Sun Dec 15 10:15:24 2024

regression_1d():
  python version:     3.10.12
  numpy version:      1.26.4
  tensorflow version: 2.16.1
  keras version:      3.1.1

  Neural network to solve a 1d regression problem.
  The data is read from external files.
(100, 2)
(10, 2)
[0.598499 0.60241  0.528659] [-0.40407  -0.542388  1.06106 ]
[2.03206 2.44061 2.37146] [1.3084  1.27157 2.95062]

Training:

step 0: training cost = 6.83552
step 10: training cost = 5.1941
step 20: training cost = 4.07082
step 30: training cost = 3.28452
step 40: training cost = 2.72106
step 50: training cost = 2.30759
step 60: training cost = 1.99701
step 70: training cost = 1.7584
step 80: training cost = 1.57115
step 90: training cost = 1.42129
step 100: training cost = 1.29918

Testing:


1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.2179
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 52ms/step - loss: 0.2179
Test cost: 0.2178911417722702
Weights =  [[1.5434928]]
Bias =  [1.5740871]

  Graphics saved as "regression_1d.png"

regression_1d():
  Normal end of execution.
Sun Dec 15 10:15:35 2024