Menu
I am trying to use keras to store a model and then load it to retrain. My question is how do I set the learning rate to a new value when loading a model?
Here are my code:
# Save a model
model = Sequential()
model.add(Dense(64, kernel_initializer='uniform', input_shape=(10,)))
model.add(Activation('tanh'))
model.add(Activation('softmax'))
# learning rate is 0.001
sgd = optimizers.SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)
model.fit_generator(...)
model.save()
Then load the model,
model = load_model(model)
# Change the model's parameters here. Set the learning rate to 0.01.
model.fit_generator(...)
Thank you.
370
Save Your Neural Network Model to JSON This can be saved to a file and later loaded via the model_from_json() function that will create a new model from the JSON specification. The weights are saved directly from the model using the save_weights() function and later loaded using the symmetrical load_weights() function.
In Model Sub-Classing there are two most important functions __init__ and call. Basically, we will define all the tf. keras layers or custom implemented layers inside the __init__ method and call those layers based on our network design inside the call method which is used to perform a forward propagation.
compile method. Configures the model for training. optimizer: String (name of optimizer) or optimizer instance.
I think I find the answer:
from keras import backend as K
# To get learning rate
print(K.get_value(model.optimizer.lr))
# To set learning rate
K.set_value(model.optimizer.lr, 0.001)
keras.__version__ # 2.0.2
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With