Regression With TensorFlow

In [25]:

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

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

In [26]:

X = tf.range(-100, 100, 4)
X

X = tf.range(-100, 100, 4) X

Out[26]:

<tf.Tensor: shape=(50,), dtype=int32, numpy=
array([-100,  -96,  -92,  -88,  -84,  -80,  -76,  -72,  -68,  -64,  -60,
        -56,  -52,  -48,  -44,  -40,  -36,  -32,  -28,  -24,  -20,  -16,
        -12,   -8,   -4,    0,    4,    8,   12,   16,   20,   24,   28,
         32,   36,   40,   44,   48,   52,   56,   60,   64,   68,   72,
         76,   80,   84,   88,   92,   96], dtype=int32)>

In [27]:

y = X + 10
y

y = X + 10 y

Out[27]:

<tf.Tensor: shape=(50,), dtype=int32, numpy=
array([-90, -86, -82, -78, -74, -70, -66, -62, -58, -54, -50, -46, -42,
       -38, -34, -30, -26, -22, -18, -14, -10,  -6,  -2,   2,   6,  10,
        14,  18,  22,  26,  30,  34,  38,  42,  46,  50,  54,  58,  62,
        66,  70,  74,  78,  82,  86,  90,  94,  98, 102, 106], dtype=int32)>

In [28]:

X_train = X[:40]
X_test = X[40:]

X_train = X[:40] X_test = X[40:]

In [29]:

X_train, X_test

X_train, X_test

Out[29]:

(<tf.Tensor: shape=(40,), dtype=int32, numpy=
 array([-100,  -96,  -92,  -88,  -84,  -80,  -76,  -72,  -68,  -64,  -60,
         -56,  -52,  -48,  -44,  -40,  -36,  -32,  -28,  -24,  -20,  -16,
         -12,   -8,   -4,    0,    4,    8,   12,   16,   20,   24,   28,
          32,   36,   40,   44,   48,   52,   56], dtype=int32)>,
 <tf.Tensor: shape=(10,), dtype=int32, numpy=array([60, 64, 68, 72, 76, 80, 84, 88, 92, 96], dtype=int32)>)

In [30]:

y_train = y[:40]
y_test = y[40:]

y_train = y[:40] y_test = y[40:]

In [31]:

plt.scatter(X, y)

plt.scatter(X, y)

Out[31]:

<matplotlib.collections.PathCollection at 0x7f8c5d722690>

MODEL 1¶

In [32]:

# 1. Creating a model 
model_1 = tf.keras.Sequential([
   tf.keras.layers.Dense(100, activation="relu"),
   tf.keras.layers.Dense(100, activation="relu"),
   tf.keras.layers.Dense(1)                            
])

# 2. Compiling a model
model_1.compile(loss=tf.keras.losses.mae,
                optimizer=tf.keras.optimizers.Adam(lr=0.01),
                metrics=["mae"])

# 3. Model fitting
model_1.fit(X_train, y_train, epochs=200)

# 1. Creating a model model_1 = tf.keras.Sequential([ tf.keras.layers.Dense(100, activation="relu"), tf.keras.layers.Dense(100, activation="relu"), tf.keras.layers.Dense(1) ]) # 2. Compiling a model model_1.compile(loss=tf.keras.losses.mae, optimizer=tf.keras.optimizers.Adam(lr=0.01), metrics=["mae"]) # 3. Model fitting model_1.fit(X_train, y_train, epochs=200)

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:375: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  "The `lr` argument is deprecated, use `learning_rate` instead.")

