msdnet.operations module¶

Module implementing network operations on CPU.

msdnet.operations.cfloatp¶: alias of msdnet.operations.LP_c_float

msdnet.operations.asfloatp(arr)[source]¶

msdnet.operations.cdoublep¶: alias of msdnet.operations.LP_c_double

msdnet.operations.asdoublep(arr)[source]¶

msdnet.operations.cintp¶: alias of msdnet.operations.LP_c_int

msdnet.operations.asintp(arr)[source]¶

msdnet.operations.relu(inp)[source]¶

msdnet.operations.leakyrelu(inp, w)[source]¶

msdnet.operations.sum(inp)[source]¶

msdnet.operations.std(inp, mn)[source]¶

msdnet.operations.multsum(a, b)[source]¶

msdnet.operations.softmax(inp)[source]¶

msdnet.operations.squaresum(a)[source]¶

msdnet.operations.relu2(inp, out)[source]¶

msdnet.operations.leakyrelu2(inp, out, w)[source]¶

msdnet.operations.combine(inp, out, w)[source]¶

msdnet.operations.conv2d(inp, out, f, d)[source]¶

msdnet.operations.filtergradient2d(inp, delta, ux, uy)[source]¶

msdnet.operations.indexlist(d, shp)[source]¶

msdnet.operations.setthreads(nthrds)[source]¶

class msdnet.operations.ImageData(shape, dl, nin)[source]¶

Bases: object

Object that represents a set of 2D images on CPU.

Parameters

shape – total shape of all images
dl – list of dilations in the network
nin – number of input images of network

setimages(ims)[source]¶

Set data to set of images.

Parameters: ims – set of images

setscalars(scl, start=0)[source]¶

Set each image to a scalar.

Parameters: scl – scalar values

fill(val, start=None, end=None)[source]¶

Set image data to single scalar value.

Parameters: val – scalar value

copy(start=None, end=None)[source]¶: Return copy of image data.

get(start=None, end=None)[source]¶: Return image data.

add(val, i)[source]¶

Add scalar to single image.

Parameters

val – scalar to add
i – index of image to add value to

mult(val, i)[source]¶

Multiply single image with value.

Parameters

val – value
i – index of image to multiply

prepare_forw_conv(f)[source]¶

Prepare for forward convolutions.

Parameters: f – convolution filters

forw_conv(i, outidx, dl)[source]¶

Perform forward convolutions

Parameters

i – image index to compute
outidx – image index to write output to
dl – dilation list

prepare_back_conv(f)[source]¶

Prepare for backward convolutions.

Parameters: f – convolution filters

back_conv(outidx, dl)[source]¶

Perform backward convolutions

Parameters

outidx – image index to write output to
dl – dilation list

property shape¶

relu(i)[source]¶: Apply ReLU to single image.

relu2(i, dat, j)[source]¶: Apply backpropagation ReLU to single image.

combine_all_all(dat, w)[source]¶: Compute linear combinations of images.

prepare_gradient()[source]¶: Prepare for gradient computation.

filtergradientfull(ims)[source]¶: Compute gradients for filters.

weightgradientall(delta)[source]¶: Compute gradients for weights.

sumall()[source]¶: Compute image sums.

softmax()[source]¶: Compute softmax.