说明：由于nvidia并未给出ubuntu16上面的cuda toolkit，本文方法不一定可行，我这边安装成功，感觉完全是瞎猫碰死耗子了。不过没有安装sample，只是其他程序可以使用显卡了。
1.第一个网址，使用
sudo apt-get install nvidia-cuda-toolkit
安装cuda toolkit，要看网速，下载很慢。还有，网址中说重启ubuntu有问题（I can't log in to my computer and end up in infinite login screen）。我这边安装了之后，正常登陆了，没有出现问题。
2.安装完之后的信息：
装的是7.5.17，不是最新的7.5.18，但是能用就行。
3.第二个网址中qed给出了在终端中持续显示GPU当前的使用率（仅限nvidia的显卡）：
nvidia-smi -l 1
结果：
说明：上面的命令貌似要显卡支持才行。也可以使用Jonathan提供的命令（目前没测试）：
watch -n0.1 "nvidia-settings -q GPUUtilization -q useddedicatedgpumemory"
4.安装完cuda之后，安装cutorch，之后安装cunn，都安装成功。使用GPU的程序也能正常运行。
5.第三个参考网址中给出了测试程序，本处稍微进行了修改，打印出来每次循环执行的时间（CPU版本和GPU版本代码实际上差不多）：
① CPU版本：
require 'torch'
require 'nn'
require 'optim'
--require 'cunn'
--require 'cutorch'
mnist = require 'mnist'
fullset = mnist.traindataset()
testset = mnist.testdataset()
trainset = {
size = 50000,
data = fullset.data[{{1,50000}}]:double(),
label = fullset.label[{{1,50000}}]
}
validationset = {
size = 10000,
data = fullset.data[{{50001,60000}}]:double(),
label = fullset.label[{{50001,60000}}]
}
trainset.data = trainset.data - trainset.data:mean()
validationset.data = validationset.data - validationset.data:mean()
model = nn.Sequential()
model:add(nn.Reshape(1, 28, 28))
model:add(nn.MulConstant(1/256.0*3.2))
model:add(nn.SpatialConvolutionMM(1, 20, 5, 5, 1, 1, 0, 0))
model:add(nn.SpatialMaxPooling(2, 2 , 2, 2, 0, 0))
model:add(nn.SpatialConvolutionMM(20, 50, 5, 5, 1, 1, 0, 0))
model:add(nn.SpatialMaxPooling(2, 2 , 2, 2, 0, 0))
model:add(nn.Reshape(4*4*50))
model:add(nn.Linear(4*4*50, 500))
model:add(nn.ReLU())
model:add(nn.Linear(500, 10))
model:add(nn.LogSoftMax())
model = require('weight-init')(model, 'xavier')
criterion = nn.ClassNLLCriterion()
--model = model:cuda()
--criterion = criterion:cuda()
--trainset.data = trainset.data:cuda()
--trainset.label = trainset.label:cuda()
--validationset.data = validationset.data:cuda()
--validationset.label = validationset.label:cuda()--[[]]
sgd_params = {
learningRate = 1e-2,
learningRateDecay = 1e-4,
weightDecay = 1e-3,
momentum = 1e-4
}
x, dl_dx = model:getParameters()
step = function(batch_size)
local current_loss = 0
local count = 0
local shuffle = torch.randperm(trainset.size)
batch_size = batch_size or 200
for t = 1,trainset.size,batch_size do
-- setup inputs and targets for this mini-batch
local size = math.min(t + batch_size - 1, trainset.size) - t
local inputs = torch.Tensor(size, 28, 28)--:cuda()
local targets = torch.Tensor(size)--:cuda()
for i = 1,size do
local input = trainset.data[shuffle[i+t]]
local target = trainset.label[shuffle[i+t]]
-- if target == 0 then target = 10 end
inputs[i] = input
targets[i] = target
end
targets:add(1)
local feval = function(x_new)
-- reset data
if x ~= x_new then x:copy(x_new) end
dl_dx:zero()
-- perform mini-batch gradient descent
local loss = criterion:forward(model:forward(inputs), targets)
model:backward(inputs, criterion:backward(model.output, targets))
return loss, dl_dx
end
_, fs = optim.sgd(feval, x, sgd_params)
-- fs is a table containing value of the loss function
-- (just 1 value for the SGD optimization)
