我目前正在学习TensorFlow，但无法理解为什么TensorFlow在以下简单的回归问题上不能进行正确的预测。

X是从1000到8000之间的随机数，Y是X + 250

所以如果X是2000，那么Y就是2250。这对我来说似乎是一个线性回归问题。然而，当我尝试进行预测时，结果与我预期的相差甚远，例如X为1000时，预测结果是1048，而不是1250。

此外，损失和平均损失都非常大：

{'average_loss': 10269.81, 'loss': 82158.48, 'global_step': 1000}

这是完整的代码：

import numpy as npimport pandas as pdimport matplotlib.pyplot as pltimport tensorflow as tffrom sklearn.model_selection import train_test_splitx_data = np.random.randint(1000, 8000, 1000000)y_true = x_data + 250feat_cols = [tf.feature_column.numeric_column('x', shape=[1])]estimator = tf.estimator.LinearRegressor(feature_columns=feat_cols)x_train, x_eval, y_train, y_eval = train_test_split(x_data, y_true, test_size=0.3, random_state=101)input_func = tf.estimator.inputs.numpy_input_fn({'x': x_train}, y_train, batch_size=8, num_epochs=None, shuffle=True)train_input_func = tf.estimator.inputs.numpy_input_fn({'x': x_train}, y_train, batch_size=8, num_epochs=1000, shuffle=False)eval_input_func = tf.estimator.inputs.numpy_input_fn({'x': x_eval}, y_eval, batch_size=8, num_epochs=1000, shuffle=False)estimator.train(input_fn=input_func, steps=1000)train_metrics = estimator.evaluate(input_fn=train_input_func, steps=1000)eval_metrics = estimator.evaluate(input_fn=eval_input_func, steps=1000)print(train_metrics)print(eval_metrics)brand_new_data = np.array([1000, 2000, 7000])input_fn_predict = tf.estimator.inputs.numpy_input_fn({'x': brand_new_data}, shuffle=False)prediction_result = estimator.predict(input_fn=input_fn_predict)print(list(prediction_result))

是我做错了什么，还是我误解了LinearRegression的含义？

回答：

我认为当你调整一些超参数时，它确实会起作用。我还将优化器改成了AdamOptimizer。

主要是批量大小设为1，epochs设为None。

train_input_func = tf.estimator.inputs.numpy_input_fn({‘x’: x_train}, y_train, batch_size=1, num_epochs=None, shuffle=True)

代码如下：

import tensorflow as tfimport numpy as npfrom sklearn.model_selection import train_test_splitx_data = np.random.randint(1000, 8000, 10000)y_true = x_data + 250feat_cols = tf.feature_column.numeric_column('x')optimizer = tf.train.AdamOptimizer(1e-3)estimator = tf.estimator.LinearRegressor(feature_columns=[feat_cols],optimizer=optimizer)x_train, x_eval, y_train, y_eval = train_test_split(x_data, y_true, test_size=0.3, random_state=101)train_input_func = tf.estimator.inputs.numpy_input_fn({'x': x_train}, y_train, batch_size=1, num_epochs=None,                                                      shuffle=True)eval_input_func = tf.estimator.inputs.numpy_input_fn({'x': x_eval}, y_eval, batch_size=1, num_epochs=None,                                                     shuffle=True)estimator.train(input_fn=train_input_func, steps=1005555)train_metrics = estimator.evaluate(input_fn=train_input_func, steps=10000)eval_metrics = estimator.evaluate(input_fn=eval_input_func, steps=10000)print(train_metrics)print(eval_metrics)brand_new_data = np.array([1000, 2000, 7000])input_fn_predict = tf.estimator.inputs.numpy_input_fn({'x': brand_new_data}, num_epochs=1,shuffle=False)prediction_result = estimator.predict(input_fn=input_fn_predict)for prediction in prediction_result:    print(prediction['predictions'])

指标如下：

{‘average_loss’: 3.9024353e-06, ‘loss’: 3.9024353e-06, ‘global_step’: 1005555}

{‘average_loss’: 3.9721594e-06, ‘loss’: 3.9721594e-06, ‘global_step’: 1005555}

[1250.003]

[2250.002]

[7249.997]