Epoch 1/200
2/2 [==============================] - 0s 7ms/step - loss: 33.4998 - mae: 33.4998
Epoch 2/200
2/2 [==============================] - 0s 8ms/step - loss: 14.6662 - mae: 14.6662
Epoch 3/200
2/2 [==============================] - 0s 8ms/step - loss: 5.7571 - mae: 5.7571
Epoch 4/200
2/2 [==============================] - 0s 8ms/step - loss: 10.2666 - mae: 10.2666
Epoch 5/200
2/2 [==============================] - 0s 7ms/step - loss: 5.4345 - mae: 5.4345
Epoch 6/200
2/2 [==============================] - 0s 7ms/step - loss: 5.8424 - mae: 5.8424
Epoch 7/200
2/2 [==============================] - 0s 9ms/step - loss: 6.5238 - mae: 6.5238
Epoch 8/200
2/2 [==============================] - 0s 8ms/step - loss: 7.8366 - mae: 7.8366
Epoch 9/200
2/2 [==============================] - 0s 5ms/step - loss: 4.4315 - mae: 4.4315
Epoch 10/200
2/2 [==============================] - 0s 7ms/step - loss: 6.9566 - mae: 6.9566
Epoch 11/200
2/2 [==============================] - 0s 7ms/step - loss: 6.9313 - mae: 6.9313
Epoch 12/200
2/2 [==============================] - 0s 7ms/step - loss: 7.5538 - mae: 7.5538
Epoch 13/200
2/2 [==============================] - 0s 14ms/step - loss: 5.2471 - mae: 5.2471
Epoch 14/200
2/2 [==============================] - 0s 6ms/step - loss: 6.1510 - mae: 6.1510
Epoch 15/200
2/2 [==============================] - 0s 8ms/step - loss: 7.6283 - mae: 7.6283
Epoch 16/200
2/2 [==============================] - 0s 6ms/step - loss: 4.8112 - mae: 4.8112
Epoch 17/200
2/2 [==============================] - 0s 7ms/step - loss: 4.5546 - mae: 4.5546
Epoch 18/200
2/2 [==============================] - 0s 4ms/step - loss: 4.6694 - mae: 4.6694
Epoch 19/200
2/2 [==============================] - 0s 6ms/step - loss: 4.9823 - mae: 4.9823
Epoch 20/200
2/2 [==============================] - 0s 6ms/step - loss: 3.9814 - mae: 3.9814
Epoch 21/200
2/2 [==============================] - 0s 9ms/step - loss: 4.2304 - mae: 4.2304
Epoch 22/200
2/2 [==============================] - 0s 9ms/step - loss: 4.3159 - mae: 4.3159
Epoch 23/200
2/2 [==============================] - 0s 9ms/step - loss: 3.8669 - mae: 3.8669
Epoch 24/200
2/2 [==============================] - 0s 9ms/step - loss: 4.7890 - mae: 4.7890
Epoch 25/200
2/2 [==============================] - 0s 10ms/step - loss: 3.7393 - mae: 3.7393
Epoch 26/200
2/2 [==============================] - 0s 9ms/step - loss: 3.3427 - mae: 3.3427
Epoch 27/200
2/2 [==============================] - 0s 6ms/step - loss: 3.7530 - mae: 3.7530
Epoch 28/200
2/2 [==============================] - 0s 10ms/step - loss: 3.4674 - mae: 3.4674
Epoch 29/200
2/2 [==============================] - 0s 6ms/step - loss: 3.2236 - mae: 3.2236
Epoch 30/200
2/2 [==============================] - 0s 4ms/step - loss: 3.0503 - mae: 3.0503
Epoch 31/200
2/2 [==============================] - 0s 4ms/step - loss: 3.1492 - mae: 3.1492
Epoch 32/200
2/2 [==============================] - 0s 5ms/step - loss: 3.0918 - mae: 3.0918
Epoch 33/200
2/2 [==============================] - 0s 7ms/step - loss: 4.2897 - mae: 4.2897
Epoch 34/200
2/2 [==============================] - 0s 4ms/step - loss: 5.1382 - mae: 5.1382
Epoch 35/200
2/2 [==============================] - 0s 5ms/step - loss: 2.7321 - mae: 2.7321
Epoch 36/200
2/2 [==============================] - 0s 4ms/step - loss: 3.7811 - mae: 3.7811
Epoch 37/200
2/2 [==============================] - 0s 5ms/step - loss: 3.4870 - mae: 3.4870
Epoch 38/200
2/2 [==============================] - 0s 5ms/step - loss: 4.0065 - mae: 4.0065
Epoch 39/200
2/2 [==============================] - 0s 5ms/step - loss: 2.8087 - mae: 2.8087
Epoch 40/200
2/2 [==============================] - 0s 5ms/step - loss: 5.5579 - mae: 5.5579
Epoch 41/200
2/2 [==============================] - 0s 5ms/step - loss: 3.4942 - mae: 3.4942
Epoch 42/200
2/2 [==============================] - 0s 6ms/step - loss: 4.5331 - mae: 4.5331
Epoch 43/200
2/2 [==============================] - 0s 5ms/step - loss: 3.2288 - mae: 3.2288
Epoch 44/200
2/2 [==============================] - 0s 7ms/step - loss: 2.7930 - mae: 2.7930
Epoch 45/200
2/2 [==============================] - 0s 5ms/step - loss: 2.2368 - mae: 2.2368
Epoch 46/200
2/2 [==============================] - 0s 8ms/step - loss: 2.5162 - mae: 2.5162
Epoch 47/200
2/2 [==============================] - 0s 6ms/step - loss: 1.8075 - mae: 1.8075
Epoch 48/200
2/2 [==============================] - 0s 16ms/step - loss: 1.7967 - mae: 1.7967
Epoch 49/200
2/2 [==============================] - 0s 6ms/step - loss: 3.5144 - mae: 3.5144
Epoch 50/200
2/2 [==============================] - 0s 8ms/step - loss: 1.4333 - mae: 1.4333
Epoch 51/200
2/2 [==============================] - 0s 16ms/step - loss: 2.2264 - mae: 2.2264
Epoch 52/200
2/2 [==============================] - 0s 5ms/step - loss: 2.5455 - mae: 2.5455
Epoch 53/200
2/2 [==============================] - 0s 5ms/step - loss: 3.7465 - mae: 3.7465
Epoch 54/200
2/2 [==============================] - 0s 6ms/step - loss: 2.7280 - mae: 2.7280
Epoch 55/200
2/2 [==============================] - 0s 8ms/step - loss: 4.5768 - mae: 4.5768
Epoch 56/200
2/2 [==============================] - 0s 10ms/step - loss: 4.3048 - mae: 4.3048
Epoch 57/200
2/2 [==============================] - 0s 5ms/step - loss: 3.1470 - mae: 3.1470
Epoch 58/200
2/2 [==============================] - 0s 6ms/step - loss: 4.4435 - mae: 4.4435
Epoch 59/200
2/2 [==============================] - 0s 4ms/step - loss: 1.3467 - mae: 1.3467
Epoch 60/200
2/2 [==============================] - 0s 9ms/step - loss: 2.1156 - mae: 2.1156
Epoch 61/200
2/2 [==============================] - 0s 5ms/step - loss: 1.7453 - mae: 1.7453
Epoch 62/200
2/2 [==============================] - 0s 7ms/step - loss: 0.8955 - mae: 0.8955
Epoch 63/200
2/2 [==============================] - 0s 6ms/step - loss: 1.7791 - mae: 1.7791
Epoch 64/200
2/2 [==============================] - 0s 6ms/step - loss: 1.5303 - mae: 1.5303
Epoch 65/200
2/2 [==============================] - 0s 6ms/step - loss: 2.5697 - mae: 2.5697
Epoch 66/200
2/2 [==============================] - 0s 7ms/step - loss: 4.5673 - mae: 4.5673
Epoch 67/200
2/2 [==============================] - 0s 9ms/step - loss: 2.4660 - mae: 2.4660
Epoch 68/200
2/2 [==============================] - 0s 5ms/step - loss: 2.2682 - mae: 2.2682
Epoch 69/200
2/2 [==============================] - 0s 5ms/step - loss: 2.6227 - mae: 2.6227
Epoch 70/200
2/2 [==============================] - 0s 4ms/step - loss: 1.8975 - mae: 1.8975
Epoch 71/200
2/2 [==============================] - 0s 7ms/step - loss: 1.3195 - mae: 1.3195
Epoch 72/200
2/2 [==============================] - 0s 6ms/step - loss: 1.1433 - mae: 1.1433
Epoch 73/200
2/2 [==============================] - 0s 14ms/step - loss: 1.5640 - mae: 1.5640
Epoch 74/200
2/2 [==============================] - 0s 5ms/step - loss: 0.9789 - mae: 0.9789
Epoch 75/200
2/2 [==============================] - 0s 5ms/step - loss: 1.0397 - mae: 1.0397
Epoch 76/200
2/2 [==============================] - 0s 8ms/step - loss: 1.5036 - mae: 1.5036
Epoch 77/200
2/2 [==============================] - 0s 10ms/step - loss: 1.7913 - mae: 1.7913
Epoch 78/200
2/2 [==============================] - 0s 5ms/step - loss: 1.0374 - mae: 1.0374
Epoch 79/200
2/2 [==============================] - 0s 7ms/step - loss: 2.5242 - mae: 2.5242
Epoch 80/200
2/2 [==============================] - 0s 5ms/step - loss: 1.0206 - mae: 1.0206
Epoch 81/200
2/2 [==============================] - 0s 10ms/step - loss: 0.9791 - mae: 0.9791
Epoch 82/200
2/2 [==============================] - 0s 5ms/step - loss: 1.5257 - mae: 1.5257
Epoch 83/200
2/2 [==============================] - 0s 5ms/step - loss: 0.4607 - mae: 0.4607
Epoch 84/200
2/2 [==============================] - 0s 6ms/step - loss: 0.5927 - mae: 0.5927
Epoch 85/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7238 - mae: 0.7238
Epoch 86/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7476 - mae: 0.7476
Epoch 87/200
2/2 [==============================] - 0s 12ms/step - loss: 0.6609 - mae: 0.6609
Epoch 88/200
2/2 [==============================] - 0s 6ms/step - loss: 0.3275 - mae: 0.3275
Epoch 89/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3446 - mae: 1.3446
Epoch 90/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7690 - mae: 0.7690
Epoch 91/200
2/2 [==============================] - 0s 5ms/step - loss: 2.8775 - mae: 2.8775
Epoch 92/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7588 - mae: 0.7588
Epoch 93/200
2/2 [==============================] - 0s 6ms/step - loss: 5.1250 - mae: 5.1250
Epoch 94/200
2/2 [==============================] - 0s 8ms/step - loss: 3.9512 - mae: 3.9512
Epoch 95/200
2/2 [==============================] - 0s 9ms/step - loss: 2.1860 - mae: 2.1860
Epoch 96/200
2/2 [==============================] - 0s 5ms/step - loss: 3.5597 - mae: 3.5597
Epoch 97/200
2/2 [==============================] - 0s 13ms/step - loss: 1.3250 - mae: 1.3250
Epoch 98/200
2/2 [==============================] - 0s 5ms/step - loss: 4.0799 - mae: 4.0799
Epoch 99/200
2/2 [==============================] - 0s 7ms/step - loss: 3.0083 - mae: 3.0083
Epoch 100/200
2/2 [==============================] - 0s 13ms/step - loss: 2.4633 - mae: 2.4633
Epoch 101/200
2/2 [==============================] - 0s 11ms/step - loss: 3.7092 - mae: 3.7092
