1 --    We now have 5 steps left to do in training our first torch neural network
  2 --    1. Load and normalize data
  3 --    2. Define Neural Network
  4 --    3. Define Loss function
  5 --    4. Train network on training data
  6 --    5. Test network on test data.
  7
  8
  9
 10
 11 --    1. Load and normalize data
 12 require 'paths'
 13 require 'image';
 14 if (not paths.filep("cifar10torchsmall.zip")) then
 15     os.execute('wget -c https://s3.amazonaws.com/torch7/data/cifar10torchsmall.zip')
 16     os.execute('unzip cifar10torchsmall.zip')
 17 end
 18 trainset = torch.load('cifar10-train.t7')
 19 testset = torch.load('cifar10-test.t7')
 20 classes = {'airplane', 'automobile', 'bird', 'cat',
 21            'deer', 'dog', 'frog', 'horse', 'ship', 'truck'}
 22
 23 print(trainset)
 24 print(#trainset.data)
 25
 26 itorch.image(trainset.data[100]) -- display the 100-th image in dataset
 27 print(classes[trainset.label[100]])
 28
 29 -- ignore setmetatable for now, it is a feature beyond the scope of this tutorial.
 30 -- It sets the index operator
 31 setmetatable(trainset,
 32     {__index = function(t, i)
 33                     return {t.data[i], t.label[i]}
 34                 end}
 35 );
 36 trainset.data = trainset.data:double()  -- convert the data from a ByteTensor to a DoubleTensor.
 37
 38 function trainset:size()
 39     return self.data:size(1)
 40 end
 41
 42 print(trainset:size())
 43 print(trainset[33])
 44 itorch.image(trainset[33][11])
 45
 46 redChannel = trainset.data[{ {}, {1}, {}, {} }] -- this pick {all images, 1st channel, all vertical pixels, all horizontal pixels}
 47 print(#redChannel)
 48
 49 -- TODO:fill
 50 mean = {}
 51 stdv = {}
 52 for i = 1,3 do
 53     mean[i] = trainset.data[{ {}, {i}, {}, {} }]:mean()  -- mean estimation
 54     print('Channel ' .. i .. ' , Mean: ' .. mean[i])
 55     trainset.data[{ {}, {i}, {}, {} }]:add(-mean[i]) -- mean subtraction
 56
 57     stdv[i] = trainset.data[ { {}, {i}, {}, {} }]:std()  -- std estimation
 58     print('Channel ' .. i .. ' , Standard Deviation: ' .. stdv[i])
 59     trainset.data[{ {}, {i}, {}, {} }]:div(stdv[i])  -- std scaling
 60 end
 61
 62
 63
 64 --    2. Define Neural Network
 65 net = nn.Sequential()
 66 net:add(nn.SpatialConvolution(3, 6, 5, 5)) -- 3 input image channels, 6 output channels, 5x5 convolution kernel
 67 net:add(nn.ReLU())                       -- non-linearity
 68 net:add(nn.SpatialMaxPooling(2,2,2,2))     -- A max-pooling operation that looks at 2x2 windows and finds the max.
 69 net:add(nn.SpatialConvolution(6, 16, 5, 5))
 70 net:add(nn.ReLU())                       -- non-linearity
 71 net:add(nn.SpatialMaxPooling(2,2,2,2))
 72 net:add(nn.View(16*5*5))                    -- reshapes from a 3D tensor of 16x5x5 into 1D tensor of 16*5*5
 73 net:add(nn.Linear(16*5*5, 120))             -- fully connected layer (matrix multiplication between input and weights)
 74 net:add(nn.ReLU())                       -- non-linearity
 75 net:add(nn.Linear(120, 84))
 76 net:add(nn.ReLU())                       -- non-linearity
 77 net:add(nn.Linear(84, 10))                   -- 10 is the number of outputs of the network (in this case, 10 digits)
 78 net:add(nn.LogSoftMax())                     -- converts the output to a log-probability. Useful for classification problems
 79
 80
 81 -- 3. Let us difine the Loss function
 82 criterion = nn.ClassNLLCriterion()
 83
 84
 85
 86 -- 4. Train the neural network
 87 trainer = nn.StochasticGradient(net, criterion)
 88 trainer.learningRate = 0.001
 89 trainer.maxIteration = 5 -- just do 5 epochs of training.
