lenet.R

# lenet.R
#
require(mlbench)
require(mxnet)

# MNIST loading
#
# please download MNIST from Kaggle
# https://www.kaggle.com/c/digit-recognizer/data
# and put both under ./data

train <- read.csv("data/train.csv", header=TRUE)
test <- read.csv("data/test.csv", header=TRUE)
train <- data.matrix(train)
test <- data.matrix(test)

train.x <- train[,-1]
train.y <- train[,1]

train.x <- t(train.x/255)
test <- t(test/255)

# First we construct the network:

# input
data <- mx.symbol.Variable('data')
# first conv
conv1 <- mx.symbol.Convolution(data=data, kernel=c(5,5), num_filter=20)
tanh1 <- mx.symbol.Activation(data=conv1, act_type="tanh")
pool1 <- mx.symbol.Pooling(data=tanh1, pool_type="max",
                          kernel=c(2,2), stride=c(2,2))
# second conv
conv2 <- mx.symbol.Convolution(data=pool1, kernel=c(5,5), num_filter=50)
tanh2 <- mx.symbol.Activation(data=conv2, act_type="tanh")
pool2 <- mx.symbol.Pooling(data=tanh2, pool_type="max",
                          kernel=c(2,2), stride=c(2,2))
# first fullc
flatten <- mx.symbol.Flatten(data=pool2)
fc1 <- mx.symbol.FullyConnected(data=flatten, num_hidden=500)
tanh3 <- mx.symbol.Activation(data=fc1, act_type="tanh")
# second fullc
fc2 <- mx.symbol.FullyConnected(data=tanh3, num_hidden=10)
# loss
lenet <- mx.symbol.SoftmaxOutput(data=fc2)

# Then let us reshape the matrices into arrays:

train.array <- train.x
dim(train.array) <- c(28, 28, 1, ncol(train.x))
test.array <- test
dim(test.array) <- c(28, 28, 1, ncol(test))

# Next we are going to compare the training speed on different devices, so the definition of the devices goes first:

n.gpu <- 1
device.cpu <- mx.cpu()
device.gpu <- lapply(0:(n.gpu-1), function(i) {
  mx.gpu(i)
})

# As you can see, we can pass a list of devices, to ask mxnet to train on multiple GPUs (you can do similar thing for cpu, but since internal computation of cpu is already multi-threaded, there is less gain than using GPUs).

# We start by training on CPU first. Because it takes a bit time to do so, we will only run it for one iteration.

mx.set.seed(0)
tic <- proc.time()
model <- mx.model.FeedForward.create(lenet, X=train.array, y=train.y,
                                     ctx=device.cpu, num.round=1, array.batch.size=100,
                                     learning.rate=0.05, momentum=0.9, wd=0.00001,
                                     eval.metric=mx.metric.accuracy,
                                     batch.end.callback=mx.callback.log.train.metric(100))
print(proc.time() - tic)

# Training on GPU:

mx.set.seed(0)
tic <- proc.time()
model <- mx.model.FeedForward.create(lenet, X=train.array, y=train.y,
                                     ctx=device.gpu, num.round=5, array.batch.size=100,
                                     learning.rate=0.05, momentum=0.9, wd=0.00001,
                                     eval.metric=mx.metric.accuracy,
                                     batch.end.callback=mx.callback.log.train.metric(100))
print(proc.time() - tic)