Hi All,
I am getting biased output from the model predicted using mxnet package in R 3.5.0.
I am posting the sample code of model training.
thank you in advance for looking into this query.
training_index <- createDataPartition(complete_set$label, p = .9, times = 1)
training_index <- unlist(training_index)
train_set <- complete_set[training_index,]
dim(train_set)
test_set <- complete_set[-training_index,]
dim(test_set)
Fix train and test datasets
train_data <- data.matrix(train_set)
train_x <- t(train_data[, -1])
train_y <- train_data[,1]
train_array <- train_x
dim(train_array) <- c(72, 72, 1, ncol(train_x))
test_data <- data.matrix(test_set)
test_x <- t(test_set[,-1])
test_y <- test_set[,1]
test_array <- test_x
dim(test_array) <- c(72, 72, 1, ncol(test_x))
test_data <- data.matrix(test_set)
test_x <- t(test_data[,-1])
test_y <- test_data[,1]
test_array <- test_x
dim(test_array) <- c(72, 72, 1, ncol(test_x))
library(mxnet)
Model
mx_data <- mx.symbol.Variable(‘data’)
1st convolutional layer 5x5 kernel and 20 filters.
conv_1 <- mx.symbol.Convolution(data = mx_data, kernel = c(6, 6), num_filter = 20)
tanh_1 <- mx.symbol.Activation(data = conv_1, act_type = “tanh”)
pool_1 <- mx.symbol.Pooling(data = tanh_1, pool_type = “max”, kernel = c(3,3), stride = c(3,3 ))
2nd convolutional layer 5x5 kernel and 50 filters.
conv_2 <- mx.symbol.Convolution(data = pool_1, kernel = c(6,6), num_filter = 30)
tanh_2 <- mx.symbol.Activation(data = conv_2, act_type = “tanh”)
pool_2 <- mx.symbol.Pooling(data = tanh_2, pool_type = “max”, kernel = c(3,3), stride = c(3, 3))
1st fully connected layer
flat <- mx.symbol.Flatten(data = pool_2)
fcl_1 <- mx.symbol.FullyConnected(data = flat, num_hidden = 500)
tanh_3 <- mx.symbol.Activation(data = fcl_1, act_type = “tanh”)
2nd fully connected layer
fcl_2 <- mx.symbol.FullyConnected(data = tanh_3, num_hidden = 2) # 2 classes
fcl_2 <- mx.symbol.FullyConnected(data = tanh_3, num_hidden = 6) # 6 classes
Output
NN_model <- mx.symbol.SoftmaxOutput(data = fcl_2)
Set seed for reproducibility
mx.set.seed(100)
Device used. Sadly not the GPU
device <- mx.cpu()
gc()
Train on 1200 samples
model <- mx.model.FeedForward.create(NN_model, X = train_array, y = train_y,
ctx = device,
num.round = 30,
# array.batch.size = 20,
learning.rate = 0.01,
# momentum = 0.9,
# wd = 0.00001,
eval.metric = mx.metric.accuracy,
epoch.end.callback = mx.callback.log.train.metric(100))
predict_probs <- predict(model, test_array)
predicted_labels <- max.col(t(predict_probs)) - 1
predicted_labels <- max.col(t(predict_probs))
table(test_data[, 1], predicted_labels)