Vision data

Prediction to mask

source

pred_to_multiclass_mask

def pred_to_multiclass_mask(
    pred:Tensor
)->Tensor:

Apply Softmax on the predicted tensor to rescale the values in the range [0, 1] and sum to 1. Then apply argmax to get the indices of the maximum value of all elements in the predicted Tensor.

Args: pred: [C,W,H,D] activation tensor.

Returns: Predicted mask.

source

batch_pred_to_multiclass_mask

def batch_pred_to_multiclass_mask(
    pred:Tensor
)->(<class 'torch.Tensor'>, <class 'int'>):

Convert a batch of predicted activation tensors to masks.

Args: pred: [B, C, W, H, D] batch of activations.

Returns: Tuple of batch of predicted masks and number of classes.

source

pred_to_binary_mask

def pred_to_binary_mask(
    pred:Tensor
)->Tensor:

Apply Sigmoid function that squishes activations into a range between 0 and 1. Then we classify all values greater than or equal to 0.5 to 1, and the values below 0.5 to 0.

Args: pred: [B, C, W, H, D] or [C, W, H, D] activation tensor

Returns: Predicted binary mask(s).

source

MedDataBlock

def MedDataBlock(
    blocks:list=None, dl_type:TfmdDL=None, getters:list=None, n_inp:int | None=None, item_tfms:list=None,
    batch_tfms:list=None, apply_reorder:bool=False, target_spacing:(<class 'int'>, <class 'list'>)=None, **kwargs
):

Container to quickly build dataloaders.

TransformBlock for segmentation

source

MedMaskBlock

def MedMaskBlock():

Create a TransformBlock for medical masks.

source

MedImageDataLoaders

def MedImageDataLoaders(
    *loaders, # `DataLoader` objects to wrap
    path:str | Path='.', # Path to store export objects
    device:NoneType=None, # Device to put `DataLoaders`
):

Higher-level MedDataBlock API.