def _get_tfbt(output_dir):
"""Configures TF Boosted Trees estimator based on flags."""
learner_config = learner_pb2.LearnerConfig()
num_classes = 10
learner_config.learning_rate_tuner.fixed.learning_rate = FLAGS.learning_rate
learner_config.num_classes = num_classes
learner_config.regularization.l1 = 0.0
learner_config.regularization.l2 = FLAGS.l2 / FLAGS.examples_per_layer
learner_config.constraints.max_tree_depth = FLAGS.depth
growing_mode = learner_pb2.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
learner_pb2.LearnerConfig.DIAGONAL_HESSIAN)
# Create a TF Boosted trees estimator that can take in custom loss.
estimator = GradientBoostedDecisionTreeClassifier(
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=FLAGS.examples_per_layer,
model_dir=output_dir,
num_trees=FLAGS.num_trees,
center_bias=False,
config=run_config)
return estimator
def _get_tfbt(output_dir, feature_cols):
"""Configures TF Boosted Trees estimator based on flags."""
learner_config = learner_pb2.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = FLAGS.learning_rate
learner_config.regularization.l1 = 0.0
# Set the regularization per instance in such a way that
# regularization for the full training data is equal to l2 flag.
learner_config.regularization.l2 = FLAGS.l2 / FLAGS.batch_size
learner_config.constraints.max_tree_depth = FLAGS.depth
learner_config.growing_mode = learner_pb2.LearnerConfig.LAYER_BY_LAYER
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=30)
# Create a TF Boosted trees regression estimator.
estimator = GradientBoostedDecisionTreeClassifier(
learner_config=learner_config,
examples_per_layer=FLAGS.examples_per_layer,
n_classes=2,
num_trees=FLAGS.num_trees,
feature_columns=feature_cols,
model_dir=output_dir,
config=run_config,
center_bias=False)
return estimator
def set_parameter(self, param):
for name in self.default_param:
if name not in param:
param[name] = self.default_param[name]
self.build_model()
self.learner_config = learner_pb2.LearnerConfig()
self.learner_config.learning_rate_tuner.fixed.learning_rate = float(
param['learning_rate'])
self.learner_config.regularization.l1 = 0.0
self.learner_config.regularization.l2 = float(param['L2']) / int(
param['examples_per_layer'])
self.learner_config.constraints.max_tree_depth = int(param['depth'])
self.growing_mode = learner_pb2.LearnerConfig.LAYER_BY_LAYER
self.learner_config.growing_mode = self.growing_mode
self.run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
self.model_path = param['model_path']
self.class_num = int(param['class_num'])
if param['objective'] is "multiclass":
print("here")
self.learner_config.num_classes = param['class_num']
self.learner_config.multi_class_strategy = (
learner_pb2.LearnerConfig.DIAGONAL_HESSIAN)
# Create a TF Boosted trees estimator that can take in custom loss.
self.estimator = GradientBoostedDecisionTreeClassifier(
learner_config=self.learner_config,
n_classes=int(self.class_num),
examples_per_layer=int(param['examples_per_layer']),
model_dir=self.model_path,
num_trees=int(param['num_trees']),
center_bias=False,
config=self.run_config)
else:
pass
self.batch_size = int(param["batch_size"])
self.eval_batch_size = int(param['eval_batch_size'])
self.num_epochs = param["num_epochs"]
learner_config = gbdt_learner.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = learning_rate
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN)\
# create a tensorflow GBDT estimator
gbdt_model = GradientBoostedDecisionTreeClassifier(
model_dir=None, # No save directory specified
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
# Display TF info logs
tf.logging.set_verbosity(tf.logging.INFO)
# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(x={'images': mnist.train.images},
y=mnist.train.labels,
batch_size=batch_size,
num_epochs=None,
shuffle=True)
# Train the Model
gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
def test2():
import tensorflow as tf
from tensorflow.contrib.boosted_trees.estimator_batch.estimator import GradientBoostedDecisionTreeClassifier
from tensorflow.contrib.boosted_trees.proto import learner_pb2 as gbdt_learner
# Ignore all GPUs (current TF GBDT does not support GPU).
import os
os.environ["CUDA_VISIBLE_DEVICES"] = ""
# 设置日志级别
tf.logging.set_verbosity(tf.logging.ERROR)
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets(
"MNIST_data",
one_hot=False,
source_url='http://yann.lecun.com/exdb/mnist/')
# 参数
batch_size = 4096 # 批次大小
num_classes = 10 # 标签数
num_features = 784 # 特征数
max_steps = 10000 # 最大步数
# GBDT Parameters
learning_rate = 0.1
l1_regul = 0.
l2_regul = 1.
