H5pyDeprecatioinWarning

[SanjeewaDias]

I get the following issue when running ./run.sh stage1_train. please help me

First training stage.
Training model /home/cscuser/Downloads/bird_audio/Dataset/SampleDataSet/Work/model_first_1.
Computing model /home/cscuser/Downloads/bird_audio/Dataset/SampleDataSet/Work/model_first_1 with network final_submission.
/home/cscuser/miniconda2/lib/python2.7/site-packages/h5py/_hl/dataset.py:313: H5pyDeprecationWarning: dataset.value has been deprecated. Use dataset[()] instead.
"Use dataset[()] instead.", H5pyDeprecationWarning)
WARNING (theano.tensor.blas): We did not find a dynamic library in the library_dir of the library we use for blas. If you use ATLAS, make sure to compile it with dynamics library.
WARNING:We did not find a dynamic library in the library_dir of the library we use for blas. If you use ATLAS, make sure to compile it with dynamics library.
WARNING (theano.tensor.blas): We did not find a dynamic library in the library_dir of the library we use for blas. If you use ATLAS, make sure to compile it with dynamics library.
WARNING:We did not find a dynamic library in the library_dir of the library we use for blas. If you use ATLAS, make sure to compile it with dynamics library.

[danstowell]

These are warnings, not errors. (Programs usually continue as normal even if they output warnings.) Do you have a problem?

[SanjeewaDias]

My system doesn't have a GPU memory (But have 8GB CPU memory). Are there any extra configurations to be done for my system to run this? Because when I get the above warning, system is getting stuck, even I have reduced the size of the dataset. Does it cause a huge effect without having a GPU?

[danstowell]

We haven't tried it on a non-GPU system.

You might alternatively like to try the re-implementation in Keras: https://github.com/UKYSpeechLab/ukybirddet