 90 trainer:train(trainset)
 91
 92
 93
 94 -- 5. Test the network, print accuracy
 95 print(classes[testset.label[100]])
 96 itorch.image(testset.data[100])
 97
 98 testset.data = testset.data:double()   -- convert from Byte tensor to Double tensor
 99 for i=1,3 do -- over each image channel
100     testset.data[{ {}, {i}, {}, {}  }]:add(-mean[i]) -- mean subtraction
101     testset.data[{ {}, {i}, {}, {}  }]:div(stdv[i]) -- std scaling
102 end
103
104 -- for fun, print the mean and standard-deviation of example-100
105 horse = testset.data[100]
106 print(horse:mean(), horse:std())
107
108 print(classes[testset.label[100]])
109 itorch.image(testset.data[100])
110 predicted = net:forward(testset.data[100])
111
112 -- the output of the network is Log-Probabilities. To convert them to probabilities, you have to take e^x
113 print(predicted:exp())
114
115
116 for i=1,predicted:size(1) do
117     print(classes[i], predicted[i])
118 end
119
120
121 -- test the accuracy
122 correct = 0
123 for i=1,10000 do
124     local groundtruth = testset.label[i]
125     local prediction = net:forward(testset.data[i])
126     local confidences, indices = torch.sort(prediction, true)  -- true means sort in descending order
127     if groundtruth == indices[1] then
128         correct = correct + 1
129     end
130 end
131
132
133 print(correct, 100*correct/10000 .. ' % ')
134
135 class_performance = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
136 for i=1,10000 do
137     local groundtruth = testset.label[i]
138     local prediction = net:forward(testset.data[i])
139     local confidences, indices = torch.sort(prediction, true)  -- true means sort in descending order
140     if groundtruth == indices[1] then
141         class_performance[groundtruth] = class_performance[groundtruth] + 1
142     end
143 end
144
145
146 for i=1,#classes do
147     print(classes[i], 100*class_performance[i]/1000 .. ' %')
148 end
149
150 require 'cunn';
151 net = net:cuda()
152 criterion = criterion:cuda()
153 trainset.data = trainset.data:cuda()
154 trainset.label = trainset.label:cuda()
155
156 trainer = nn.StochasticGradient(net, criterion)
157 trainer.learningRate = 0.001
158 trainer.maxIteration = 5 -- just do 5 epochs of training.
159
160
161 trainer:train(trainset)

 1 using cudnn
 2 Successfully loaded ./feature_transfer/AlexNet_files/bvlc_alexnet.caffemodel
 3 MODULE data UNDEFINED
 4 warning: module 'data [type 5]' not found
 5 nn supports no groups!
 6 warning: module 'conv2 [type 4]' not found
 7 nn supports no groups!
 8 warning: module 'conv4 [type 4]' not found
 9 nn supports no groups!
10 warning: module 'conv5 [type 4]' not found

  1 wangxiao@AHU:~/Downloads/multi-modal-visual-tracking$ qlua ./train_match_function_alexNet_version_2017_02_28.lua
  2 using cudnn
  3 Successfully loaded ./feature_transfer/AlexNet_files/bvlc_alexnet.caffemodel
  4 MODULE data UNDEFINED
  5 warning: module 'data [type 5]' not found
  6 nn supports no groups!
  7 warning: module 'conv2 [type 4]' not found
  8 nn supports no groups!
  9 warning: module 'conv4 [type 4]' not found
 10 nn supports no groups!
