pyflink.multimodal.utils.run_image_batch_inference

run_image_batch_inference(image_series, predict_fn, mode='RGB')

Prepare a decoded Image batch, run inference, and scatter results.

mode is the model-input normalization mode. Most vision models expect RGB tensors, so the default converts non-null Image rows to RGB before calling predict_fn. Operators that intentionally consume another image mode should pass it explicitly.