Training Run

Attributes

context	cloudml
script	train.R
started	2017-12-08 20:46:18 GMT
time	00:02:08

Metrics

loss	0.0515
acc	0.9864
val_loss	0.1124
val_acc	0.9812

Optimization

loss	categorical_crossentropy
optimizer	<keras.optimizers.RMSprop>
lr	0.001

Training

samples	48,000
validation_samples	12,000
epochs	30
batch_size	128

History

30
val_loss	0.1124
loss	0.0515

Model

Layer (type)                        Output Shape                    Param #     
================================================================================
dense_1 (Dense)                     (None, 256)                     200960      
________________________________________________________________________________
dropout_1 (Dropout)                 (None, 256)                     0           
________________________________________________________________________________
dense_2 (Dense)                     (None, 128)                     32896       
________________________________________________________________________________
dropout_2 (Dropout)                 (None, 128)                     0           
________________________________________________________________________________
dense_3 (Dense)                     (None, 10)                      1290        
================================================================================
Total params: 235,146
Trainable params: 235,146
Non-trainable params: 0
________________________________________________________________________________


	> library(keras)

	> mnist <- dataset_mnist()

	> x_train <- mnist$train$x

	> y_train <- mnist$train$y

	> x_test <- mnist$test$x

	> y_test <- mnist$test$y

	> x_train <- array_reshape(x_train, c(nrow(x_train),
	+ 784))

	> x_test <- array_reshape(x_test, c(nrow(x_test), 784))

	> x_train <- x_train/255

	> x_test <- x_test/255

	> y_train <- to_categorical(y_train, 10)

	> y_test <- to_categorical(y_test, 10)

	> model <- keras_model_sequential()

	> model %>% layer_dense(units = 256, activation = "relu",
	+ input_shape = c(784)) %>% layer_dropout(rate = 0.4) %>% layer_dense(units = 128,
	+ .... [TRUNCATED]

	> model %>% compile(loss = "categorical_crossentropy",
	+ optimizer = optimizer_rmsprop(), metrics = c("accuracy"))

	> model %>% fit(x_train, y_train, epochs = 30, batch_size = 128,
	+ validation_split = 0.2)

	> export_savedmodel(model, "savedmodel")
	[1] "savedmodel/saved_model.pb"

	library(keras)

	mnist <- dataset_mnist()
	x_train <- mnist$train$x
	y_train <- mnist$train$y
	x_test <- mnist$test$x
	y_test <- mnist$test$y

	# reshape
	x_train <- array_reshape(x_train, c(nrow(x_train), 784))
	x_test <- array_reshape(x_test, c(nrow(x_test), 784))
	# rescale
	x_train <- x_train / 255
	x_test <- x_test / 255

	y_train <- to_categorical(y_train, 10)
	y_test <- to_categorical(y_test, 10)

	model <- keras_model_sequential()

	model %>%
	layer_dense(units = 256, activation = 'relu', input_shape = c(784)) %>%
	layer_dropout(rate = 0.4) %>%
	layer_dense(units = 128, activation = 'relu') %>%
	layer_dropout(rate = 0.3) %>%
	layer_dense(units = 10, activation = 'softmax')

	model %>% compile(
	loss = 'categorical_crossentropy',
	optimizer = optimizer_rmsprop(),
	metrics = c('accuracy')
	)

	model %>% fit(
	x_train, y_train,
	epochs = 30, batch_size = 128,
	validation_split = 0.2
	)

	export_savedmodel(model, "savedmodel")