Commit 9e9a0f42 authored by Constantin Pohl's avatar Constantin Pohl
Browse files

+7% accuracy (Philipps idea)

parent edcbb3d9
......@@ -40,12 +40,13 @@ def build_model_columns():
#numeric column because of float value in certain range
#COURSE is the key, necessary to map attribute to feature column
course = tf.feature_column.numeric_column('COURSE')
shiptype = tf.feature_column.numeric_column('SHIPTYPE')
#see above
lon = tf.feature_column.numeric_column('LON')
lat = tf.feature_column.numeric_column('LAT')
#combine to single variable
base_columns = [course, lon, lat]
base_columns = [lon, lat, course, shiptype]
return base_columns
#construct estimator for the model (with directory specification)
......@@ -79,6 +80,10 @@ def input_fn(data_file, num_epochs, batch_size):
#reading raw file
dataset = tf.data.TextLineDataset(data_file)
#shuffle for each epoch run
#HINT: does not improve accuracy; since there are timestamps shuffling maybe not useful
#dataset = dataset.shuffle(buffer_size=32000)
#map and parse input strings into features
dataset = dataset.map(parse_csv, num_parallel_calls=5)
......@@ -94,8 +99,12 @@ def input_fn(data_file, num_epochs, batch_size):
#main
def main(unused_argv):
#parametrization
#for a good explanation look at https://towardsdatascience.com/epoch-vs-iterations-vs-batch-size-4dfb9c7ce9c9
#num_epochs is the number of full runs through the training data file (5 = run five times)
num_epochs = 5
#batch_size derives the amount of steps in each epoch (1 means there is one step with all 400.000 input tuples at once)
batch_size = 10
#directories
model_dir = "./model/"
train_data = "./train_data/training_data.csv"
test_data = "./train_data/testing_data.csv"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment