Tensor flow model that convert temperature in Celsius to Fahrenheit .

Celsius to Fahrenheit convertor

steps involved are:

1) Importing necessary dependencies:

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

2) Set up training data:

celsius_q    = np.array([0, 8, 15, 22,100 ],  dtype=float )

fahrenheit_a = np.array([32, 46.4, 59, 71.6,180],  dtype=float )

for i,c in enumerate(celsius_q):

    print("{} degree Celcius = {}  degree Fahrenhet" .format(c, fahrenheit_a[i]))

3) Defining the layer for CNN:

l0 = tf.keras.layers.Dense(units = 1, input_shape=[1] )

4) Assembling layer into model:

model = tf.keras.Sequential([l0])

5)Compile the model with loss and optimizer function:

model.compile(loss = 'mean_squared_error',

             optimizer = tf.keras.optimizers.Adam(0.1))

6)Training the model:

history = model.fit(celsius_q, fahrenheit_a, epochs = 500, verbose = False )

print("Finished training the model")

7) Displaying trained statistics:

plt.xlabel('Epoch Number')

plt.ylabel('Loss Magnitude')

plt.plot(history.history['loss'])

8)predicting values:

print(model.predict([100]))

print(model.predict([0]))

by running above code in Jupyter notebook step by step you can observe how things are going on.