Keras FAQ: Frequently Asked Keras Questions
How can I run Keras on GPU?
Method 1: use Theano flags.
THEANO_FLAGS=device=gpu,floatX=float32 python my_keras_script.py
The name 'gpu' might have to be changed depending on your device's identifier (e.g.
Method 2: set up your
Method 3: manually set
theano.config.floatX at the beginning of your code:
import theano theano.config.device = 'gpu' theano.config.floatX = 'float32'
How can I save a Keras model?
It is not recommended to use pickle or cPickle to save a Keras model.
If you only need to save the architecture of a model, and not its weights, you can do:
# save as JSON json_string = model.to_json() # save as YAML yaml_string = model.to_yaml()
You can then build a fresh model from this data:
# model reconstruction from JSON: from keras.models import model_from_json model = model_from_json(json_string) # model reconstruction from YAML model = model_from_yaml(yaml_string)
If you need to save the weights of a model, you can do so in HDF5:
Assuming you have code for instantiating your model, you can then load the weights you saved into a model with the same architecture:
This leads us to a way to save and reconstruct models from only serialized data:
json_string = model.to_json() open('my_model_architecture.json', 'w').write(json_string) model.save_weights('my_model_weights.h5') # elsewhere... model = model_from_json(open('my_model_architecture.json').read()) model.load_weights('my_model_weights.h5')
Why is the training loss much higher than the testing loss?
A Keras model has two modes: training and testing. Regularization mechanisms, such as Dropout and L1/L2 weight regularization, are turned off at testing time.
Besides, the training loss is the average of the losses over each batch of training data. Because your model is changing over time, the loss over the first batches of an epoch is generally higher than over the last batches. On the other hand, the testing loss for an epoch is computed using the model as it is at the end of the epoch, resulting in a lower loss.
How can I visualize the output of an intermediate layer?
You can build a Theano function that will return the output of a certain layer given a certain input, for example:
# with a Sequential model get_3rd_layer_output = theano.function([model.layers.input], model.layers.get_output(train=False)) layer_output = get_3rd_layer_output(X) # with a Graph model get_conv_layer_output = theano.function([model.inputs[i].input for i in model.input_order], model.outputs['conv'].get_output(train=False), on_unused_input='ignore') conv_output = get_conv_output(input_data_dict)
Isn't there a bug with Merge or Graph related to input concatenation?
Yes, there was a known bug with tensor concatenation in Thenao that was fixed early 2015. Please upgrade to the latest version of Theano:
sudo pip install git+git://github.com/Theano/Theano.git
How can I use Keras with datasets that don't fit in memory?
You can do batch training using
model.train_on_batch(X, y) and
model.test_on_batch(X, y). See the models documentation.
You can also see batch training in action in our CIFAR10 example.
How can I interrupt training when the validation loss isn't decreasing anymore?
You can use an
from keras.callbacks import EarlyStopping early_stopping = EarlyStopping(monitor='val_loss', patience=2) model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])
Find out more in the callbacks documentation.
How is the validation split computed?
If you set the
validation_split arugment in
model.fit to e.g. 0.1, then the validation data used will be the last 10% of the data. If you set it to 0.25, it will be the last 25% of the data, etc.
Is the data shuffled during training?
Yes, if the
shuffle argument in
model.fit is set to
True (which is the default), the training data will be randomly shuffled at each epoch.
Validation data isn't shuffled.
How can I record the training / validation loss / accuracy at each epoch?
model.fit method returns an
History callback, which has a
history attribute containing the lists of successive losses / accuracies.
hist = model.fit(X, y, validation_split=0.2) print(hist.history)