Epoch 102/200
2/2 [==============================] - 0s 4ms/step - loss: 1.7028 - mae: 1.7028
Epoch 103/200
2/2 [==============================] - 0s 10ms/step - loss: 3.7462 - mae: 3.7462
Epoch 104/200
2/2 [==============================] - 0s 4ms/step - loss: 3.5765 - mae: 3.5765
Epoch 105/200
2/2 [==============================] - 0s 9ms/step - loss: 0.6709 - mae: 0.6709
Epoch 106/200
2/2 [==============================] - 0s 5ms/step - loss: 2.5038 - mae: 2.5038
Epoch 107/200
2/2 [==============================] - 0s 10ms/step - loss: 1.0662 - mae: 1.0662
Epoch 108/200
2/2 [==============================] - 0s 7ms/step - loss: 3.2977 - mae: 3.2977
Epoch 109/200
2/2 [==============================] - 0s 11ms/step - loss: 1.7277 - mae: 1.7277
Epoch 110/200
2/2 [==============================] - 0s 8ms/step - loss: 1.7222 - mae: 1.7222
Epoch 111/200
2/2 [==============================] - 0s 4ms/step - loss: 2.4556 - mae: 2.4556
Epoch 112/200
2/2 [==============================] - 0s 4ms/step - loss: 1.2323 - mae: 1.2323
Epoch 113/200
2/2 [==============================] - 0s 3ms/step - loss: 2.3107 - mae: 2.3107
Epoch 114/200
2/2 [==============================] - 0s 5ms/step - loss: 1.1657 - mae: 1.1657
Epoch 115/200
2/2 [==============================] - 0s 6ms/step - loss: 0.5163 - mae: 0.5163
Epoch 116/200
2/2 [==============================] - 0s 11ms/step - loss: 0.9971 - mae: 0.9971
Epoch 117/200
2/2 [==============================] - 0s 4ms/step - loss: 0.5883 - mae: 0.5883
Epoch 118/200
2/2 [==============================] - 0s 4ms/step - loss: 1.3641 - mae: 1.3641
Epoch 119/200
2/2 [==============================] - 0s 6ms/step - loss: 1.2354 - mae: 1.2354
Epoch 120/200
2/2 [==============================] - 0s 8ms/step - loss: 2.1195 - mae: 2.1195
Epoch 121/200
2/2 [==============================] - 0s 8ms/step - loss: 1.5836 - mae: 1.5836
Epoch 122/200
2/2 [==============================] - 0s 4ms/step - loss: 1.6398 - mae: 1.6398
Epoch 123/200
2/2 [==============================] - 0s 4ms/step - loss: 1.2508 - mae: 1.2508
Epoch 124/200
2/2 [==============================] - 0s 5ms/step - loss: 1.4922 - mae: 1.4922
Epoch 125/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3658 - mae: 1.3658
Epoch 126/200
2/2 [==============================] - 0s 9ms/step - loss: 1.2253 - mae: 1.2253
Epoch 127/200
2/2 [==============================] - 0s 5ms/step - loss: 1.1196 - mae: 1.1196
Epoch 128/200
2/2 [==============================] - 0s 5ms/step - loss: 0.9335 - mae: 0.9335
Epoch 129/200
2/2 [==============================] - 0s 4ms/step - loss: 0.8113 - mae: 0.8113
Epoch 130/200
2/2 [==============================] - 0s 10ms/step - loss: 1.0733 - mae: 1.0733
Epoch 131/200
2/2 [==============================] - 0s 4ms/step - loss: 1.8052 - mae: 1.8052
Epoch 132/200
2/2 [==============================] - 0s 4ms/step - loss: 2.5612 - mae: 2.5612
Epoch 133/200
2/2 [==============================] - 0s 4ms/step - loss: 1.4219 - mae: 1.4219
Epoch 134/200
2/2 [==============================] - 0s 7ms/step - loss: 1.4680 - mae: 1.4680
Epoch 135/200
2/2 [==============================] - 0s 5ms/step - loss: 1.8870 - mae: 1.8870
Epoch 136/200
2/2 [==============================] - 0s 4ms/step - loss: 2.2592 - mae: 2.2592
Epoch 137/200
2/2 [==============================] - 0s 7ms/step - loss: 1.9956 - mae: 1.9956
Epoch 138/200
2/2 [==============================] - 0s 5ms/step - loss: 3.0650 - mae: 3.0650
Epoch 139/200
2/2 [==============================] - 0s 6ms/step - loss: 1.0014 - mae: 1.0014
Epoch 140/200
2/2 [==============================] - 0s 9ms/step - loss: 3.2610 - mae: 3.2610
Epoch 141/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6062 - mae: 1.6062
Epoch 142/200
2/2 [==============================] - 0s 7ms/step - loss: 1.2257 - mae: 1.2257
Epoch 143/200
2/2 [==============================] - 0s 18ms/step - loss: 0.8448 - mae: 0.8448
Epoch 144/200
2/2 [==============================] - 0s 8ms/step - loss: 1.0984 - mae: 1.0984
Epoch 145/200
2/2 [==============================] - 0s 13ms/step - loss: 2.4422 - mae: 2.4422
Epoch 146/200
2/2 [==============================] - 0s 7ms/step - loss: 2.6819 - mae: 2.6819
Epoch 147/200
2/2 [==============================] - 0s 5ms/step - loss: 2.7767 - mae: 2.7767
Epoch 148/200
2/2 [==============================] - 0s 3ms/step - loss: 1.4457 - mae: 1.4457
Epoch 149/200
2/2 [==============================] - 0s 14ms/step - loss: 2.2885 - mae: 2.2885
Epoch 150/200
2/2 [==============================] - 0s 6ms/step - loss: 2.1808 - mae: 2.1808
Epoch 151/200
2/2 [==============================] - 0s 5ms/step - loss: 1.7162 - mae: 1.7162
Epoch 152/200
2/2 [==============================] - 0s 5ms/step - loss: 2.5100 - mae: 2.5100
Epoch 153/200
2/2 [==============================] - 0s 11ms/step - loss: 3.0009 - mae: 3.0009
Epoch 154/200
2/2 [==============================] - 0s 4ms/step - loss: 1.3393 - mae: 1.3393
Epoch 155/200
2/2 [==============================] - 0s 5ms/step - loss: 1.4204 - mae: 1.4204
Epoch 156/200
2/2 [==============================] - 0s 9ms/step - loss: 0.8329 - mae: 0.8329
Epoch 157/200
2/2 [==============================] - 0s 8ms/step - loss: 0.8151 - mae: 0.8151
Epoch 158/200
2/2 [==============================] - 0s 6ms/step - loss: 0.4740 - mae: 0.4740
Epoch 159/200
2/2 [==============================] - 0s 6ms/step - loss: 0.5993 - mae: 0.5993
Epoch 160/200
2/2 [==============================] - 0s 7ms/step - loss: 0.8892 - mae: 0.8892
Epoch 161/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3737 - mae: 1.3737
Epoch 162/200
2/2 [==============================] - 0s 6ms/step - loss: 1.3816 - mae: 1.3816
Epoch 163/200
2/2 [==============================] - 0s 12ms/step - loss: 0.4873 - mae: 0.4873
Epoch 164/200
2/2 [==============================] - 0s 10ms/step - loss: 2.6898 - mae: 2.6898
Epoch 165/200
2/2 [==============================] - 0s 9ms/step - loss: 2.1343 - mae: 2.1343
Epoch 166/200
2/2 [==============================] - 0s 8ms/step - loss: 2.5751 - mae: 2.5751
Epoch 167/200
2/2 [==============================] - 0s 11ms/step - loss: 3.2341 - mae: 3.2341
Epoch 168/200
2/2 [==============================] - 0s 4ms/step - loss: 1.3389 - mae: 1.3389
Epoch 169/200
2/2 [==============================] - 0s 5ms/step - loss: 3.1156 - mae: 3.1156
Epoch 170/200
2/2 [==============================] - 0s 5ms/step - loss: 3.9627 - mae: 3.9627
Epoch 171/200
2/2 [==============================] - 0s 7ms/step - loss: 2.9557 - mae: 2.9557
Epoch 172/200
2/2 [==============================] - 0s 5ms/step - loss: 2.7741 - mae: 2.7741
Epoch 173/200
2/2 [==============================] - 0s 8ms/step - loss: 1.7854 - mae: 1.7854
Epoch 174/200
2/2 [==============================] - 0s 5ms/step - loss: 2.7852 - mae: 2.7852
Epoch 175/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6089 - mae: 1.6089
Epoch 176/200
2/2 [==============================] - 0s 5ms/step - loss: 1.1539 - mae: 1.1539
Epoch 177/200
2/2 [==============================] - 0s 9ms/step - loss: 1.7511 - mae: 1.7511
Epoch 178/200
2/2 [==============================] - 0s 5ms/step - loss: 1.5213 - mae: 1.5213
Epoch 179/200
2/2 [==============================] - 0s 5ms/step - loss: 0.4070 - mae: 0.4070
Epoch 180/200
2/2 [==============================] - 0s 9ms/step - loss: 0.7122 - mae: 0.7122
Epoch 181/200
2/2 [==============================] - 0s 5ms/step - loss: 1.0361 - mae: 1.0361
Epoch 182/200
2/2 [==============================] - 0s 6ms/step - loss: 1.0402 - mae: 1.0402
Epoch 183/200
2/2 [==============================] - 0s 9ms/step - loss: 0.8103 - mae: 0.8103
Epoch 184/200
2/2 [==============================] - 0s 5ms/step - loss: 1.1456 - mae: 1.1456
Epoch 185/200
2/2 [==============================] - 0s 5ms/step - loss: 2.6328 - mae: 2.6328
Epoch 186/200
2/2 [==============================] - 0s 8ms/step - loss: 0.6912 - mae: 0.6912
Epoch 187/200
2/2 [==============================] - 0s 5ms/step - loss: 3.9797 - mae: 3.9797
Epoch 188/200
2/2 [==============================] - 0s 5ms/step - loss: 3.8691 - mae: 3.8691
Epoch 189/200
2/2 [==============================] - 0s 8ms/step - loss: 1.5077 - mae: 1.5077
Epoch 190/200
2/2 [==============================] - 0s 6ms/step - loss: 4.3976 - mae: 4.3976
Epoch 191/200
2/2 [==============================] - 0s 6ms/step - loss: 3.6373 - mae: 3.6373
Epoch 192/200
2/2 [==============================] - 0s 5ms/step - loss: 2.1293 - mae: 2.1293
Epoch 193/200
2/2 [==============================] - 0s 8ms/step - loss: 3.2316 - mae: 3.2316
Epoch 194/200
2/2 [==============================] - 0s 7ms/step - loss: 1.7595 - mae: 1.7595
Epoch 195/200
2/2 [==============================] - 0s 5ms/step - loss: 1.8424 - mae: 1.8424
Epoch 196/200
2/2 [==============================] - 0s 6ms/step - loss: 1.7401 - mae: 1.7401
Epoch 197/200
2/2 [==============================] - 0s 5ms/step - loss: 1.1691 - mae: 1.1691
Epoch 198/200
2/2 [==============================] - 0s 7ms/step - loss: 1.0087 - mae: 1.0087
Epoch 199/200
2/2 [==============================] - 0s 7ms/step - loss: 1.4872 - mae: 1.4872
Epoch 200/200
2/2 [==============================] - 0s 6ms/step - loss: 0.9445 - mae: 0.9445

Out[32]:

<tensorflow.python.keras.callbacks.History at 0x7f8c5d8365d0>

In [33]:

model_1.summary()

model_1.summary()

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_9 (Dense)              (None, 100)               200       
_________________________________________________________________
dense_10 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_11 (Dense)             (None, 1)                 101       
=================================================================
Total params: 10,401
Trainable params: 10,401
Non-trainable params: 0
_________________________________________________________________

MODEL 2¶

In [34]:

# 1. Creating a model
model_2 = tf.keras.Sequential([
  tf.keras.layers.Dense(100, activation="relu"),
  tf.keras.layers.Dense(50, activation="relu"),
  tf.keras.layers.Dense(1)
])

#2. COmppiling the model
model_2.compile(loss=tf.keras.losses.mae,
                optimizer=tf.keras.optimizers.Adam(lr=0.01),
                metrics=["mae"])

#3. Fitting the model
model_2.fit(X_train, y_train, epochs=210)

# 1. Creating a model model_2 = tf.keras.Sequential([ tf.keras.layers.Dense(100, activation="relu"), tf.keras.layers.Dense(50, activation="relu"), tf.keras.layers.Dense(1) ]) #2. COmppiling the model model_2.compile(loss=tf.keras.losses.mae, optimizer=tf.keras.optimizers.Adam(lr=0.01), metrics=["mae"]) #3. Fitting the model model_2.fit(X_train, y_train, epochs=210)

Epoch 1/210

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:375: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  "The `lr` argument is deprecated, use `learning_rate` instead.")

