run inference (same as above)
-img = Image.open("candidate.jpg").convert("RGB")
-img = img.resize((224, 224))
-input_data = np.expand_dims(np.array(img, dtype=np.float32) / 255.0, axis=0)
-
-input_details = interpreter.get_input_details()[0]
-interpreter.set_tensor(input_details["index"], input_data)
-interpreter.invoke()
-
-output = interpreter.get_tensor(interpreter.get_output_details()[0]["index"])[0]
-pred_idx = int(np.argmax(output))
-confidence = float(np.max(output))
-
-print(f"Prediction: {labels[pred_idx]} (confidence: {confidence:.4f})")
-```
+The repository includes an `inference.py` file with a sample implementation that has been tested on desktop (OSX) and a Raspberry Pi 5 device (Trixie 64-bit).
 
 ## Citation