zea.data.convert.echonet

Script to convert the EchoNet database to .npy and zea formats. Will segment the images and convert them to polar coordinates.

Functions

accept_shape(tensor)	Acceptance algorithm that determines whether to reject an image based on left and right corner data.
cartesian_to_polar_matrix(cartesian_matrix)	Function that converts a timeseries of a cartesian cone to a polar representation that is more compatible with CNN's/action selection.
find_split_for_file(file_dict, target_file)	Function that finds the split for a given file in a dictionary.
get_args()	Parse command line arguments.
rotate_coordinates(data_points, degrees)	Function that rotates the datapoints by a certain degree.
segment(tensor[, number_erasing, min_clip])	Segments the background of the echonet images by setting it to 0 and creating a hard edge.

Classes

H5Processor(path_out_h5[, path_out, ...])

Stores a few variables and paths to allow for hyperthreading.

class zea.data.convert.echonet.H5Processor(path_out_h5, path_out=None, num_val=500, num_test=500, range_from=(0, 255), range_to=(-60, 0), splits=None)

Bases: object

Stores a few variables and paths to allow for hyperthreading.

get_split(hdf5_file, sequence)

Determine the split for a given file.

translate(data)

Translate the data from the processing range to final range.

zea.data.convert.echonet.accept_shape(tensor)

Acceptance algorithm that determines whether to reject an image based on left and right corner data.

Parameters:

tensor (ndarray) – Input image (sc) with 2 dimensions. (112, 112)

Returns:

Whether or not the tensor should be rejected.

Return type:

decision (bool)

zea.data.convert.echonet.cartesian_to_polar_matrix(cartesian_matrix, tip=(61, 7), r_max=107, angle=0.79, interpolation='nearest')

Function that converts a timeseries of a cartesian cone to a polar representation that is more compatible with CNN’s/action selection.

Parameters:

• cartesian_matrix (-) – (rows, cols) matrix containing time sequence of image_sc data.

• tip (-) – coordinates (in indices) of the tip of the cone. Defaults to (61, 7).

• r_max (-) – expected radius of the cone. Defaults to 107.

• angle (-) – expected angle of the cone, will be used as (-angle, angle). Defaults to 0.79.

• interpolation (-) – can be [nearest, linear, cubic]. Defaults to ‘nearest’.

Returns:

polar conversion of the input.

Return type:

polar_matrix (2d array)

zea.data.convert.echonet.find_split_for_file(file_dict, target_file)

Function that finds the split for a given file in a dictionary.

zea.data.convert.echonet.get_args()

Parse command line arguments.

zea.data.convert.echonet.rotate_coordinates(data_points, degrees)

Function that rotates the datapoints by a certain degree.

Parameters:

• data_points (ndarray) – tensor containing [N,2] (x and y) datapoints.

• degrees (int) – angle to rotate the datapoints with

Returns:

the rotated data_points.

Return type:

rotated_points (ndarray)

zea.data.convert.echonet.segment(tensor, number_erasing=0, min_clip=0)

Segments the background of the echonet images by setting it to 0 and creating a hard edge.

Parameters:

• tensor (ndarray) – Input image (sc) with 3 dimensions. (N, 112, 112)

• number_erasing (float, optional) – number to fill the background with.

Returns:

Segmented matrix of same dimensions as input

Return type:

tensor (ndarray)