tf_api

main.py

import numpy as np
import tf_api as tf

# Create model
model = lambda x: 1.23 * x + 10

# Create small dataset of 5 entries
train_X = np.linspace(0, 5, 5).reshape((-1, 1))
train_Y = np.array([model(x) for x in train_X]).reshape((-1, 1))

# Create default graph
tf.Graph().as_default()

X = tf.Placeholder()

# Weights
Wh = tf.Variable(np.array([[0.5, 0.3, 0.2]]))
Wo = tf.Variable(np.array([[0.4,0.1,0.2]]).T)

# Biases
Bh = tf.Variable(np.array([0.1, 0.2, 0.3]))
Bo = tf.Variable(np.array([0.2]))

# Computations (input → hidden and hidden → output)
hidden_output = tf.add(tf.matmul(X, Wh), Bh)
output = tf.add(tf.matmul(hidden_output, Wo), Bo)

# Create session
session = tf.Session()

# Run session and train for 5 epochs
for epoch in range(5):
  for x in train_X:
    pred = session.run(output, { X: x })
    print(pred)