Optimizers | R Documentation |
Optimization functions to use in compiling a keras model. See keras_compile()
.
SGD(lr = 0.01, momentum = 0, decay = 0, nesterov = FALSE, clipnorm = -1, clipvalue = -1) RMSprop(lr = 0.001, rho = 0.9, epsilon = 1e-08, decay = 0, clipnorm = -1, clipvalue = -1) Adagrad(lr = 0.01, epsilon = 1e-08, decay = 0, clipnorm = -1, clipvalue = -1) Adadelta(lr = 1, rho = 0.95, epsilon = 1e-08, decay = 0, clipnorm = -1, clipvalue = -1) Adam(lr = 0.001, beta_1 = 0.9, beta_2 = 0.999, epsilon = 1e-08, decay = 0, clipnorm = -1, clipvalue = -1) Adamax(lr = 0.002, beta_1 = 0.9, beta_2 = 0.999, epsilon = 1e-08, decay = 0, clipnorm = -1, clipvalue = -1) Nadam(lr = 0.002, beta_1 = 0.9, beta_2 = 0.999, epsilon = 1e-08, schedule_decay = 0.004, clipnorm = -1, clipvalue = -1)
lr |
float >= 0. Learning rate. |
momentum |
float >= 0. Parameter updates momentum. |
decay |
float >= 0. Learning rate decay over each update. |
nesterov |
boolean. Whether to apply Nesterov momentum. |
clipnorm |
float >= 0. Gradients will be clipped when their L2 norm exceeds this value. Set to -1 to disable. |
clipvalue |
float >= 0. Gradients will be clipped when their absolute value exceeds this value. Set to -1 to disable. |
rho |
float >= 0 to be used in RMSprop |
epsilon |
float >= 0. Fuzz factor. |
beta_1 |
float, 0 < beta < 1. Generally close to 1. |
beta_2 |
float, 0 < beta < 1. Generally close to 1. |
schedule_decay |
float >= 0. Learning rate decay over each schedule in Nadam. |
Taylor B. Arnold, taylor.arnold@acm.org
Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.
if(keras_available()) { X_train <- matrix(rnorm(100 * 10), nrow = 100) Y_train <- to_categorical(matrix(sample(0:2, 100, TRUE), ncol = 1), 3) mod <- Sequential() mod$add(Dense(units = 50, input_shape = dim(X_train)[2])) mod$add(Activation("relu")) mod$add(Dense(units = 3)) mod$add(Activation("softmax")) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = SGD()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = RMSprop()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = Adagrad()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = Adadelta()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = Adam()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = Adamax()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) keras_compile(mod, loss = 'categorical_crossentropy', optimizer = Nadam()) keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5, verbose = 0, validation_split = 0.2) }
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.