vgg16モデルを使ったfinetune
Kaggleの「Dogs vs. Cats」をやってみる
学習データ、テストデータの準備
- 学習データは犬の写真2000枚、猫の写真2000枚
- テストデータは犬の写真1250枚、猫の写真1250枚
library(EBImage)
x_train <- array(0, c(224, 224, 3, 4000))
path <- "G:/cat/"
setwd(path)
files_cat <- list.files()
for (i in 1:2000) {
img <- readImage(files_cat[i])
resize <- resize(img, w = 224, h = 224)
x_train[,,, i] <- resize@.Data
}
path <- "G:/dog"
setwd(path)
files_dog <- list.files()
for (i in 1:2000) {
img <- readImage(files_dog[i])
resize <- resize(img, w = 224, h = 224)
x_train[,,, 2000 + i] <- resize@.Data
}
x_train <- x_train * 255
x_train[,, 1,] <- x_train[,, 1,] - 123.68
x_train[,, 2,] <- x_train[,, 2,] - 116.779
x_train[,, 3,] <- x_train[,, 3,] - 103.939
t_train <- c(rep(0, 2000), rep(1, 2000))
library(EBImage)
x_test <- array(0, c(224, 224, 3, 2500))
path <- "G:/cat_test/"
setwd(path)
files_cat <- list.files()
for (i in 1:1250) {
img <- readImage(files_cat[i])
resize <- resize(img, w = 224, h = 224)
x_test[,,, i] <- resize@.Data
}
path <- "G:/dog_test"
setwd(path)
files_dog <- list.files()
for (i in 1:1250) {
img <- readImage(files_dog[i])
resize <- resize(img, w = 224, h = 224)
x_test[,,, 1250 + i] <- resize@.Data
}
x_test <- x_test * 255
x_test[,, 1,] <- x_test[,, 1,] - 123.68
x_test[,, 2,] <- x_test[,, 2,] - 116.779
x_test[,, 3,] <- x_test[,, 3,] - 103.939
t_test <- c(rep(0, 1250), rep(1, 1250))
畳み込み層のみ計算
vgg16 <- mx.model.load("vgg16", 0)
all_layers <- vgg16$symbol$get.internals()
pool5 <- all_layers[[match("pool5_output", all_layers$outputs)]]
new.params <- vgg16$arg.params
new.params$fc6_weight <- NULL
new.params$fc6_bias <- NULL
new.params$fc7_weight <- NULL
new.params$fc7_bias <- NULL
new.params$fc8_weight <- NULL
new.params$fc8_bias <- NULL
new.model <- list(symbol = pool5, arg.params = new.params, aux.params = list())
class(new.model) <- "MXFeedForwardModel"
pred <- predict(new.model, x_train, ctx = mx.gpu())
新規に学習
rand <- sample(4000, 4000)
x_train <- pred[,,, rand]
t_train <- t_train[rand]
rm(rand)
mydata <- mx.symbol.Variable("data")
flat <- mx.symbol.flatten(data = mydata)
fc1 <- mx.symbol.FullyConnected(data = flat, name="new_fc1",num_hidden = 200)
act1 <- mx.symbol.Activation(data = fc1, act_type = "relu")
fc2 <- mx.symbol.FullyConnected(data = act1, name="new_fc2",num_hidden = 200)
act2 <- mx.symbol.Activation(data = fc2, act_type = "relu")
fc3 <- mx.symbol.FullyConnected(data = act2, name="new_fc3",num_hidden = 2)
softmax <- mx.symbol.SoftmaxOutput(data = fc3)
mx.set.seed(1)
model <- mx.model.FeedForward.create(
softmax, X = x_train,
y = t_train,
ctx = mx.cpu(),
num.round = 5,
array.batch.size = 10,
learning.rate = 0.001, momentum = 0.9,
eval.metric = mx.metric.accuracy,
initializer = mx.init.normal(0.002),
array.layout = "auto")
ニューモデルの作成
vgg16 <- mx.model.load("vgg16", 0)
all_layers <- vgg16$symbol$get.internals()
pool5 <- all_layers[[match("pool5_output", all_layers$outputs)]]
fc6 <- mx.symbol.FullyConnected(data = pool5, name = "fc6", num_hidden = 200)
act6 <- mx.symbol.Activation(data = fc6, act_type = "relu")
fc7 <- mx.symbol.FullyConnected(data = act6, name = "fc7", num_hidden = 200)
act7 <- mx.symbol.Activation(data = fc7, act_type = "relu")
fc8 <- mx.symbol.FullyConnected(data = act7, name = "fc8", num_hidden = 2)
softmax <- mx.symbol.SoftmaxOutput(data = fc8)
new.params <- vgg16$arg.params
new.params$fc6_weight <- model$arg.params$new_fc1_weight
new.params$fc6_bias <- model$arg.params$new_fc1_bias
new.params$fc7_weight <- model$arg.params$new_fc2_weight
new.params$fc7_bias <- model$arg.params$new_fc2_bias
new.params$fc8_weight <- model$arg.params$new_fc3_weight
new.params$fc8_bias <- model$arg.params$new_fc3_bias
new.model <- list(symbol = softmax, arg.params = new.params, aux.params = list())
class(new.model) <- "MXFeedForwardModel"
テストデータを用いた評価
pred <- apply(predict(new.model, x_test, ctx = mx.gpu()), 2, which.max) - 1
sum(pred == t_test) / 2500
