PackClsInputs

class mmcls.datasets.transforms.PackClsInputs(meta_keys=('sample_idx', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'flip', 'flip_direction'))

Pack the inputs data for the classification.

Required Keys:

• img

• gt_label (optional)

• *meta_keys (optional)

Deleted Keys:

All keys in the dict.

Added Keys:

• inputs (torch.Tensor): The forward data of models.

• data_samples (ClsDataSample): The annotation info of the sample.

Parameters

meta_keys (Sequence[str]) –

The meta keys to be saved in the metainfo of the packed data_samples. Defaults to a tuple includes keys:

• sample_idx: The id of the image sample.

• img_path: The path to the image file.

• ori_shape: The original shape of the image as a tuple (H, W).

• img_shape: The shape of the image after the pipeline as a tuple (H, W).

• scale_factor: The scale factor between the resized image and the original image.

• flip: A boolean indicating if image flip transform was used.

• flip_direction: The flipping direction.

transform(results)

Method to pack the input data.