rex_xai.input_data¶

Attributes¶

Classes¶

Functions¶

_guess_mode(input)

Module Contents¶

rex_xai.input_data.Setup¶

rex_xai.input_data._guess_mode(input)¶

class rex_xai.input_data.Data(input, model_shape, device, mode=None, process=True)¶

input¶

mode = None¶

target: rex_xai.prediction.Prediction | None = None¶

device¶

setup: Setup | None = None¶

model_shape¶

model_height: int | None¶

model_width: int | None¶

model_depth: int | None = None¶

model_channels: int | None = 1¶

model_order = None¶

mask_value = None¶

background = None¶

context = None¶

set_height(h)¶

Parameters:: h (int)

set_width(w)¶

Parameters:: w (int)

set_channels(c=None)¶

__repr__()¶

Return type:: str

set_classification(cl)¶

match_data_to_model_shape()¶: a PIL image has the from H * W * C, so if the model takes C * H * W we need to transpose self.data to get it into the correct form for the model to consume This function does not add in the batch channel at the beginning

generic_tab_preprocess()¶

load_data(astype='float32')¶

_normalise(means, stds, astype, norm)¶

try_unsqueeze()¶

generic_image_preprocess(means=None, stds=None, astype='float32', norm=255.0)¶

Parameters:: norm (Optional[float])

__get_shape()¶: returns height, width, channels, order, depth for the model

set_mask_value(m)¶