mnist_deepR.R

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

reticulate::py_config()

## python:         C:\conda\envs\r-reticulate\python.exe
## libpython:      C:/conda/envs/r-reticulate/python36.dll
## pythonhome:     C:\conda\envs\R-RETI~1
## version:        3.6.9 |Anaconda, Inc.| (default, Jul 30 2019, 14:00:49) [MSC v.1915 64 bit (AMD64)]
## Architecture:   64bit
## numpy:          C:\conda\envs\R-RETI~1\lib\site-packages\numpy
## numpy_version:  1.17.3
## tensorflow:     C:\conda\envs\R-RETI~1\lib\site-packages\tensorflow\__init__.p
## 
## python versions found: 
##  C:\conda\envs\r-reticulate\python.exe
##  C:\conda\envs\R-RETI~1\python.exe
##  C:\conda\python.exe
##  C:\Users\somy\AppData\Local\Programs\Python\Python38\\python.exe

tensorflow::tf_config()

## TensorFlow v1.14.0 (C:\conda\envs\R-RETI~1\lib\site-packages\tensorflow\__init__.p)
## Python v3.6 (C:\conda\envs\r-reticulate\python.exe)

# 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')




summary(model)

## Model: "sequential"
## ___________________________________________________________________________
## Layer (type)                     Output Shape                  Param #     
## ===========================================================================
## dense (Dense)                    (None, 256)                   200960      
## ___________________________________________________________________________
## dropout (Dropout)                (None, 256)                   0           
## ___________________________________________________________________________
## dense_1 (Dense)                  (None, 128)                   32896       
## ___________________________________________________________________________
## dropout_1 (Dropout)              (None, 128)                   0           
## ___________________________________________________________________________
## dense_2 (Dense)                  (None, 10)                    1290        
## ===========================================================================
## Total params: 235,146
## Trainable params: 235,146
## Non-trainable params: 0
## ___________________________________________________________________________

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



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




plot(history)