2/2 [==============================] - 0s 8ms/step - loss: 40.9351 - mae: 40.9351
Epoch 2/210
2/2 [==============================] - 0s 6ms/step - loss: 19.7538 - mae: 19.7538
Epoch 3/210
2/2 [==============================] - 0s 5ms/step - loss: 6.8715 - mae: 6.8715
Epoch 4/210
2/2 [==============================] - 0s 3ms/step - loss: 11.5456 - mae: 11.5456
Epoch 5/210
2/2 [==============================] - 0s 7ms/step - loss: 7.8229 - mae: 7.8229
Epoch 6/210
2/2 [==============================] - 0s 7ms/step - loss: 8.5973 - mae: 8.5973
Epoch 7/210
2/2 [==============================] - 0s 7ms/step - loss: 5.6946 - mae: 5.6946
Epoch 8/210
2/2 [==============================] - 0s 9ms/step - loss: 5.0799 - mae: 5.0799
Epoch 9/210
2/2 [==============================] - 0s 4ms/step - loss: 5.5372 - mae: 5.5372
Epoch 10/210
2/2 [==============================] - 0s 4ms/step - loss: 6.2204 - mae: 6.2204
Epoch 11/210
2/2 [==============================] - 0s 5ms/step - loss: 4.3710 - mae: 4.3710
Epoch 12/210
2/2 [==============================] - 0s 4ms/step - loss: 4.5278 - mae: 4.5278
Epoch 13/210
2/2 [==============================] - 0s 6ms/step - loss: 4.8974 - mae: 4.8974
Epoch 14/210
2/2 [==============================] - 0s 6ms/step - loss: 5.8988 - mae: 5.8988
Epoch 15/210
2/2 [==============================] - 0s 5ms/step - loss: 5.0977 - mae: 5.0977
Epoch 16/210
2/2 [==============================] - 0s 10ms/step - loss: 5.0082 - mae: 5.0082
Epoch 17/210
2/2 [==============================] - 0s 8ms/step - loss: 5.9184 - mae: 5.9184
Epoch 18/210
2/2 [==============================] - 0s 9ms/step - loss: 3.7560 - mae: 3.7560
Epoch 19/210
2/2 [==============================] - 0s 10ms/step - loss: 5.0354 - mae: 5.0354
Epoch 20/210
2/2 [==============================] - 0s 6ms/step - loss: 5.3906 - mae: 5.3906
Epoch 21/210
2/2 [==============================] - 0s 5ms/step - loss: 4.3119 - mae: 4.3119
Epoch 22/210
2/2 [==============================] - 0s 7ms/step - loss: 4.0914 - mae: 4.0914
Epoch 23/210
2/2 [==============================] - 0s 7ms/step - loss: 3.5067 - mae: 3.5067
Epoch 24/210
2/2 [==============================] - 0s 7ms/step - loss: 3.7444 - mae: 3.7444
Epoch 25/210
2/2 [==============================] - 0s 4ms/step - loss: 3.4558 - mae: 3.4558
Epoch 26/210
2/2 [==============================] - 0s 6ms/step - loss: 3.3452 - mae: 3.3452
Epoch 27/210
2/2 [==============================] - 0s 5ms/step - loss: 3.3669 - mae: 3.3669
Epoch 28/210
2/2 [==============================] - 0s 6ms/step - loss: 3.1544 - mae: 3.1544
Epoch 29/210
2/2 [==============================] - 0s 7ms/step - loss: 3.3645 - mae: 3.3645
Epoch 30/210
2/2 [==============================] - 0s 4ms/step - loss: 3.0552 - mae: 3.0552
Epoch 31/210
2/2 [==============================] - 0s 10ms/step - loss: 3.4643 - mae: 3.4643
Epoch 32/210
2/2 [==============================] - 0s 8ms/step - loss: 3.1348 - mae: 3.1348
Epoch 33/210
2/2 [==============================] - 0s 5ms/step - loss: 3.0246 - mae: 3.0246
Epoch 34/210
2/2 [==============================] - 0s 18ms/step - loss: 2.8322 - mae: 2.8322
Epoch 35/210
2/2 [==============================] - 0s 6ms/step - loss: 3.2354 - mae: 3.2354
Epoch 36/210
2/2 [==============================] - 0s 10ms/step - loss: 2.7716 - mae: 2.7716
Epoch 37/210
2/2 [==============================] - 0s 6ms/step - loss: 4.3061 - mae: 4.3061
Epoch 38/210
2/2 [==============================] - 0s 12ms/step - loss: 2.9324 - mae: 2.9324
Epoch 39/210
2/2 [==============================] - 0s 8ms/step - loss: 3.2347 - mae: 3.2347
Epoch 40/210
2/2 [==============================] - 0s 5ms/step - loss: 2.3673 - mae: 2.3673
Epoch 41/210
2/2 [==============================] - 0s 5ms/step - loss: 2.4462 - mae: 2.4462
Epoch 42/210
2/2 [==============================] - 0s 9ms/step - loss: 2.9135 - mae: 2.9135
Epoch 43/210
2/2 [==============================] - 0s 9ms/step - loss: 2.4955 - mae: 2.4955
Epoch 44/210
2/2 [==============================] - 0s 7ms/step - loss: 2.3365 - mae: 2.3365
Epoch 45/210
2/2 [==============================] - 0s 5ms/step - loss: 2.8339 - mae: 2.8339
Epoch 46/210
2/2 [==============================] - 0s 9ms/step - loss: 1.7937 - mae: 1.7937
Epoch 47/210
2/2 [==============================] - 0s 7ms/step - loss: 3.0757 - mae: 3.0757
Epoch 48/210
2/2 [==============================] - 0s 6ms/step - loss: 1.7305 - mae: 1.7305
Epoch 49/210
2/2 [==============================] - 0s 10ms/step - loss: 3.1400 - mae: 3.1400
Epoch 50/210
2/2 [==============================] - 0s 5ms/step - loss: 2.4909 - mae: 2.4909
Epoch 51/210
2/2 [==============================] - 0s 9ms/step - loss: 2.0234 - mae: 2.0234
Epoch 52/210
2/2 [==============================] - 0s 10ms/step - loss: 3.2417 - mae: 3.2417
Epoch 53/210
2/2 [==============================] - 0s 4ms/step - loss: 2.2664 - mae: 2.2664
Epoch 54/210
2/2 [==============================] - 0s 10ms/step - loss: 1.7532 - mae: 1.7532
Epoch 55/210
2/2 [==============================] - 0s 7ms/step - loss: 1.4831 - mae: 1.4831
Epoch 56/210
2/2 [==============================] - 0s 10ms/step - loss: 1.0309 - mae: 1.0309
Epoch 57/210
2/2 [==============================] - 0s 8ms/step - loss: 0.7118 - mae: 0.7118
Epoch 58/210
2/2 [==============================] - 0s 7ms/step - loss: 0.8425 - mae: 0.8425
Epoch 59/210
2/2 [==============================] - 0s 11ms/step - loss: 1.7186 - mae: 1.7186
Epoch 60/210
2/2 [==============================] - 0s 7ms/step - loss: 1.1274 - mae: 1.1274
Epoch 61/210
2/2 [==============================] - 0s 4ms/step - loss: 2.4831 - mae: 2.4831
Epoch 62/210
2/2 [==============================] - 0s 6ms/step - loss: 2.6176 - mae: 2.6176
Epoch 63/210
2/2 [==============================] - 0s 7ms/step - loss: 2.8625 - mae: 2.8625
Epoch 64/210
2/2 [==============================] - 0s 7ms/step - loss: 2.0290 - mae: 2.0290
Epoch 65/210
2/2 [==============================] - 0s 7ms/step - loss: 2.8852 - mae: 2.8852
Epoch 66/210
2/2 [==============================] - 0s 5ms/step - loss: 1.4067 - mae: 1.4067
Epoch 67/210
2/2 [==============================] - 0s 6ms/step - loss: 1.4066 - mae: 1.4066
Epoch 68/210
2/2 [==============================] - 0s 5ms/step - loss: 1.6937 - mae: 1.6937
Epoch 69/210
2/2 [==============================] - 0s 5ms/step - loss: 0.9554 - mae: 0.9554
Epoch 70/210
2/2 [==============================] - 0s 4ms/step - loss: 0.9344 - mae: 0.9344
Epoch 71/210
2/2 [==============================] - 0s 5ms/step - loss: 2.4489 - mae: 2.4489
Epoch 72/210
2/2 [==============================] - 0s 6ms/step - loss: 1.7987 - mae: 1.7987
Epoch 73/210
2/2 [==============================] - 0s 9ms/step - loss: 4.2098 - mae: 4.2098
Epoch 74/210
2/2 [==============================] - 0s 6ms/step - loss: 2.7456 - mae: 2.7456
Epoch 75/210
2/2 [==============================] - 0s 6ms/step - loss: 3.7931 - mae: 3.7931
Epoch 76/210
2/2 [==============================] - 0s 4ms/step - loss: 5.4268 - mae: 5.4268
Epoch 77/210
2/2 [==============================] - 0s 4ms/step - loss: 3.4310 - mae: 3.4310
Epoch 78/210
2/2 [==============================] - 0s 4ms/step - loss: 2.4441 - mae: 2.4441
Epoch 79/210
2/2 [==============================] - 0s 5ms/step - loss: 3.6209 - mae: 3.6209
Epoch 80/210
2/2 [==============================] - 0s 6ms/step - loss: 0.5217 - mae: 0.5217
Epoch 81/210
2/2 [==============================] - 0s 7ms/step - loss: 1.9092 - mae: 1.9092
Epoch 82/210
2/2 [==============================] - 0s 6ms/step - loss: 0.8684 - mae: 0.8684
Epoch 83/210
2/2 [==============================] - 0s 7ms/step - loss: 0.8802 - mae: 0.8802
Epoch 84/210
2/2 [==============================] - 0s 5ms/step - loss: 1.7133 - mae: 1.7133
Epoch 85/210
2/2 [==============================] - 0s 5ms/step - loss: 0.8196 - mae: 0.8196
Epoch 86/210
2/2 [==============================] - 0s 10ms/step - loss: 1.8599 - mae: 1.8599
Epoch 87/210
2/2 [==============================] - 0s 4ms/step - loss: 0.9053 - mae: 0.9053
Epoch 88/210
2/2 [==============================] - 0s 13ms/step - loss: 0.9107 - mae: 0.9107
Epoch 89/210
2/2 [==============================] - 0s 7ms/step - loss: 1.2858 - mae: 1.2858
Epoch 90/210
2/2 [==============================] - 0s 7ms/step - loss: 0.5374 - mae: 0.5374
Epoch 91/210
2/2 [==============================] - 0s 5ms/step - loss: 0.9030 - mae: 0.9030
Epoch 92/210
2/2 [==============================] - 0s 6ms/step - loss: 1.7772 - mae: 1.7772
Epoch 93/210
2/2 [==============================] - 0s 6ms/step - loss: 1.8618 - mae: 1.8618
Epoch 94/210
2/2 [==============================] - 0s 4ms/step - loss: 2.0607 - mae: 2.0607
Epoch 95/210
2/2 [==============================] - 0s 5ms/step - loss: 2.8777 - mae: 2.8777
Epoch 96/210
2/2 [==============================] - 0s 4ms/step - loss: 0.7386 - mae: 0.7386
Epoch 97/210
2/2 [==============================] - 0s 4ms/step - loss: 2.8049 - mae: 2.8049
Epoch 98/210
2/2 [==============================] - 0s 6ms/step - loss: 1.1087 - mae: 1.1087
Epoch 99/210
2/2 [==============================] - 0s 6ms/step - loss: 2.6545 - mae: 2.6545
Epoch 100/210
2/2 [==============================] - 0s 8ms/step - loss: 1.4348 - mae: 1.4348
Epoch 101/210
2/2 [==============================] - 0s 7ms/step - loss: 2.3339 - mae: 2.3339
Epoch 102/210
2/2 [==============================] - 0s 11ms/step - loss: 1.9062 - mae: 1.9062
Epoch 103/210
2/2 [==============================] - 0s 5ms/step - loss: 2.2477 - mae: 2.2477
Epoch 104/210
2/2 [==============================] - 0s 4ms/step - loss: 1.4148 - mae: 1.4148
Epoch 105/210
2/2 [==============================] - 0s 6ms/step - loss: 2.0923 - mae: 2.0923
Epoch 106/210