count = count + 1
current_loss = current_loss + fs[1]
end
-- normalize loss
return current_loss / count
end
eval = function(dataset, batch_size)
local count = 0
batch_size = batch_size or 200
for i = 1,dataset.size,batch_size do
local size = math.min(i + batch_size - 1, dataset.size) - i
local inputs = dataset.data[{{i,i+size-1}}]--:cuda()
local targets = dataset.label[{{i,i+size-1}}]:long()--:cuda()
local outputs = model:forward(inputs)
local _, indices = torch.max(outputs, 2)
indices:add(-1)
local guessed_right = indices:eq(targets):sum()
count = count + guessed_right
end
return count / dataset.size
end
max_iters = 5
do
local last_accuracy = 0
local decreasing = 0
local threshold = 1 -- how many deacreasing epochs we allow
for i = 1,max_iters do
timer = torch.Timer()
local loss = step()
print(string.format('Epoch: %d Current loss: %4f', i, loss))
local accuracy = eval(validationset)
print(string.format('Accuracy on the validation set: %4f', accuracy))
if accuracy < last_accuracy then
if decreasing > threshold then break end
decreasing = decreasing + 1
else
decreasing = 0
end
last_accuracy = accuracy
print('Time elapsed: ' .. i .. 'iter: ' .. timer:time().real .. ' seconds')
end
end
testset.data = testset.data:double()
eval(testset)
② GPU版本：
require 'torch'
require 'nn'
require 'optim'
require 'cunn'
require 'cutorch'
mnist = require 'mnist'
fullset = mnist.traindataset()
testset = mnist.testdataset()
trainset = {
size = 50000,
data = fullset.data[{{1,50000}}]:double(),
label = fullset.label[{{1,50000}}]
}
validationset = {
size = 10000,
data = fullset.data[{{50001,60000}}]:double(),
label = fullset.label[{{50001,60000}}]
}
trainset.data = trainset.data - trainset.data:mean()
validationset.data = validationset.data - validationset.data:mean()
model = nn.Sequential()
model:add(nn.Reshape(1, 28, 28))
model:add(nn.MulConstant(1/256.0*3.2))
model:add(nn.SpatialConvolutionMM(1, 20, 5, 5, 1, 1, 0, 0))
model:add(nn.SpatialMaxPooling(2, 2 , 2, 2, 0, 0))
model:add(nn.SpatialConvolutionMM(20, 50, 5, 5, 1, 1, 0, 0))
model:add(nn.SpatialMaxPooling(2, 2 , 2, 2, 0, 0))
model:add(nn.Reshape(4*4*50))
model:add(nn.Linear(4*4*50, 500))
model:add(nn.ReLU())
model:add(nn.Linear(500, 10))
model:add(nn.LogSoftMax())
model = require('weight-init')(model, 'xavier')
criterion = nn.ClassNLLCriterion()
model = model:cuda()
criterion = criterion:cuda()
trainset.data = trainset.data:cuda()
trainset.label = trainset.label:cuda()
validationset.data = validationset.data:cuda()
validationset.label = validationset.label:cuda()--[[]]
sgd_params = {
learningRate = 1e-2,
learningRateDecay = 1e-4,
weightDecay = 1e-3,
momentum = 1e-4
}
x, dl_dx = model:getParameters()
step = function(batch_size)
local current_loss = 0
local count = 0
local shuffle = torch.randperm(trainset.size)
batch_size = batch_size or 200
for t = 1,trainset.size,batch_size do
-- setup inputs and targets for this mini-batch
local size = math.min(t + batch_size - 1, trainset.size) - t
local inputs = torch.Tensor(size, 28, 28):cuda()
local targets = torch.Tensor(size):cuda()
