PyTorch的一些類及函式

以下是一些我在使用pytorch中遇到的一些類及函式，為了便於理解和使用，將官網中的說明摘錄一些下來。

**

class conv1d(_convnd):

def __init__(self, in_channels, out_channels, kernel_size, stride=1,
padding=0, dilation=1, groups=1,
bias=true, padding_mode='zeros'):
kernel_size = _single(kernel_size)
stride = _single(stride)
padding = _single(padding)
dilation = _single(dilation)
super(conv1d, self).__init__(
in_channels, out_channels, kernel_size, stride, padding, dilation,
false, _single(0), groups, bias, padding_mode)

官網中對初始化函式中一些引數的說明：

in_channels (int): number of channels in the input image

out_channels (int): number of channels produced by the convolution

kernel_size (int or tuple): size of the convolving kernel

stride (int or tuple, optional): stride of the convolution. default: 1

padding (int or tuple, optional): zero-padding added to both sides of the input. default: 0

dilation (int or tuple, optional): spacing between kernel elements. default: 1

groups (int, optional): number of blocked connections from input channels to output channels. default: 1

bias (bool, optional): iftrue, adds a learnable bias to the output. default:true

padding_mode (string, optional). accepted valueszerosandcirculardefault:zeros

in_channels (int): 輸入影象中的通道數

out_channels (int): 由卷積產生的通道數

kernel_size (int or tuple): 卷積核的大小

stride (int or tuple, optional): 卷積的步幅

padding (int or tuple, optional): 輸入的兩邊都加上了零填充

dilation (int or tuple, optional): 卷積核元素之間的間距

groups (int, optional): 從輸入通道到輸出通道的阻塞連線數

bias (bool, optional): 如果為「 true」 ，則在輸出中新增可學習的偏差

padding_mode (string, optional): 接受值「0」和「迴圈」

class conv2d(_convnd):

def __init__(self, in_channels, out_channels, kernel_size, stride=1,
padding=0, dilation=1, groups=1,
bias=true, padding_mode='zeros'):
kernel_size = _pair(kernel_size)
stride = _pair(stride)
padding = _pair(padding)
dilation = _pair(dilation)
super(conv2d, self).__init__(
in_channels, out_channels, kernel_size, stride, padding, dilation,
false, _pair(0), groups, bias, padding_mode)

官網中對初始化函式中一些引數的說明：

in_channels (int): number of channels in the input image

out_channels (int): number of channels produced by the convolution

kernel_size (int or tuple): size of the convolving kernel

stride (int or tuple, optional): stride of the convolution. default: 1

padding (int or tuple, optional): zero-padding added to both sides of the input. default: 0

dilation (int or tuple, optional): spacing between kernel elements. default: 1

groups (int, optional): number of blocked connections from input channels to output channels. default: 1

bias (bool, optional): iftrue, adds a learnable bias to the output. default:true

padding_mode (string, optional). accepted valueszerosandcirculardefault:zeros

in_channels (int): 輸入影象中的通道數

out_channels (int): 由卷積產生的通道數

kernel_size (int or tuple): 卷積核的大小

stride (int or tuple, optional): 卷積的步幅

padding (int or tuple, optional): 輸入的兩邊都加上了零填充

dilation (int or tuple, optional): 卷積核元素之間的間距

groups (int, optional): 從輸入通道到輸出通道的阻塞連線數

bias (bool, optional): 如果為「 true」 ，則在輸出中新增可學習的偏差

padding_mode (string, optional): 接受值「0」和「迴圈」

下面是官網對於nn.conv2d輸入輸出shape的說明。

以及官網中給出的樣例

>>> # with square kernels and equal stride

>>> m = nn.conv2d(16, 33, 3, stride=2)

>>> # non-square kernels and unequal stride and with padding

>>> m = nn.conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))

>>> # non-square kernels and unequal stride and with padding and dilation

>>> m = nn.conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1))

>>> input = torch.randn(20, 16, 50, 100)

>>> output = m(input)

pytorch學習筆記(9)——nn.conv2d和其中的padding策略

pytorch的gather函式的一些粗略的理解

先給出官方文件的解釋，我覺得官方的文件寫的已經很清楚了，四個引數分別是input，dim，index，out，輸出的tensor是以index為大小的tensor。其中，這就是最關鍵的定義 out i j k tensor index i j k j k dim 0 out i j k tensor...

PyTorch的一些線性代數函式

pytorch還支援一些線性函式，免得用起來的時候自己造輪子，具體用法參考官方文件。如下表所示 函式功能 trace 對 角線元素之和 矩陣的跡 diag 對 角線元素 triu tril 矩陣的上三 角 下三 角，可指定偏移量 mm bmm 矩陣乘法，batch的矩陣乘法 addmm addbmm...

pytorch裡一些函式的說明記錄

thlongstorage thtensor newsizeof thtensor self thlongstorage thtensor newstrideof thtensor self 把thtensor的size stride資料提取出來，賦值給乙個新的thlongstorage並返回 th...