Closed lamblin closed 10 years ago
Perhaps we should make unit tests for scripts/papers too. Currently maxout/cifar10.yaml is broken.
That is a good idea. But what is the run time of them?
On Tue, Jun 25, 2013 at 9:57 AM, Mehdi Mirza notifications@github.comwrote:
Perhaps we should make unit tests for scripts/papers too. Currently maxout/cifar10.yaml is broken.
— Reply to this email directly or view it on GitHubhttps://github.com/lisa-lab/pylearn2/issues/371#issuecomment-19977634 .
All tutorials in
pylearn2/scripts/tutorials
should not get broken, and be updated when the interface changes or things get deprecated.Here is the status of current tutorials:
convolutional_network.ipynb
: tested intest_convnet.py
multilayer_perceptron.ipynb
: untestedsoftmax_regression.ipynb
: untesteddbm_demo/rbm.yaml
: untesteddeep_trainer/run_deep_trainer.py
: tested indeep_trainer/test_deep_trainer.py
grbm_smd/cifar_grbm_smd.yaml
: tested ingrbm_smd/test_grbm_smd.py
, see #67For
test_convnet.py
, I copied and pasted the YAML code inconvolutional_network.ipynb
, changing a few things to make it run in a reasonable amount of time. It would be better to have the string be a template, and use Python formatting to fill in the value of hyper-parameters. If the.ipynb
file can import that template string from an external file, that would be even better, since it would avoid duplicating it.