2/2 [==============================] - 0s 8ms/step - loss: 2.3238 - mae: 2.3238
Epoch 107/210
2/2 [==============================] - 0s 7ms/step - loss: 1.9052 - mae: 1.9052
Epoch 108/210
2/2 [==============================] - 0s 9ms/step - loss: 2.7566 - mae: 2.7566
Epoch 109/210
2/2 [==============================] - 0s 5ms/step - loss: 2.7271 - mae: 2.7271
Epoch 110/210
2/2 [==============================] - 0s 6ms/step - loss: 1.9361 - mae: 1.9361
Epoch 111/210
2/2 [==============================] - 0s 6ms/step - loss: 0.5295 - mae: 0.5295
Epoch 112/210
2/2 [==============================] - 0s 7ms/step - loss: 2.4236 - mae: 2.4236
Epoch 113/210
2/2 [==============================] - 0s 4ms/step - loss: 2.7980 - mae: 2.7980
Epoch 114/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7440 - mae: 0.7440
Epoch 115/210
2/2 [==============================] - 0s 6ms/step - loss: 0.6299 - mae: 0.6299
Epoch 116/210
2/2 [==============================] - 0s 7ms/step - loss: 0.7008 - mae: 0.7008
Epoch 117/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7745 - mae: 0.7745
Epoch 118/210
2/2 [==============================] - 0s 4ms/step - loss: 0.4657 - mae: 0.4657
Epoch 119/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7751 - mae: 0.7751
Epoch 120/210
2/2 [==============================] - 0s 10ms/step - loss: 0.6514 - mae: 0.6514
Epoch 121/210
2/2 [==============================] - 0s 11ms/step - loss: 1.1230 - mae: 1.1230
Epoch 122/210
2/2 [==============================] - 0s 9ms/step - loss: 0.9754 - mae: 0.9754
Epoch 123/210
2/2 [==============================] - 0s 9ms/step - loss: 0.9105 - mae: 0.9105
Epoch 124/210
2/2 [==============================] - 0s 13ms/step - loss: 0.5790 - mae: 0.5790
Epoch 125/210
2/2 [==============================] - 0s 6ms/step - loss: 1.0840 - mae: 1.0840
Epoch 126/210
2/2 [==============================] - 0s 7ms/step - loss: 0.8570 - mae: 0.8570
Epoch 127/210
2/2 [==============================] - 0s 7ms/step - loss: 0.8023 - mae: 0.8023
Epoch 128/210
2/2 [==============================] - 0s 9ms/step - loss: 0.8632 - mae: 0.8632
Epoch 129/210
2/2 [==============================] - 0s 8ms/step - loss: 1.0138 - mae: 1.0138
Epoch 130/210
2/2 [==============================] - 0s 5ms/step - loss: 2.5399 - mae: 2.5399
Epoch 131/210
2/2 [==============================] - 0s 7ms/step - loss: 1.7454 - mae: 1.7454
Epoch 132/210
2/2 [==============================] - 0s 8ms/step - loss: 0.8864 - mae: 0.8864
Epoch 133/210
2/2 [==============================] - 0s 6ms/step - loss: 2.3999 - mae: 2.3999
Epoch 134/210
2/2 [==============================] - 0s 3ms/step - loss: 1.9659 - mae: 1.9659
Epoch 135/210
2/2 [==============================] - 0s 6ms/step - loss: 2.0174 - mae: 2.0174
Epoch 136/210
2/2 [==============================] - 0s 8ms/step - loss: 2.4927 - mae: 2.4927
Epoch 137/210
2/2 [==============================] - 0s 7ms/step - loss: 0.6498 - mae: 0.6498
Epoch 138/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7374 - mae: 0.7374
Epoch 139/210
2/2 [==============================] - 0s 9ms/step - loss: 0.4689 - mae: 0.4689
Epoch 140/210
2/2 [==============================] - 0s 5ms/step - loss: 0.9127 - mae: 0.9127
Epoch 141/210
2/2 [==============================] - 0s 5ms/step - loss: 0.8833 - mae: 0.8833
Epoch 142/210
2/2 [==============================] - 0s 5ms/step - loss: 0.5901 - mae: 0.5901
Epoch 143/210
2/2 [==============================] - 0s 6ms/step - loss: 1.1828 - mae: 1.1828
Epoch 144/210
2/2 [==============================] - 0s 5ms/step - loss: 1.2800 - mae: 1.2800
Epoch 145/210
2/2 [==============================] - 0s 4ms/step - loss: 1.3633 - mae: 1.3633
Epoch 146/210
2/2 [==============================] - 0s 5ms/step - loss: 2.4257 - mae: 2.4257
Epoch 147/210
2/2 [==============================] - 0s 9ms/step - loss: 0.8584 - mae: 0.8584
Epoch 148/210
2/2 [==============================] - 0s 4ms/step - loss: 3.0708 - mae: 3.0708
Epoch 149/210
2/2 [==============================] - 0s 5ms/step - loss: 2.1043 - mae: 2.1043
Epoch 150/210
2/2 [==============================] - 0s 4ms/step - loss: 1.5102 - mae: 1.5102
Epoch 151/210
2/2 [==============================] - 0s 5ms/step - loss: 1.8070 - mae: 1.8070
Epoch 152/210
2/2 [==============================] - 0s 4ms/step - loss: 1.4216 - mae: 1.4216
Epoch 153/210
2/2 [==============================] - 0s 5ms/step - loss: 1.9647 - mae: 1.9647
Epoch 154/210
2/2 [==============================] - 0s 15ms/step - loss: 1.9341 - mae: 1.9341
Epoch 155/210
2/2 [==============================] - 0s 7ms/step - loss: 1.6531 - mae: 1.6531
Epoch 156/210
2/2 [==============================] - 0s 7ms/step - loss: 1.8322 - mae: 1.8322
Epoch 157/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7070 - mae: 0.7070
Epoch 158/210
2/2 [==============================] - 0s 8ms/step - loss: 1.2598 - mae: 1.2598
Epoch 159/210
2/2 [==============================] - 0s 6ms/step - loss: 1.1934 - mae: 1.1934
Epoch 160/210
2/2 [==============================] - 0s 14ms/step - loss: 1.8699 - mae: 1.8699
Epoch 161/210
2/2 [==============================] - 0s 5ms/step - loss: 2.0104 - mae: 2.0104
Epoch 162/210
2/2 [==============================] - 0s 8ms/step - loss: 2.2555 - mae: 2.2555
Epoch 163/210
2/2 [==============================] - 0s 7ms/step - loss: 1.6957 - mae: 1.6957
Epoch 164/210
2/2 [==============================] - 0s 11ms/step - loss: 2.0672 - mae: 2.0672
Epoch 165/210
2/2 [==============================] - 0s 17ms/step - loss: 0.8550 - mae: 0.8550
Epoch 166/210
2/2 [==============================] - 0s 9ms/step - loss: 1.9163 - mae: 1.9163
Epoch 167/210
2/2 [==============================] - 0s 8ms/step - loss: 0.8698 - mae: 0.8698
Epoch 168/210
2/2 [==============================] - 0s 4ms/step - loss: 1.9434 - mae: 1.9434
Epoch 169/210
2/2 [==============================] - 0s 9ms/step - loss: 0.9729 - mae: 0.9729
Epoch 170/210
2/2 [==============================] - 0s 7ms/step - loss: 0.7842 - mae: 0.7842
Epoch 171/210
2/2 [==============================] - 0s 6ms/step - loss: 0.8120 - mae: 0.8120
Epoch 172/210
2/2 [==============================] - 0s 6ms/step - loss: 1.1547 - mae: 1.1547
Epoch 173/210
2/2 [==============================] - 0s 6ms/step - loss: 0.7852 - mae: 0.7852
Epoch 174/210
2/2 [==============================] - 0s 6ms/step - loss: 0.9087 - mae: 0.9087
Epoch 175/210
2/2 [==============================] - 0s 5ms/step - loss: 0.6243 - mae: 0.6243
Epoch 176/210
2/2 [==============================] - 0s 11ms/step - loss: 0.5617 - mae: 0.5617
Epoch 177/210
2/2 [==============================] - 0s 6ms/step - loss: 0.8467 - mae: 0.8467
Epoch 178/210
2/2 [==============================] - 0s 10ms/step - loss: 0.8652 - mae: 0.8652
Epoch 179/210
2/2 [==============================] - 0s 9ms/step - loss: 0.4983 - mae: 0.4983
Epoch 180/210
2/2 [==============================] - 0s 6ms/step - loss: 1.2310 - mae: 1.2310
Epoch 181/210
2/2 [==============================] - 0s 8ms/step - loss: 0.5272 - mae: 0.5272
Epoch 182/210
2/2 [==============================] - 0s 5ms/step - loss: 0.4467 - mae: 0.4467
Epoch 183/210
2/2 [==============================] - 0s 4ms/step - loss: 1.8793 - mae: 1.8793
Epoch 184/210
2/2 [==============================] - 0s 6ms/step - loss: 0.8299 - mae: 0.8299
Epoch 185/210
2/2 [==============================] - 0s 4ms/step - loss: 1.2196 - mae: 1.2196
Epoch 186/210
2/2 [==============================] - 0s 5ms/step - loss: 0.5875 - mae: 0.5875
Epoch 187/210
2/2 [==============================] - 0s 9ms/step - loss: 0.5685 - mae: 0.5685
Epoch 188/210
2/2 [==============================] - 0s 5ms/step - loss: 0.5309 - mae: 0.5309
Epoch 189/210
2/2 [==============================] - 0s 11ms/step - loss: 0.3358 - mae: 0.3358
Epoch 190/210
2/2 [==============================] - 0s 4ms/step - loss: 0.6681 - mae: 0.6681
Epoch 191/210
2/2 [==============================] - 0s 5ms/step - loss: 1.0028 - mae: 1.0028
Epoch 192/210
2/2 [==============================] - 0s 4ms/step - loss: 0.7211 - mae: 0.7211
Epoch 193/210
2/2 [==============================] - 0s 4ms/step - loss: 0.6490 - mae: 0.6490
Epoch 194/210
2/2 [==============================] - 0s 4ms/step - loss: 1.4121 - mae: 1.4121
Epoch 195/210
2/2 [==============================] - 0s 5ms/step - loss: 1.5574 - mae: 1.5574
Epoch 196/210
2/2 [==============================] - 0s 4ms/step - loss: 1.1966 - mae: 1.1966
Epoch 197/210
2/2 [==============================] - 0s 6ms/step - loss: 1.1823 - mae: 1.1823
Epoch 198/210
2/2 [==============================] - 0s 5ms/step - loss: 0.7966 - mae: 0.7966
Epoch 199/210
2/2 [==============================] - 0s 9ms/step - loss: 0.7818 - mae: 0.7818
Epoch 200/210
2/2 [==============================] - 0s 4ms/step - loss: 1.2106 - mae: 1.2106
Epoch 201/210
2/2 [==============================] - 0s 10ms/step - loss: 0.9856 - mae: 0.9856
Epoch 202/210
2/2 [==============================] - 0s 4ms/step - loss: 0.9638 - mae: 0.9638
Epoch 203/210
2/2 [==============================] - 0s 8ms/step - loss: 0.8076 - mae: 0.8076
Epoch 204/210
2/2 [==============================] - 0s 5ms/step - loss: 1.4806 - mae: 1.4806
Epoch 205/210
2/2 [==============================] - 0s 10ms/step - loss: 0.8523 - mae: 0.8523
Epoch 206/210
2/2 [==============================] - 0s 6ms/step - loss: 2.4696 - mae: 2.4696
Epoch 207/210
2/2 [==============================] - 0s 5ms/step - loss: 1.8450 - mae: 1.8450
Epoch 208/210
2/2 [==============================] - 0s 5ms/step - loss: 1.7544 - mae: 1.7544
Epoch 209/210
2/2 [==============================] - 0s 7ms/step - loss: 2.2677 - mae: 2.2677
Epoch 210/210
2/2 [==============================] - 0s 7ms/step - loss: 0.6536 - mae: 0.6536

