geowatch.tasks.depth.dzyne_img_util module

geowatch.tasks.depth.dzyne_img_util.pad(img, pad_size=32)

Pad image on the sides, so that eash side is divisible by 32 (network requirement) if pad = True:

returns image as numpy.array, tuple with padding in pixels as(x_min_pad, y_min_pad, x_max_pad, y_max_pad)

else:

returns image as numpy.array

geowatch.tasks.depth.dzyne_img_util.unpad(img, pads)

img: numpy array of the shape (height, width) pads: (x_min_pad, y_min_pad, x_max_pad, y_max_pad) @return padded image

geowatch.tasks.depth.dzyne_img_util.minmax(img)

geowatch.tasks.depth.dzyne_img_util.equalizeRGB(img)

geowatch.tasks.depth.dzyne_img_util.normalizeRGB(img, percent_range=(2, 98))

geowatch.tasks.depth.dzyne_img_util.load_image(file_name_rgb, file_name_tif)

geowatch.tasks.depth.dzyne_img_util.readRasterImage(filename: str, geoProps={}, convert=False)

Reads ntf files

[description]

Decorators:

task

Parameters:

filename {str} – filename of the file to read in

Keyword Arguments:

• (default (convert {bool} -- should raster be converted to float and normalized) – {{}})

• (default – {False})

Returns:

Tuple of (img, transform, bands, datatype)