Deconv3D

Warning

Documentation for the module is under development.

Description

Info

Parent class: DeconvND

Derived classes: -

This module performs the operation of 3-dimensional transposed convolution. For more detailed theoretical information about the transposed convolution operation, see DeconvND.

Initializing

def __init__(self, inmaps, outmaps, size, stride=1, pad=0, dilation=1, wscale=1.0, useBias=True, name=None,
                 initscheme=None, empty=False, groups=1):

Parameters

Parameter	Allowed types	Description	Default
inmaps	int	Number of maps in the input tensor	-
outmaps	int	Number of maps in the output tensor	-
size	int	Convolution kernel size (the kernel is always equilateral)	-
stride	Union[int, tuple]	Convolution stride	1
pad	Union[int, tuple]	Map padding	0
dilation	Union[int, tuple]	Convolution window dilation	1
wscale	float	Random layer weights variance	1.0
useBias	bool	Specifies the layer weights initialization scheme	True
initscheme	Union[tuple, str]	Specifies the layer weights initialization scheme (see createTensorWithScheme)	None -> ("xavier_uniform", "in")
name	str	Layer name	None
empty	bool	Whether to initialize the matrix of weights and biases	False
groups	int	Number of groups the maps are split into for separate processing	1

Explanations

-

Examples

---

Basic deconvolution example

---

Necessary imports

import numpy as np
from PuzzleLib.Backend import gpuarray
from PuzzleLib.Modules import Deconv3D

Info

gpuarray is required to properly place the tensor in the GPU.

Synthetic tensor:

batchsize, inmaps, d, h, w = 1, 2, 5, 5, 5
outsize = 2
data = gpuarray.to_gpu(np.arange(batchsize * inmaps * d * h * w).reshape((batchsize, inmaps, d, h, w)).astype(np.float32))

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, useBias=False)
print(deconv(data))

---

Size parameter

---

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=3, useBias=False)
print(deconv(data))

---

Pad parameter

---

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=3, pad=1, useBias=False)
print(deconv(data))

---

Stride parameter

---

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, stride=2, useBias=False)
deconv(data)

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, stride=2, pad=3, useBias=False)
print(deconv(data))

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, stride=(2, 4, 2), pad=3, useBias=False)
print(deconv(data))

---

Параметр dilation

---

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, stride=1, pad=0, dilation=2, useBias=False)
print(deconv(data))

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, stride=1, pad=0, dilation=(3, 1, 3), useBias=False)
print(deconv(data))

---

Groups parameter

---

deconv = Deconv3D(inmaps=inmaps, outmaps=outsize, size=2, groups=2, useBias=False)
print(deconv(data))