examples_per_layer = 1000
num_trees = 10
max_depth = 16
# 设置参数
learner_config = gbdt_learner.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = learning_rate
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN)
# 创建模型
gbdt_model = GradientBoostedDecisionTreeClassifier(
model_dir=None, # No save directory specified
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
# Display TF info logs
tf.logging.set_verbosity(tf.logging.INFO)
# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.train.images},
y=mnist.train.labels,
batch_size=batch_size,
num_epochs=None,
shuffle=True)
# 训练
gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
# 预测
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.test.images},
y=mnist.test.labels,
batch_size=batch_size,
shuffle=False)
e = gbdt_model.evaluate(input_fn=input_fn)
print("Testing Accuracy:", e['accuracy'])
learner_config = gbdt_learner.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = learning_rate
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN)\
# Create a TensorFlor GBDT Estimator
gbdt_model = GradientBoostedDecisionTreeClassifier(
model_dir=None, # No save directory specified
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
# Display TF info logs
tf.logging.set_verbosity(tf.logging.INFO)
# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.train.images}, y=mnist.train.labels,
batch_size=batch_size, num_epochs=None, shuffle=True)
# Train the Model
gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
# Evaluate the Model
# -*- coding: utf-8 -*- # @Time : 2019/8/7 17:28 # @Author : skydm # @Email : [email protected] # @File : gbdt.py # @Software: PyCharm import os os.environ["CUDA_VISIBLE_DEVICES"] = "5" os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' import numpy as np import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data from tensorflow.contrib.boosted_trees.estimator_batch.estimator import GradientBoostedDecisionTreeClassifier import tensorflow.contrib.boosted_trees.proto.learner_pb2 as gbdt_learner # Set verbosity to display errors only (Remove this line for showing warnings) tf.logging.set_verbosity(tf.logging.ERROR) mnist = input_data.read_data_sets("./data", one_hot=False) # params learner_config = gbdt_learner.LearnerConfig() learner_config.learn gbdt_model = GradientBoostedDecisionTreeClassifier()
def run():
# 忽略所有的 GPU, 当前的 TF GBDT 不支持 GPU
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
# 设置 Tensorflow 的 log 只显示 error
tf.logging.set_verbosity(tf.logging.ERROR)
# 导入 MNIST 数据集
mnist = input_data.read_data_sets(
"/tmp/data/",
one_hot=False,
source_url='http://yann.lecun.com/exdb/mnist/')
# 超参数设置
batch_size = 4096 # 每批用来训练的数据的大小
num_classes = 10 # 最终结果一共有基类
num_features = 784 # 输入数据的特征数——每张图片的大小是 28 * 28 像素
max_steps = 10000
# GBDT 超参数
learning_rate = 0.1 # 学习率
l1_regul = 0. # L1 正则化
l2_regul = 1. # L2 正则化
examples_per_layer = 1000
num_trees = 10 # 树的数量
max_depth = 16 # 最大深度
# 设置 GBDT 的超参数
learner_config = gbdt_learner.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = learning_rate
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN)
# 创建TensorFlor GBDT 模型
gbdt_model = GradientBoostedDecisionTreeClassifier(
model_dir=None, # 不指定保存位置
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
# 展示 log 的 info 信息
tf.logging.set_verbosity(tf.logging.INFO)
# 定义用来训练的输入数据
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.train.images},
y=mnist.train.labels,
batch_size=batch_size,
num_epochs=None,
shuffle=True)
# 拟合模型
gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
# 评估拟合后的模型
# 定义用于评估的输入
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.test.images},
y=mnist.test.labels,
batch_size=batch_size,
shuffle=False)
# 使用 评估 方法来进行评估
e = gbdt_model.evaluate(input_fn=input_fn)
print("测试准确度为:", e['accuracy'])
return
learner_config = gbdt_learner.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = learning_rate
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = (
gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN)
#定义分类器
gbdt_model = GradientBoostedDecisionTreeClassifier(
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
#mini-batch输入, 训练模型
input_fn = tf.estimator.inputs.numpy_input_fn(x={'images': mnist.train.images},
y=mnist.train.labels,
batch_size=batch_size,
num_epochs=None,
shuffle=True)
gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
#测试
input_fn = tf.estimator.inputs.numpy_input_fn(x={'images': mnist.test.images},
y=mnist.test.labels,
learner_config.regularization.l1 = l1_regul
learner_config.regularization.l2 = l2_regul / examples_per_layer
learner_config.constraints.max_tree_depth = max_depth
growing_mode = gbdt_learner.LearnerConfig.LAYER_BY_LAYER
learner_config.growing_mode = growing_mode
run_config = tf.contrib.learn.RunConfig(save_checkpoints_secs=300)
learner_config.multi_class_strategy = gbdt_learner.LearnerConfig.DIAGONAL_HESSIAN
print("-0-----------------------------------------------------------")
print(mnist.train.images.dtype, mnist.train.labels.dtype)
# Create a TensorFlor GBDT Estimator
gbdt_model = GradientBoostedDecisionTreeClassifier(
model_dir=None, # No save directory specified
learner_config=learner_config,
n_classes=num_classes,
examples_per_layer=examples_per_layer,
num_trees=num_trees,
center_bias=False,
config=run_config)
# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'im': np.asarray(mnist.train.images)},
y=np.asarray(mnist.train.labels),
batch_size=batch_size,
num_epochs=None,
shuffle=False)
# Train the Model
# gbdt_model.fit(input_fn=input_fn, max_steps=max_steps)
# Evaluate the Model
