Keras: CuDNN not available?

Question

I am running the example kaggle_otto_nn.py of Keras with backend of theano .

In the following print out, line 5, something says:

CNMeM is enabled with initial size: 90.0% of memory, CuDNN not available

I am wondering, does this CuDNN not available matter since the GPU device is detectable? Am I running my program on GPU correctly? Or it's actually not running on GPU.

cliu@cliu-ubuntu:keras-examples$ THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32,lib.cnmem=0.9 python kaggle_otto_nn.py
Using Theano backend.
/usr/local/lib/python2.7/dist-packages/Theano-0.8.0rc1-py2.7.egg/theano/tensor/signal/downsample.py:6: UserWarning: downsample module has been moved to the theano.tensor.signal.pool module.
  "downsample module has been moved to the theano.tensor.signal.pool module.")
Using gpu device 0: Quadro K610M (CNMeM is enabled with initial size: 90.0% of memory, CuDNN not available)
Loading data...
9 classes
93 dims
Building model...
Training model...
Train on 52596 samples, validate on 9282 samples
Epoch 1/20
52596/52596 [==============================] - 6s - loss: 0.9420 - val_loss: 0.6269
Epoch 2/20
52596/52596 [==============================] - 6s - loss: 0.6955 - val_loss: 0.5817
...
Epoch 20/20
52596/52596 [==============================] - 6s - loss: 0.4866 - val_loss: 0.4819
Generating submission...
144368/144368 [==============================] - 1s     
Wrote submission to file keras-otto.csv.

Answer 1

cuDNN is a library by NVidia which increases the performance of neural networks on GPU. So your program still runs on GPU but much slower than it could have been if you had installed cuDNN.