mindformers.pipeline.FillMaskPipeline

class mindformers.pipeline.FillMaskPipeline(model, tokenizer=None, **kwargs)

Pipeline for mask fill

参数

• model – a pretrained model (str or BaseModel) in _supproted_list.

• tokenizer – a tokenizer (None or Tokenizer) for text processing

forward(model_inputs, **forward_params)

Forward process

参数

model_inputs (dict) – outputs of preprocess.

返回

probs dict.

postprocess(model_outputs, **postprocess_params)

Postprocess

参数

model_outputs (dict) – outputs of forward process.

返回

The generated results

preprocess(inputs, **preprocess_params)

Preprocess of mask fill

参数

• inputs (url, PIL.Image, tensor, numpy) – the image to be classified.

• max_length (int) – max length of tokenizer’s output

• padding (False / "max_length") – padding for max_length

• return_tensors ("ms") – the type of returned tensors

返回

processed image.