spyrit.misc.load_data.generate_synthetic_tumors

spyrit.misc.load_data.generate_synthetic_tumors(x: Tensor, tumor_params: List[dict]) → Tuple[Tensor, Tensor]

Creates synthetic Gaussian tumors to a tensor of shape (batch, n_wav, *img_shape).

Args:

x (torch.Tensor): Input tensor of shape (batch, n_wav, *img_shape)

tumor_params (List[dict]): List of tumor parameters. Each dict should contain:

• center: (row, col) center position of the tumor

• sigma_x: Standard deviation of the Gaussian in the x direction

• sigma_y: Standard deviation of the Gaussian in the y direction

• amplitude: Amplitude of the tumor

• channels: List of channel indices to add the tumor to (if None, adds to all channels)

• angle (optional): Rotation angle in degrees (counter-clockwise). Default is 0.

Returns:

Tuple of (tumors, x_with_tumors):

• tumors (torch.Tensor): Tensor of the same shape as x containing only the tumor contributions.

• x_with_tumors (torch.Tensor): Tensor of the same shape as x with the tumors added and values clamped to [0, 1].