Out[34]:

<tensorflow.python.keras.callbacks.History at 0x7f8c5d6bac50>

MODEL 3¶

In [35]:

# 1. Creating a model
model_3 = tf.keras.Sequential([
  tf.keras.layers.Dense(75, activation="relu"),
  tf.keras.layers.Dense(75, activation="relu"),
  tf.keras.layers.Dense(1)
])

#2. COmppiling the model
model_3.compile(loss=tf.keras.losses.mae,
                optimizer=tf.keras.optimizers.Adam(lr=0.01),
                metrics=["mae"])

#3. Fitting the model
model_3.fit(X_train, y_train, epochs=200)

# 1. Creating a model model_3 = tf.keras.Sequential([ tf.keras.layers.Dense(75, activation="relu"), tf.keras.layers.Dense(75, activation="relu"), tf.keras.layers.Dense(1) ]) #2. COmppiling the model model_3.compile(loss=tf.keras.losses.mae, optimizer=tf.keras.optimizers.Adam(lr=0.01), metrics=["mae"]) #3. Fitting the model model_3.fit(X_train, y_train, epochs=200)

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:375: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  "The `lr` argument is deprecated, use `learning_rate` instead.")

Epoch 1/200
2/2 [==============================] - 0s 6ms/step - loss: 41.1289 - mae: 41.1289
Epoch 2/200
2/2 [==============================] - 0s 7ms/step - loss: 19.5215 - mae: 19.5215
Epoch 3/200
2/2 [==============================] - 0s 5ms/step - loss: 7.0380 - mae: 7.0380
Epoch 4/200
2/2 [==============================] - 0s 6ms/step - loss: 12.3443 - mae: 12.3443
Epoch 5/200
2/2 [==============================] - 0s 8ms/step - loss: 8.4949 - mae: 8.4949
Epoch 6/200
2/2 [==============================] - 0s 8ms/step - loss: 6.2283 - mae: 6.2283
Epoch 7/200
2/2 [==============================] - 0s 8ms/step - loss: 9.3871 - mae: 9.3871
Epoch 8/200
2/2 [==============================] - 0s 7ms/step - loss: 7.3160 - mae: 7.3160
Epoch 9/200
2/2 [==============================] - 0s 8ms/step - loss: 4.4906 - mae: 4.4906
Epoch 10/200
2/2 [==============================] - 0s 7ms/step - loss: 6.2689 - mae: 6.2689
Epoch 11/200
2/2 [==============================] - 0s 7ms/step - loss: 4.4471 - mae: 4.4471
Epoch 12/200
2/2 [==============================] - 0s 7ms/step - loss: 5.8056 - mae: 5.8056
Epoch 13/200
2/2 [==============================] - 0s 9ms/step - loss: 6.7199 - mae: 6.7199
Epoch 14/200
2/2 [==============================] - 0s 10ms/step - loss: 5.5459 - mae: 5.5459
Epoch 15/200
2/2 [==============================] - 0s 11ms/step - loss: 4.6035 - mae: 4.6035
Epoch 16/200
2/2 [==============================] - 0s 6ms/step - loss: 4.3060 - mae: 4.3060
Epoch 17/200
2/2 [==============================] - 0s 5ms/step - loss: 5.2975 - mae: 5.2975
Epoch 18/200
2/2 [==============================] - 0s 8ms/step - loss: 6.2361 - mae: 6.2361
Epoch 19/200
2/2 [==============================] - 0s 10ms/step - loss: 5.4398 - mae: 5.4398
Epoch 20/200
2/2 [==============================] - 0s 6ms/step - loss: 4.3869 - mae: 4.3869
Epoch 21/200
2/2 [==============================] - 0s 4ms/step - loss: 3.7468 - mae: 3.7468
Epoch 22/200
2/2 [==============================] - 0s 6ms/step - loss: 3.8847 - mae: 3.8847
Epoch 23/200
2/2 [==============================] - 0s 5ms/step - loss: 3.4379 - mae: 3.4379
Epoch 24/200
2/2 [==============================] - 0s 5ms/step - loss: 3.4881 - mae: 3.4881
Epoch 25/200
2/2 [==============================] - 0s 5ms/step - loss: 3.4063 - mae: 3.4063
Epoch 26/200
2/2 [==============================] - 0s 6ms/step - loss: 3.7933 - mae: 3.7933
Epoch 27/200
2/2 [==============================] - 0s 8ms/step - loss: 3.2673 - mae: 3.2673
Epoch 28/200
2/2 [==============================] - 0s 6ms/step - loss: 3.1937 - mae: 3.1937
Epoch 29/200
2/2 [==============================] - 0s 6ms/step - loss: 3.1845 - mae: 3.1845
Epoch 30/200
2/2 [==============================] - 0s 5ms/step - loss: 3.1045 - mae: 3.1045
Epoch 31/200
2/2 [==============================] - 0s 6ms/step - loss: 3.1574 - mae: 3.1574
Epoch 32/200
2/2 [==============================] - 0s 6ms/step - loss: 2.9285 - mae: 2.9285
Epoch 33/200
2/2 [==============================] - 0s 7ms/step - loss: 2.8956 - mae: 2.8956
Epoch 34/200
2/2 [==============================] - 0s 6ms/step - loss: 2.8111 - mae: 2.8111
Epoch 35/200
2/2 [==============================] - 0s 6ms/step - loss: 2.7699 - mae: 2.7699
Epoch 36/200
2/2 [==============================] - 0s 6ms/step - loss: 2.6578 - mae: 2.6578
Epoch 37/200
2/2 [==============================] - 0s 6ms/step - loss: 2.7879 - mae: 2.7879
Epoch 38/200
2/2 [==============================] - 0s 6ms/step - loss: 2.9494 - mae: 2.9494
Epoch 39/200
2/2 [==============================] - 0s 6ms/step - loss: 2.2748 - mae: 2.2748
Epoch 40/200
2/2 [==============================] - 0s 7ms/step - loss: 3.7555 - mae: 3.7555
Epoch 41/200
2/2 [==============================] - 0s 6ms/step - loss: 2.4248 - mae: 2.4248
Epoch 42/200
2/2 [==============================] - 0s 18ms/step - loss: 3.0332 - mae: 3.0332
Epoch 43/200
2/2 [==============================] - 0s 7ms/step - loss: 2.0923 - mae: 2.0923
Epoch 44/200
2/2 [==============================] - 0s 10ms/step - loss: 1.9709 - mae: 1.9709
Epoch 45/200
2/2 [==============================] - 0s 9ms/step - loss: 1.7119 - mae: 1.7119
Epoch 46/200
2/2 [==============================] - 0s 9ms/step - loss: 1.4175 - mae: 1.4175
Epoch 47/200
2/2 [==============================] - 0s 11ms/step - loss: 1.9366 - mae: 1.9366
Epoch 48/200
2/2 [==============================] - 0s 16ms/step - loss: 1.2003 - mae: 1.2003
Epoch 49/200
2/2 [==============================] - 0s 8ms/step - loss: 1.5288 - mae: 1.5288
Epoch 50/200
2/2 [==============================] - 0s 12ms/step - loss: 1.6784 - mae: 1.6784
Epoch 51/200
2/2 [==============================] - 0s 10ms/step - loss: 2.5784 - mae: 2.5784
Epoch 52/200
2/2 [==============================] - 0s 7ms/step - loss: 2.8497 - mae: 2.8497
Epoch 53/200
2/2 [==============================] - 0s 7ms/step - loss: 2.0333 - mae: 2.0333
Epoch 54/200
2/2 [==============================] - 0s 10ms/step - loss: 2.7066 - mae: 2.7066
Epoch 55/200
2/2 [==============================] - 0s 9ms/step - loss: 1.4759 - mae: 1.4759
Epoch 56/200
2/2 [==============================] - 0s 6ms/step - loss: 1.7415 - mae: 1.7415
Epoch 57/200
2/2 [==============================] - 0s 8ms/step - loss: 1.7518 - mae: 1.7518
Epoch 58/200
2/2 [==============================] - 0s 6ms/step - loss: 1.2377 - mae: 1.2377
Epoch 59/200
2/2 [==============================] - 0s 5ms/step - loss: 1.6128 - mae: 1.6128
Epoch 60/200
2/2 [==============================] - 0s 13ms/step - loss: 2.8634 - mae: 2.8634
Epoch 61/200
2/2 [==============================] - 0s 7ms/step - loss: 1.5915 - mae: 1.5915
Epoch 62/200
2/2 [==============================] - 0s 11ms/step - loss: 1.7314 - mae: 1.7314
Epoch 63/200
2/2 [==============================] - 0s 7ms/step - loss: 1.1843 - mae: 1.1843
Epoch 64/200
2/2 [==============================] - 0s 12ms/step - loss: 2.2412 - mae: 2.2412
Epoch 65/200
2/2 [==============================] - 0s 8ms/step - loss: 2.7530 - mae: 2.7530
Epoch 66/200
2/2 [==============================] - 0s 9ms/step - loss: 2.4460 - mae: 2.4460
Epoch 67/200
2/2 [==============================] - 0s 6ms/step - loss: 2.4389 - mae: 2.4389
Epoch 68/200
2/2 [==============================] - 0s 15ms/step - loss: 0.9443 - mae: 0.9443
Epoch 69/200
2/2 [==============================] - 0s 9ms/step - loss: 2.6949 - mae: 2.6949
Epoch 70/200
2/2 [==============================] - 0s 7ms/step - loss: 1.4199 - mae: 1.4199
Epoch 71/200
2/2 [==============================] - 0s 7ms/step - loss: 1.6733 - mae: 1.6733
Epoch 72/200
2/2 [==============================] - 0s 8ms/step - loss: 1.2866 - mae: 1.2866
Epoch 73/200
2/2 [==============================] - 0s 9ms/step - loss: 1.2760 - mae: 1.2760
Epoch 74/200
2/2 [==============================] - 0s 8ms/step - loss: 1.6047 - mae: 1.6047
Epoch 75/200
2/2 [==============================] - 0s 7ms/step - loss: 0.8391 - mae: 0.8391
Epoch 76/200
2/2 [==============================] - 0s 11ms/step - loss: 0.8350 - mae: 0.8350
Epoch 77/200
2/2 [==============================] - 0s 6ms/step - loss: 0.9546 - mae: 0.9546
Epoch 78/200
2/2 [==============================] - 0s 6ms/step - loss: 1.0579 - mae: 1.0579
Epoch 79/200
2/2 [==============================] - 0s 9ms/step - loss: 0.4193 - mae: 0.4193
Epoch 80/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6906 - mae: 1.6906
Epoch 81/200
2/2 [==============================] - 0s 7ms/step - loss: 1.7759 - mae: 1.7759
Epoch 82/200
2/2 [==============================] - 0s 6ms/step - loss: 1.7221 - mae: 1.7221
Epoch 83/200
2/2 [==============================] - 0s 7ms/step - loss: 2.9398 - mae: 2.9398
Epoch 84/200
