I am new for torch. Recently, I am trying to use torch to do multi-linear regression. But the error is always being infinity and nan.
For the first two error, it is obviously increasing. Here is my code.
dataset=
124.0000 81.6900 64.5000 118.0000
150.0000 103.8400 73.3000 143.0000
...
137.0000 94.9600 67.0000 191.0000
110.0000 99.7900 75.5000 192.0000
...
94.0000 89.4000 64.5000 139.0000
74.0000 93.0000 74.0000 148.0000
89.0000 93.5900 75.5000 179.0000
linLayer = nn.Linear(3,1)
model = nn.Sequential()
model:add(linLayer)
criterion = nn.MSECriterion()
feval = function(x_new)
if x ~= x_new then
x:copy(x_new)
end
_nidx_ = (_nidx_ or 0) + 1
if _nidx_ > (#dataset_inputs)[1] then _nidx_ = 1 end
local sample = dataset[_nidx_]
local inputs = sample[{ {2,4} }]
local target = sample[{ {1} }]
dl_dx:zero()
local loss_x = criterion:forward(model:forward(inputs),target)
model:backward(inputs, criterion:backward(model.output,target))
-- return loss(x) and dloss/dx
return loss_x, dl_dx
end
sgd_params = {
learningRate = 1e-3,
learningRateDecay = 1e-4,
weightDecay = 0,
momentum = 0
}
epochs = 100
for i = 1,epochs do
current_loss = 0
for i = 1,(#dataset_inputs)[1] do
_,fs = optim.sgd(feval,x,sgd_params)
current_loss = current_loss + fs[1]
end
current_loss = current_loss / (#dataset_inputs)[1]
print('epoch = ' .. i ..
' of ' .. epochs ..
' current loss = ' .. current_loss)
end
And the result:
epoch = 1 of 100 current loss = 8.1958765768632e+138
epoch = 2 of 100 current loss = 5.0759297005752e+278
epoch = 3 of 100 current loss = inf
epoch = 4 of 100 current loss = inf
epoch = 5 of 100 current loss = nan
... ...
epoch = 97 of 100 current loss = nan
epoch = 98 of 100 current loss = nan
epoch = 99 of 100 current loss = nan
epoch = 100 of 100 current loss = nan
What should I do for this problem? And I use the same way for train logistic regression. The result seems better than this. But still not good enough. Is there something wrong? Thanks a lot.
