steganogan.utils module

steganogan.utils.bits_to_bytearray(bits)

Convert a list of bits to a bytearray

steganogan.utils.bits_to_text(bits)

Convert a list of ints in {0, 1} to text

steganogan.utils.bytearray_to_bits(x)

Convert bytearray to a list of bits

steganogan.utils.bytearray_to_text(x)

Apply error correction and decompress

steganogan.utils.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) → Tensor

Applies a 2D convolution over an input image composed of several input planes.

See Conv2d for details and output shape.

Parameters

• input – input tensor of shape \((\text{minibatch} \times \text{in\_channels} \times iH \times iW)\)

• weight – filters of shape \((\text{out\_channels} \times \frac{\text{in\_channels}}{\text{groups}} \times kH \times kW)\)

• bias – optional bias tensor of shape \((\text{out\_channels})\). Default: None

• stride – the stride of the convolving kernel. Can be a single number or a tuple (sH, sW). Default: 1

• padding – implicit zero paddings on both sides of the input. Can be a single number or a tuple (padH, padW). Default: 0

• dilation – the spacing between kernel elements. Can be a single number or a tuple (dH, dW). Default: 1

• groups – split input into groups, \(\text{in\_channels}\) should be divisible by the number of groups. Default: 1

Examples:

>>> # With square kernels and equal stride
>>> filters = torch.randn(8,4,3,3)
>>> inputs = torch.randn(1,4,5,5)
>>> F.conv2d(inputs, filters, padding=1)

steganogan.utils.create_window(window_size, channel)

steganogan.utils.first_element(storage, loc)

Returns the first element of two

steganogan.utils.gaussian(window_size, sigma)

Gaussian window.

https://en.wikipedia.org/wiki/Window_function#Gaussian_window

steganogan.utils.ssim(img1, img2, window_size=11, size_average=True)

steganogan.utils.text_to_bits(text)

Convert text to a list of ints in {0, 1}

steganogan.utils.text_to_bytearray(text)

Compress and add error correction