 11 warning: module 'conv5 [type 4]' not found
 12 conv1: 96 3 11 11
 13 conv3: 384 256 3 3
 14 fc6: 1 1 9216 4096
 15 fc7: 1 1 4096 4096
 16 fc8: 1 1 4096 1000
 17 nn.Sequential {
 18 [input -> (1) -> (2) -> (3) -> output]
 19 (1): nn.SplitTable
 20 (2): nn.ParallelTable {
 21 input
 22 |`-> (1): nn.Sequential {
 23 | [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> (11) -> (12) -> (13) -> (14) -> (15) -> (16) -> (17) -> (18) -> output]
 24 | (1): nn.SpatialConvolution(3 -> 96, 11x11, 4,4)
 25 | (2): nn.ReLU
 26 | (3): nn.SpatialCrossMapLRN
 27 | (4): nn.SpatialMaxPooling(3x3, 2,2)
 28 | (5): nn.ReLU
 29 | (6): nn.SpatialCrossMapLRN
 30 | (7): nn.SpatialMaxPooling(3x3, 2,2)
 31 | (8): nn.SpatialConvolution(256 -> 384, 3x3, 1,1, 1,1)
 32 | (9): nn.ReLU
 33 | (10): nn.ReLU
 34 | (11): nn.ReLU
 35 | (12): nn.SpatialMaxPooling(3x3, 2,2)
 36 | (13): nn.View(-1)
 37 | (14): nn.Linear(9216 -> 4096)
 38 | (15): nn.ReLU
 39 | (16): nn.Dropout(0.500000)
 40 | (17): nn.Linear(4096 -> 4096)
 41 | (18): nn.ReLU
 42 | }
 43 `-> (2): nn.Sequential {
 44 [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> (11) -> (12) -> (13) -> (14) -> (15) -> (16) -> (17) -> (18) -> output]
 45 (1): nn.SpatialConvolution(3 -> 96, 11x11, 4,4)
 46 (2): nn.ReLU
 47 (3): nn.SpatialCrossMapLRN
 48 (4): nn.SpatialMaxPooling(3x3, 2,2)
 49 (5): nn.ReLU
 50 (6): nn.SpatialCrossMapLRN
 51 (7): nn.SpatialMaxPooling(3x3, 2,2)
 52 (8): nn.SpatialConvolution(256 -> 384, 3x3, 1,1, 1,1)
 53 (9): nn.ReLU
 54 (10): nn.ReLU
 55 (11): nn.ReLU
 56 (12): nn.SpatialMaxPooling(3x3, 2,2)
 57 (13): nn.View(-1)
 58 (14): nn.Linear(9216 -> 4096)
 59 (15): nn.ReLU
 60 (16): nn.Dropout(0.500000)
 61 (17): nn.Linear(4096 -> 4096)
 62 (18): nn.ReLU
 63 }
 64 ... -> output
 65 }
 66 (3): nn.PairwiseDistance
 67 }
 68 =================================================================================================================
 69 ================= AlextNet based Siamese Search for Visual Tracking ========================
 70 =================================================================================================================
 71 ==>> The Benchmark Contain: 36 videos ...
 72 deal with video 1/36 video name: BlurFace ... please waiting ...
 73 the num of gt bbox: 493
 74 the num of video frames: 493
 75 ========>>>> Begin to track 2 video name: nil-th frame, please waiting ...
 76 ========>>>> Begin to track 3 video name: nil-th frame, please waiting ... ............] ETA: 0ms | Step: 0ms
 77 ========>>>> Begin to track 4 video name: nil-th frame, please waiting ... ............] ETA: 39s424ms | Step: 80ms
 78 ========>>>> Begin to track 5 video name: nil-th frame, please waiting ... ............] ETA: 33s746ms | Step: 69ms
 79 ========>>>> Begin to track 6 video name: nil-th frame, please waiting ... ............] ETA: 31s817ms | Step: 65ms
 80 ========>>>> Begin to track 7 video name: nil-th frame, please waiting ... ............] ETA: 32s575ms | Step: 66ms
 81 ========>>>> Begin to track 8 video name: nil-th frame, please waiting ... ............] ETA: 34s376ms | Step: 70ms
 82 ========>>>> Begin to track 9 video name: nil-th frame, please waiting ... ............] ETA: 40s240ms | Step: 82ms
 83 ========>>>> Begin to track 10 video name: nil-th frame, please waiting ... ...........] ETA: 44s211ms | Step: 91ms
 84 ========>>>> Begin to track 11 video name: nil-th frame, please waiting ... ...........] ETA: 45s993ms | Step: 95ms
 85 ========>>>> Begin to track 12 video name: nil-th frame, please waiting ... ...........] ETA: 47s754ms | Step: 99ms
