transformers/docs/source/zh/main_classes/image_processor.md

Image Processor

Image processor负责为视觉模型准备输入特征并后期处理处理它们的输出。这包括诸如调整大小、归一化和转换为PyTorch、TensorFlow、Flax和NumPy张量等转换。它还可能包括特定于模型的后期处理，例如将logits转换为分割掩码。

ImageProcessingMixin

[[autodoc]] image_processing_utils.ImageProcessingMixin - from_pretrained - save_pretrained

BatchFeature

[[autodoc]] BatchFeature

BaseImageProcessor

[[autodoc]] image_processing_utils.BaseImageProcessor