Pytorch to(device)用法

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

mytensor = my_tensor.to(device)

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

model = Model()

if torch.cuda.device_count() > 1:

 model = nn.DataParallel(model，device_ids=[0,1,2])

 

model.to(device)

if torch.cuda.is_available():
 h = g.cuda()
 print(h)

torch.nn.functional
Convolution函数
torch.nn.functional.vonv1d(input,weight,bias=None,stride=1,padding=0,dilation=1,groups=1)
 
 
 
torch.nn.functional.conv2d(input,weight,bias=None,stride=1,padding=0,dilation=1,group=1)
 
parameter:
 input --输入张量（minibatch * in_channels * iH * iW）-weights-– 过滤器张量 (out_channels, in_channels/groups, kH, kW) - bias – 可选偏置张量 (out_channels) - stride – 卷积核的步长，可以是单个数字或一个元组 (sh x sw)。默认为1 - padding – 输入上隐含零填充。可以是单个数字或元组。 默认值：0 - groups – 将输入分成组，in_channels应该被组数除尽
 
 
>>> # With square kernels and equal stride
>>> filters = autograd.Variable(torch.randn(8,4,3,3))
>>> inputs = autograd.Variable(torch.randn(1,4,5,5))
>>> F.conv2d(inputs, filters, padding=1)

CUDA_VISIBLE_DEVICES=1

import os

os.environ['CUDA_VISIBLE_DEVICE']='1'

import torch

torch.cuda.set_device(id)

Pytoch中的in-place

import torch
x=torch.rand(2) #tensor([0.8284, 0.5539])
print(x)
y=torch.rand(2)
print(x+y)  #tensor([1.0250, 0.7891])
print(x)  #tensor([0.8284, 0.5539])

import torch
x=torch.rand(2) #tensor([0.8284, 0.5539])
print(x)
y=torch.rand(2)
x.add_(y)
print(x)  #tensor([1.1610, 1.3789])