0
我與tensorflow波士頓住房數據教程的學習,但我將我自己的數據集:Tensorflow - 如何操作節電器
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import pandas as pd
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.INFO)
COLUMNS = ["crim", "zn", "indus", "nox", "rm", "age",
"dis", "tax", "ptratio", "medv"]
FEATURES = ["crim", "zn", "indus", "nox", "rm",
"age", "dis", "tax", "ptratio"]
LABEL = "medv"
def input_fn(data_set):
feature_cols = {k: tf.constant(data_set[k].values) for k in FEATURES}
labels = tf.constant(data_set[LABEL].values)
return feature_cols, labels
def main(unused_argv):
# Load datasets
training_set = pd.read_csv("boston_train.csv", skipinitialspace=True,
skiprows=1, names=COLUMNS)
test_set = pd.read_csv("boston_test.csv", skipinitialspace=True,
skiprows=1, names=COLUMNS)
# Set of 6 examples for which to predict median house values
prediction_set = pd.read_csv("boston_predict.csv", skipinitialspace=True,
skiprows=1, names=COLUMNS)
# Feature cols
feature_cols = [tf.contrib.layers.real_valued_column(k)
for k in FEATURES]
# Build 2 layer fully connected DNN with 10, 10 units respectively.
regressor = tf.contrib.learn.DNNRegressor(
feature_columns=feature_cols, hidden_units=[10, 10])
# Fit
regressor.fit(input_fn=lambda: input_fn(training_set), steps=5000)
# Score accuracy
ev = regressor.evaluate(input_fn=lambda: input_fn(test_set), steps=1)
loss_score = ev["loss"]
print("Loss: {0:f}".format(loss_score))
# Print out predictions
y = regressor.predict(input_fn=lambda: input_fn(prediction_set))
print("Predictions: {}".format(str(y)))
if __name__ == "__main__":
tf.app.run()
我遇到的問題是,數據集是如此巨大,通過tf.train.Saver()保存檢查點文件將填滿我的所有磁盤空間。
有沒有辦法來禁用保存檢查點文件,或減少保存在上面腳本中的檢查點的數量?
由於
非常感謝! –