"Input tensor has type float32: it requires specifying NormalizationOptions metadata to preprocess input images."
means your TFLite model expects the input images to be normalized (e.g., values scaled between 0 and 1) but no normalization metadata is provided.You can Manually Normalize Input Image.
means your TFLite model expects the input images to be normalized (e.g., values scaled between 0 and 1) but no normalization metadata is provided.You can Manually Normalize Input Image.
Code:
rgb_image = rgb_image.astype('float32') / 255.0 # Normalize to range [0, 1]mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=rgb_image)Statistics: Posted by ahsrabrifat — Sat Feb 08, 2025 5:01 pm