for i = 1,size do
local input = trainset.data[shuffle[i+t]]
local target = trainset.label[shuffle[i+t]]
-- if target == 0 then target = 10 end
inputs[i] = input
targets[i] = target
end
targets:add(1)
local feval = function(x_new)
-- reset data
if x ~= x_new then x:copy(x_new) end
dl_dx:zero()
-- perform mini-batch gradient descent
local loss = criterion:forward(model:forward(inputs), targets)
model:backward(inputs, criterion:backward(model.output, targets))
return loss, dl_dx
end
_, fs = optim.sgd(feval, x, sgd_params)
-- fs is a table containing value of the loss function
-- (just 1 value for the SGD optimization)
count = count + 1
current_loss = current_loss + fs[1]
end
-- normalize loss
return current_loss / count
end
eval = function(dataset, batch_size)
local count = 0
batch_size = batch_size or 200
for i = 1,dataset.size,batch_size do
local size = math.min(i + batch_size - 1, dataset.size) - i
local inputs = dataset.data[{{i,i+size-1}}]:cuda()
local targets = dataset.label[{{i,i+size-1}}]:long():cuda()
local outputs = model:forward(inputs)
local _, indices = torch.max(outputs, 2)
indices:add(-1)
local guessed_right = indices:eq(targets):sum()
count = count + guessed_right
end
return count / dataset.size
end
max_iters = 5
do
local last_accuracy = 0
local decreasing = 0
local threshold = 1 -- how many deacreasing epochs we allow
for i = 1,max_iters do
timer = torch.Timer()
local loss = step()
print(string.format('Epoch: %d Current loss: %4f', i, loss))
local accuracy = eval(validationset)
print(string.format('Accuracy on the validation set: %4f', accuracy))
if accuracy < last_accuracy then
if decreasing > threshold then break end
decreasing = decreasing + 1
else
decreasing = 0
end
last_accuracy = accuracy
print('Time elapsed: ' .. i .. 'iter: ' .. timer:time().real .. ' seconds')
end
end
testset.data = testset.data:double()
eval(testset)
6.CPU和GPU使用率
① CPU版本
CPU情况：
② GPU版本
CPU情况：
7.可以看出，CPU版本的程序，CPU全部使用上了，GPU则基本没用。GPU版本，只有一个核心（线程）的CPU完全是用上了，其他的则在围观。而GPU使用率已经很高了。
8.时间比较
CPU版本：
Epoch: 1 Current loss: 0.619644
Accuracy on the validation set: 0.924800
Time elapsed: 1iter: 895.69850516319 seconds
Epoch: 2 Current loss: 0.225129
Accuracy on the validation set: 0.949000
Time elapsed: 2iter: 914.15352702141 seconds
GPU版本：
Epoch: 1 Current loss: 0.687380
Accuracy on the validation set: 0.925300
Time elapsed: 1iter: 14.031280994415 seconds
Epoch: 2 Current loss: 0.231011
Accuracy on the validation set: 0.944000
Time elapsed: 2iter: 13.848378896713 seconds
Epoch: 3 Current loss: 0.167991
Accuracy on the validation set: 0.959800
Time elapsed: 3iter: 14.071791887283 seconds
Epoch: 4 Current loss: 0.135209
Accuracy on the validation set: 0.963700
Time elapsed: 4iter: 14.238609790802 seconds
Epoch: 5 Current loss: 0.113471
Accuracy on the validation set: 0.966800
Time elapsed: 5iter: 14.328102111816 seconds
说明：
① CPU为4790K@4.4GHZ（8线程全开时，应该没有这么高的主频，具体多少没注意）；GPU为nvidia GTX 970。
② 由于CPU版本的执行时间实在太长，我都怀疑程序是否有问题了。但是看着CPU一直100%的全力工作，又不忍心暂停。直到第一次循环结束，用了将近900s，才意识到，原来程序应该木有错误。等第二次循环结束，就直接停止测试了。GPU版本的程序，每次循环则只用14s，时间上差距。使用CPU执行时间是GPU执行时间的64倍。