Can I run this code If my data have no label? about jule.torch HOT 6 CLOSED

yes, you can, replace the labels with any numbers and then run the algorithm. In this case, you just get some meaningless evaluation results.

from jule.torch.

Do the numbers that I set affect the result？

no, it will not affect the results

Do different sets have different results？

no,

Do I need to set the same category to the same number？

no, just randomly set the ground truth labels.

from jule.torch.

Thanks for your advice.
And I am having trouble when run my data:
`==> testing
NMI: nan
==> online epoch # 0 [batchSize = 100] [learningRate = 0.01]
THCudaCheck FAIL file=/tmp/luarocks_cutorch-scm-1-3009/cutorch/lib/THC/generic/THCStorage.cu line=66 error=2 : out of memory
/home/ai/torch/install/bin/luajit: /home/ai/torch/install/share/lua/5.1/nn/Container.lua:67:
In 2 module of nn.Sequential:
In 1 module of nn.Sequential:
In 2 module of nn.Sequential:
/home/ai/torch/install/share/lua/5.1/nn/THNN.lua:110: cuda runtime error (2) : out of memory at /tmp/luarocks_cutorch-scm-1-3009/cutorch/lib/THC/generic/THCStorage.cu:66
stack traceback:
[C]: in function 'v'
/home/ai/torch/install/share/lua/5.1/nn/THNN.lua:110: in function 'BatchNormalization_updateOutput'
...ai/torch/install/share/lua/5.1/nn/BatchNormalization.lua:124: in function <...ai/torch/install/share/lua/5.1/nn/BatchNormalization.lua:113>
[C]: in function 'xpcall'
/home/ai/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
/home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:41>
[C]: in function 'xpcall'
/home/ai/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
/home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:41>
[C]: in function 'xpcall'
/home/ai/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
/home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
train.lua:421: in function 'opfunc'
/home/ai/torch/install/share/lua/5.1/optim/sgd.lua:44: in function 'sgd'
train.lua:436: in function 'updateCNN'
train.lua:487: in main chunk
[C]: in function 'dofile'
...e/ai/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670

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.
stack traceback:
[C]: in function 'error'
/home/ai/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors'
/home/ai/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
train.lua:421: in function 'opfunc'
/home/ai/torch/install/share/lua/5.1/optim/sgd.lua:44: in function 'sgd'
train.lua:436: in function 'updateCNN'
train.lua:487: in main chunk
[C]: in function 'dofile'
...e/ai/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670`
How to solve this problem?

from jule.torch.

it seems that it is out of memory. How much GPU memory do you have? Which GPU are you using? Did you run the examples in this repo, such as MNIST-test, USPS, etc?

from jule.torch.

I think the labels can effect the result. The result was different when I used different labels.

from jule.torch.

you mean the NMI evaluation results? It will definitely affect these results. Also, since the CNN is randomly initialized. Each run you will have slightly different results as well.

from jule.torch.