在tensorflow中训练模型时的Epochs问题

Question

因此，我是TensorFlow2.0的新手，正在尝试训练一个简单的模型，将摄氏度转换为华氏温度。代码如下：

import tensorflow as tf
import numpy as np 
import matplotlib.pyplot as plt

c = np.array([-40, -10, 0, 8, 15, 22, 38], dtype = float)
f = np.array([-40, 14, 32, 46, 59, 72, 100], dtype = float)

lyr = tf.keras.layers.Dense(units = 1, input_shape = [1])
mod = tf.keras.Sequential([lyr])

mod.compile(loss = "mean_squared_error", optimzer = tf.keras.optimizers.Adam(0.1))

hist = mod.fit(c, f, epochs = 5000, verbose = False)

plt.xlabel("Epoch Number")
plt.ylabel("Loss Magnitude")
plt.plot(hist.history["loss"])
plt.show()

print(mod.predict([100.0]))

该模型应该只需要500个历元就能产生一个精确值，但它至少需要5000个历元才能获得精确值。发生这种情况的原因可能是什么？

Answer 1

您的代码在model.fit method.Please中使用epochs=10000作为参数，请使用以下代码：

import tensorflow as tf
import numpy as np 
import matplotlib.pyplot as plt

c = np.array([-40, -10, 0, 8, 15, 22, 38], dtype = float)
f = np.array([-40, 14, 32, 46, 59, 72, 100], dtype = float)

lyr = tf.keras.layers.Dense(units = 1, input_shape = [1])
mod = tf.keras.Sequential([lyr])

mod.compile(loss = "mean_squared_error", optimzer = tf.keras.optimizers.Adam(0.1))

hist = mod.fit(c, f, epochs = 5000, verbose = False)

plt.xlabel("Epoch Number")
plt.ylabel("Loss Magnitude")
plt.plot(hist.history["loss"])
plt.show()

print(mod.predict([100.0]))