Lua5.2: Torch tutorial gives an __index based Stack Overflow

Question

I have been wanting to get into torch and started with this tutorial. However I ran into a stack overflow when running the code specifically with the setmetatable function. I believe that this is happening because of the large 50000 image input file but I might be wrong. I have tried editing the luaconf.h file to try to fix it to no avail. Other than that I am running torch with Lua 5.2 and without iTorch as I had trouble setting it up.

Here is the error:

/home/student/torch/install/bin/lua: C stack overflow
stack traceback:
[C]: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
...
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:56: in function '__index'
Documents/TorchImageRecognition.lua:66: in main chunk
[C]: in function 'dofile'
...dent/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?

Otherwise my code should be the same as in the tutorial from 1. Load and normalize the data to 4. Train the neural network

Here's my code, sorry for not initially having it.

require 'torch'
require 'nn'
require 'paths'

if (not paths.filep("cifar10torchsmall.zip")) then
    os.execute('wget -c https://s3.amazonaws.com/torch7/data/cifar10torchsmall.zip')
    os.execute('unzip cifar10torchsmall.zip')
end
trainset = torch.load('cifar10-train.t7')
testset = torch.load('cifar10-test.t7')
classes = {'airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'}

print(trainset)
print(#trainset.data)

--itorch.image(trainset.data[100])
--print(classes[trainset.label[100]])
-- -- -- -- -- -- -- -- -- -- --
-- This code is from the previous parts of the tutorial
--net = nn.Sequential() 
--net:add(nn.SpatialConvolution(1, 6, 5, 5))
--neecognitiont:add(nn.ReLU())
--net:add(nn.SpatialMaxPooling(2, 2, 2, 2))
--net:add(nn.SpatialConvolution(6, 16, 5, 5))
--net:add(nn.ReLU())
--net:add(nn.SpatialMaxPooling(2, 2, 2, 2))
--net:add(nn.View(16*5*5))
--net:add(nn.Linear(16*5*5, 120))
--net:add(nn.ReLU())
--net:add(nn.Linear(120, 84))
--net:add(nn.ReLU())
--net:add(nn.Linear(84, 10))
--net:add(nn.LogSoftMax())

--print('Lenet5\n' .. net:__tostring())

--input = torch.rand(1, 32, 32)
--output = net:forward(input)
--print(output)
--net:zeroGradParameters()
--gradInput = net:backward(input, torch.rand(10))
--print(#gradInput)

--criterion = nn.ClassNLLCriterion()
--criterion:forward(output, 3)
--gradients = criterion:backward(output,  3)

--gradInput = net:backward(input, gradients)

--m= nn.SpatialConvolution(1, 3, 2, 2)
--print(m.weight)
--print(m.bias)
-- -- -- -- -- -- -- -- --

setmetatable(trainset, {__index = function(t, i)
        return {t.data[i], t.lable[i]}
end})
trainset.data = trainset.data:double()

function trainset:size()
    return self.data:size(1)
end

print(trainset:size())

print(trainset[33])

redChannel = trainset.data[{ {}, {1}, {}, {} }]
print(#redChannel)

mean = {}
stdv = {}
for i=1,3 do
    mean[i] = trainset.data[{ {}, {i}, {}, {} }]:mean()
    print('Channel ' .. i .. ', Mean: ' .. mean[i])
    trainset.data[{ {}, {i}, {}, {} }]:add(-mean[i])

    stdv[i] = trainset.data[{ {}, {i}, {}, {} }]:std()
    print('Channel ' .. i .. ', Standard Deviation: ' .. stdv[i])
    trainset.data[{ {}, {i}, {}, {} }]:div(stdv[i])
end

net = nn.Sequential()
net:add(nn.SpatialConvolution(3, 6, 5, 5))
net:add(nn.ReLU())
net:add(nn.SpatialMaxPooling(2, 2, 2, 2))
net:add(nn.SpatialConvolution(6, 16, 5, 5))
net:add(nn.ReLU())
net:add(nn.SpatialMaxPooling(2, 2, 2, 2))
net:add(nn.View(16*5*5))
net:add(nn.Linear(16*5*5, 120))
net:add(nn.ReLU())
net:add(nn.Linear(120, 84))
net:add(nn.ReLU())
net:add(nn.Linear(84, 10))
net:add(nn.LogSoftMax())

criterion = nn.ClassNLLCriterion()

trainer = nn.StochasticGradient(net, criterion)
trainer.learningRate = 0.001
trainer.maxIteration = 5
trainer:train(trainset)

Answer 1

There is a typo in setmetatable, t.lable instead of t.label