我想训练一个模型来学习形状为(1,3751)的特征与形状为(1,1)的标签之间的关系。
它看起来很简单,因此我只使用了两个密集层DNN作为模型类型,希望训练有素的模型可以帮助我做出足够好的预测。但是,预测值相差甚远,我注意到训练过程中的损失根本没有减少。
我尝试了不同的方法,例如更改学习率或增加模型中的隐藏层,但没有一个起作用。
以下是我的代码:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import with_statement
import argparse
import sys
import numpy as np
import pandas as pd
import tensorflow as tf
LEARNING_RATE = 0.0001
def model_fn(features, labels, mode, params):
"""Model function for Estimator."""
input_layer = tf.reshape(features["x"], [1,3751])
first_hidden_layer = tf.layers.dense(input_layer, 1000, activation=tf.nn.relu)
second_hidden_layer = tf.layers.dense(first_hidden_layer, 100, activation=tf.nn.relu)
third_hidden_layer = tf.layers.dense(second_hidden_layer,10, activation=tf.nn.relu)
predictions = tf.layers.dense(third_hidden_layer, 1)
# Provide an estimator spec for `ModeKeys.PREDICT`.
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(
mode=mode,
predictions={"ages": predictions})
labels_first_row = tf.reshape(labels[1], [1,-1])
loss = tf.losses.mean_squared_error(labels_first_row, predictions)
optimizer = tf.train.GradientDescentOptimizer(
learning_rate=params["learning_rate"])
train_op = optimizer.minimize(
loss=loss, global_step=tf.train.get_global_step())
# Calculate root mean squared error as additional eval metric
eval_metric_ops = {
"rmse": tf.metrics.root_mean_squared_error(
tf.cast(labels_first_row, tf.float32), predictions)
}
return tf.estimator.EstimatorSpec(
mode=mode,
loss=loss,
train_op=train_op,
eval_metric_ops=eval_metric_ops)
def main(unused_argv):
train_file = "training_data.csv"
test_file = "test_data.csv"
train_features_interim = pd.read_csv(train_file, usecols=['current'])
train_features_numpy = np.asarray(train_features_interim, dtype=np.float32)
train_labels_interim = pd.read_csv(train_file, usecols=['plo_tox'])
train_labels_numpy = np.asarray(train_labels_interim, dtype=np.float32)
model_params = {"learning_rate": LEARNING_RATE}
# Instantiate Estimator
nn = tf.estimator.Estimator(model_fn=model_fn, params=model_params,
model_dir='/tmp/nmos_self_define')
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": train_features_numpy},
y=train_labels_numpy,
batch_size = 3751,
num_epochs= None,
shuffle=False)
# Train
nn.train(input_fn=train_input_fn, steps=10000)
test_features_interim = pd.read_csv(test_file, usecols = ['current'])
test_features_numpy = np.asarray(test_features_interim, dtype=np.float32)
test_labels_interim = pd.read_csv(test_file, usecols=['plo_tox'])
test_labels_numpy = np.asarray(test_labels_interim, dtype=np.float32)
# Score accuracy
test_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": test_features_numpy},
y=test_labels_numpy,
batch_size = 3751,
num_epochs= None,
shuffle=False)
ev = nn.evaluate(input_fn=test_input_fn, steps = 500)
print("Loss: %s" % ev["loss"])
print("Root Mean Squared Error: %s" % ev["rmse"])
prediction_file = "Tensorflow_prediction_data.csv"
predict_features_interim = pd.read_csv(prediction_file, usecols=['current'])
predict_features_numpy = np.asarray(predict_features_interim, dtype=np.float32)
# Print out predictions
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
x= {"x": predict_features_numpy},
num_epochs=1,
batch_size = 3751,
shuffle=False)
predictions = nn.predict(input_fn=predict_input_fn)
for i, p in enumerate(predictions):
print("Prediction %s: %s" % (i + 1, p["ages"]))
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
parser = argparse.ArgumentParser()
parser.register("type", "bool", lambda v: v.lower() == "true")
parser.add_argument(
"--train_data", type=str, default="", help="Path to the training data.")
parser.add_argument(
"--test_data", type=str, default="", help="Path to the test data.")
parser.add_argument(
"--predict_data",
type=str,
default="",
help="Path to the prediction data.")
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
由于我只是机器学习的初学者,因此我认为,向更了解的人征求意见可能会更好。我认为我需要调整一些旋钮,但是我不太确定,请提供您认为有用的任何建议。
还有其他选择吗?预先感谢您提供任何想法。
答案 0 :(得分:0)
您说批次大小为3751
,在model_fn
中您将重塑输入要素的形状以塑造(1, 3751)
,这没有意义,因为tf.layers.dense
在第一维和第二维中期望每个批次和每个功能。