Epochs problem when training model in tensorflow

Question

So I am a newbie to Tensorflow 2.0 and was trying to train a simple model which converts a value in Celsius to Fahrenheit. Here is the code:

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]))

The model was supposed to produce a precise value with just 500 epochs but it takes at least 5000 epochs to get an accurate value. What might be the reason this happens?

Answer 1

Your code is having epochs=10000 as an argument in model.fit method.Please use the below code:

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]))