 86 ========>>>> Begin to track 13 video name: nil-th frame, please waiting ... ...........] ETA: 50s392ms | Step: 104ms
 87 ========>>>> Begin to track 14 video name: nil-th frame, please waiting ... ...........] ETA: 53s138ms | Step: 110ms
 88 ========>>>> Begin to track 15 video name: nil-th frame, please waiting ... ...........] ETA: 55s793ms | Step: 116ms
 89 ========>>>> Begin to track 16 video name: nil-th frame, please waiting ... ...........] ETA: 59s253ms | Step: 123ms
 90 ========>>>> Begin to track 17 video name: nil-th frame, please waiting ... ...........] ETA: 1m2s | Step: 130ms
 91 ========>>>> Begin to track 18 video name: nil-th frame, please waiting ... ...........] ETA: 1m5s | Step: 137ms
 92 ========>>>> Begin to track 19 video name: nil-th frame, please waiting ... ...........] ETA: 1m8s | Step: 143ms
 93 ========>>>> Begin to track 20 video name: nil-th frame, please waiting ... ...........] ETA: 1m11s | Step: 149ms
 94 //..............] ETA: 1m14s | Step: 157ms
 95 ==>> pos_proposal_list: 19
 96 ==>> neg_proposal_list: 19
 97 qlua: /home/wangxiao/torch/install/share/lua/5.1/nn/Container.lua:67:
 98 In 2 module of nn.Sequential:
 99 In 1 module of nn.ParallelTable:
100 In 8 module of nn.Sequential:
101 /home/wangxiao/torch/install/share/lua/5.1/nn/THNN.lua:117: Need input of dimension 3 and input.size[0] == 256 but got input to be of shape: [96 x 13 x 13] at /tmp/luarocks_cunn-scm-1-6210/cunn/lib/THCUNN/generic/SpatialConvolutionMM.cu:49
102 stack traceback:
103 [C]: in function 'v'
104 /home/wangxiao/torch/install/share/lua/5.1/nn/THNN.lua:117: in function 'SpatialConvolutionMM_updateOutput'
105 ...ao/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:79: in function <...ao/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:76>
106 [C]: in function 'xpcall'
107 /home/wangxiao/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
108 ...e/wangxiao/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function <...e/wangxiao/torch/install/share/lua/5.1/nn/Sequential.lua:41>
109 [C]: in function 'xpcall'
110 /home/wangxiao/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
111 ...angxiao/torch/install/share/lua/5.1/nn/ParallelTable.lua:12: in function <...angxiao/torch/install/share/lua/5.1/nn/ParallelTable.lua:10>
112 [C]: in function 'xpcall'
113 /home/wangxiao/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
114 ...e/wangxiao/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
115 ./train_match_function_alexNet_version_2017_02_28.lua:525: in function 'opfunc'
116 /home/wangxiao/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'optim'
117 ./train_match_function_alexNet_version_2017_02_28.lua:550: in main chunk
118
119
120
121 WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above.
122 stack traceback:
123 [C]: at 0x7f86014df9c0
124 [C]: in function 'error'
125 /home/wangxiao/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors'
126 ...e/wangxiao/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
127 ./train_match_function_alexNet_version_2017_02_28.lua:525: in function 'opfunc'
128 /home/wangxiao/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'optim'
129 ./train_match_function_alexNet_version_2017_02_28.lua:550: in main chunk
130 wangxiao@AHU:~/Downloads/multi-modal-visual-tracking$

sudo apt-get install libhdf5-serial-dev hdf5-tools
git clone https://github.com/deepmind/torch-hdf5
cd torch-hdf5
sudo luarocks make hdf5-0-0.rockspec LIBHDF5_LIBDIR=”/usr/lib/x86_64-Linux-gnu/”

git clone https://github.com/zeromq/zeromq4-1.git
mkdir build-zeromq
cd build-zeromq
cmake ..
make && make install
安装完之后，luarocks install itorch
之后可以通过luarocks list查看是否安装成功