NLVRInferencer¶

class mmpretrain.apis.NLVRInferencer(model, pretrained=True, device=None, device_map=None, offload_folder=None, **kwargs)[source]¶

The inferencer for Natural Language for Visual Reasoning.

Parameters:

model (BaseModel | str | Config) – A model name or a path to the config file, or a BaseModel object. The model name can be found by NLVRInferencer.list_models() and you can also query it in 模型库统计.
pretrained (str, optional) – Path to the checkpoint. If None, it will try to find a pre-defined weight from the model you specified (only work if the model is a model name). Defaults to None.
device (str, optional) – Device to run inference. If None, the available device will be automatically used. Defaults to None.
**kwargs – Other keyword arguments to initialize the model (only work if the model is a model name).

__call__(inputs, return_datasamples=False, batch_size=1, **kwargs)[source]¶

Call the inferencer.

Parameters:

inputs (tuple, List[tuple]) – The input data tuples, every tuple should include three items (left image, right image, text). The image can be a path or numpy array.
return_datasamples (bool) – Whether to return results as DataSample. Defaults to False.
batch_size (int) – Batch size. Defaults to 1.
resize (int, optional) – Resize the short edge of the image to the specified length before visualization. Defaults to None.
draw_score (bool) – Whether to draw the prediction scores of prediction categories. Defaults to True.
show (bool) – Whether to display the visualization result in a window. Defaults to False.
wait_time (float) – The display time (s). Defaults to 0, which means “forever”.
show_dir (str, optional) – If not None, save the visualization results in the specified directory. Defaults to None.

Returns:

The inference results.

Return type:

list

static list_models(pattern=None)[source]¶

List all available model names.

Parameters:: pattern (str | None) – A wildcard pattern to match model names.
Returns:: a list of model names.
Return type:: List[str]