2/2 [==============================] - 0s 9ms/step - loss: 2.4558 - mae: 2.4558
Epoch 85/200
2/2 [==============================] - 0s 12ms/step - loss: 2.0620 - mae: 2.0620
Epoch 86/200
2/2 [==============================] - 0s 7ms/step - loss: 2.4766 - mae: 2.4766
Epoch 87/200
2/2 [==============================] - 0s 11ms/step - loss: 0.7302 - mae: 0.7302
Epoch 88/200
2/2 [==============================] - 0s 6ms/step - loss: 1.3501 - mae: 1.3501
Epoch 89/200
2/2 [==============================] - 0s 8ms/step - loss: 1.6824 - mae: 1.6824
Epoch 90/200
2/2 [==============================] - 0s 9ms/step - loss: 0.9305 - mae: 0.9305
Epoch 91/200
2/2 [==============================] - 0s 6ms/step - loss: 2.1000 - mae: 2.1000
Epoch 92/200
2/2 [==============================] - 0s 6ms/step - loss: 2.1390 - mae: 2.1390
Epoch 93/200
2/2 [==============================] - 0s 9ms/step - loss: 2.1296 - mae: 2.1296
Epoch 94/200
2/2 [==============================] - 0s 9ms/step - loss: 1.0818 - mae: 1.0818
Epoch 95/200
2/2 [==============================] - 0s 11ms/step - loss: 0.9694 - mae: 0.9694
Epoch 96/200
2/2 [==============================] - 0s 8ms/step - loss: 2.4078 - mae: 2.4078
Epoch 97/200
2/2 [==============================] - 0s 7ms/step - loss: 1.9811 - mae: 1.9811
Epoch 98/200
2/2 [==============================] - 0s 7ms/step - loss: 2.2951 - mae: 2.2951
Epoch 99/200
2/2 [==============================] - 0s 5ms/step - loss: 2.5898 - mae: 2.5898
Epoch 100/200
2/2 [==============================] - 0s 9ms/step - loss: 1.0213 - mae: 1.0213
Epoch 101/200
2/2 [==============================] - 0s 6ms/step - loss: 1.2439 - mae: 1.2439
Epoch 102/200
2/2 [==============================] - 0s 10ms/step - loss: 1.6630 - mae: 1.6630
Epoch 103/200
2/2 [==============================] - 0s 14ms/step - loss: 1.5021 - mae: 1.5021
Epoch 104/200
2/2 [==============================] - 0s 10ms/step - loss: 2.0826 - mae: 2.0826
Epoch 105/200
2/2 [==============================] - 0s 9ms/step - loss: 1.6183 - mae: 1.6183
Epoch 106/200
2/2 [==============================] - 0s 7ms/step - loss: 2.1318 - mae: 2.1318
Epoch 107/200
2/2 [==============================] - 0s 8ms/step - loss: 1.0657 - mae: 1.0657
Epoch 108/200
2/2 [==============================] - 0s 9ms/step - loss: 1.0688 - mae: 1.0688
Epoch 109/200
2/2 [==============================] - 0s 15ms/step - loss: 1.2223 - mae: 1.2223
Epoch 110/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7085 - mae: 0.7085
Epoch 111/200
2/2 [==============================] - 0s 7ms/step - loss: 0.5997 - mae: 0.5997
Epoch 112/200
2/2 [==============================] - 0s 5ms/step - loss: 0.3767 - mae: 0.3767
Epoch 113/200
2/2 [==============================] - 0s 6ms/step - loss: 0.5839 - mae: 0.5839
Epoch 114/200
2/2 [==============================] - 0s 7ms/step - loss: 0.9787 - mae: 0.9787
Epoch 115/200
2/2 [==============================] - 0s 10ms/step - loss: 1.3361 - mae: 1.3361
Epoch 116/200
2/2 [==============================] - 0s 5ms/step - loss: 0.8628 - mae: 0.8628
Epoch 117/200
2/2 [==============================] - 0s 8ms/step - loss: 3.5464 - mae: 3.5464
Epoch 118/200
2/2 [==============================] - 0s 6ms/step - loss: 3.5992 - mae: 3.5992
Epoch 119/200
2/2 [==============================] - 0s 6ms/step - loss: 1.3739 - mae: 1.3739
Epoch 120/200
2/2 [==============================] - 0s 17ms/step - loss: 1.6595 - mae: 1.6595
Epoch 121/200
2/2 [==============================] - 0s 8ms/step - loss: 1.0235 - mae: 1.0235
Epoch 122/200
2/2 [==============================] - 0s 5ms/step - loss: 1.8700 - mae: 1.8700
Epoch 123/200
2/2 [==============================] - 0s 18ms/step - loss: 2.0862 - mae: 2.0862
Epoch 124/200
2/2 [==============================] - 0s 8ms/step - loss: 1.1830 - mae: 1.1830
Epoch 125/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3957 - mae: 1.3957
Epoch 126/200
2/2 [==============================] - 0s 7ms/step - loss: 2.6202 - mae: 2.6202
Epoch 127/200
2/2 [==============================] - 0s 5ms/step - loss: 4.2999 - mae: 4.2999
Epoch 128/200
2/2 [==============================] - 0s 6ms/step - loss: 2.4253 - mae: 2.4253
Epoch 129/200
2/2 [==============================] - 0s 6ms/step - loss: 1.4112 - mae: 1.4112
Epoch 130/200
2/2 [==============================] - 0s 5ms/step - loss: 1.7903 - mae: 1.7903
Epoch 131/200
2/2 [==============================] - 0s 6ms/step - loss: 0.8653 - mae: 0.8653
Epoch 132/200
2/2 [==============================] - 0s 12ms/step - loss: 2.1391 - mae: 2.1391
Epoch 133/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3911 - mae: 1.3911
Epoch 134/200
2/2 [==============================] - 0s 12ms/step - loss: 1.1253 - mae: 1.1253
Epoch 135/200
2/2 [==============================] - 0s 7ms/step - loss: 1.7845 - mae: 1.7845
Epoch 136/200
2/2 [==============================] - 0s 12ms/step - loss: 1.5779 - mae: 1.5779
Epoch 137/200
2/2 [==============================] - 0s 10ms/step - loss: 0.6124 - mae: 0.6124
Epoch 138/200
2/2 [==============================] - 0s 10ms/step - loss: 2.1694 - mae: 2.1694
Epoch 139/200
2/2 [==============================] - 0s 14ms/step - loss: 0.8609 - mae: 0.8609
Epoch 140/200
2/2 [==============================] - 0s 8ms/step - loss: 2.2875 - mae: 2.2875
Epoch 141/200
2/2 [==============================] - 0s 8ms/step - loss: 2.3581 - mae: 2.3581
Epoch 142/200
2/2 [==============================] - 0s 5ms/step - loss: 0.5700 - mae: 0.5700
Epoch 143/200
2/2 [==============================] - 0s 6ms/step - loss: 1.2420 - mae: 1.2420
Epoch 144/200
2/2 [==============================] - 0s 11ms/step - loss: 0.9949 - mae: 0.9949
Epoch 145/200
2/2 [==============================] - 0s 6ms/step - loss: 0.7412 - mae: 0.7412
Epoch 146/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6675 - mae: 1.6675
Epoch 147/200
2/2 [==============================] - 0s 14ms/step - loss: 1.8967 - mae: 1.8967
Epoch 148/200
2/2 [==============================] - 0s 5ms/step - loss: 0.6390 - mae: 0.6390
Epoch 149/200
2/2 [==============================] - 0s 6ms/step - loss: 2.0457 - mae: 2.0457
Epoch 150/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6658 - mae: 1.6658
Epoch 151/200
2/2 [==============================] - 0s 6ms/step - loss: 1.2185 - mae: 1.2185
Epoch 152/200
2/2 [==============================] - 0s 6ms/step - loss: 1.7930 - mae: 1.7930
Epoch 153/200
2/2 [==============================] - 0s 8ms/step - loss: 1.2255 - mae: 1.2255
Epoch 154/200
2/2 [==============================] - 0s 10ms/step - loss: 0.9245 - mae: 0.9245
Epoch 155/200
2/2 [==============================] - 0s 10ms/step - loss: 0.7340 - mae: 0.7340
Epoch 156/200
2/2 [==============================] - 0s 9ms/step - loss: 0.5897 - mae: 0.5897
Epoch 157/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6752 - mae: 1.6752
Epoch 158/200
2/2 [==============================] - 0s 9ms/step - loss: 1.4592 - mae: 1.4592
Epoch 159/200
2/2 [==============================] - 0s 10ms/step - loss: 1.5713 - mae: 1.5713
Epoch 160/200
2/2 [==============================] - 0s 6ms/step - loss: 2.8214 - mae: 2.8214
Epoch 161/200
2/2 [==============================] - 0s 7ms/step - loss: 1.9762 - mae: 1.9762
Epoch 162/200
2/2 [==============================] - 0s 19ms/step - loss: 3.6855 - mae: 3.6855
Epoch 163/200
2/2 [==============================] - 0s 13ms/step - loss: 2.4482 - mae: 2.4482
Epoch 164/200
2/2 [==============================] - 0s 10ms/step - loss: 1.1538 - mae: 1.1538
Epoch 165/200
2/2 [==============================] - 0s 9ms/step - loss: 1.8930 - mae: 1.8930
Epoch 166/200
2/2 [==============================] - 0s 7ms/step - loss: 0.7947 - mae: 0.7947
Epoch 167/200
2/2 [==============================] - 0s 12ms/step - loss: 2.0803 - mae: 2.0803
Epoch 168/200
2/2 [==============================] - 0s 6ms/step - loss: 1.6438 - mae: 1.6438
Epoch 169/200
2/2 [==============================] - 0s 15ms/step - loss: 1.5302 - mae: 1.5302
Epoch 170/200
2/2 [==============================] - 0s 10ms/step - loss: 2.2502 - mae: 2.2502
Epoch 171/200
2/2 [==============================] - 0s 7ms/step - loss: 1.3565 - mae: 1.3565
Epoch 172/200
2/2 [==============================] - 0s 5ms/step - loss: 1.7005 - mae: 1.7005
Epoch 173/200
2/2 [==============================] - 0s 13ms/step - loss: 0.5689 - mae: 0.5689
Epoch 174/200
2/2 [==============================] - 0s 6ms/step - loss: 1.4057 - mae: 1.4057
Epoch 175/200
2/2 [==============================] - 0s 13ms/step - loss: 0.9480 - mae: 0.9480
Epoch 176/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3511 - mae: 1.3511
Epoch 177/200
2/2 [==============================] - 0s 5ms/step - loss: 0.7883 - mae: 0.7883
Epoch 178/200
2/2 [==============================] - 0s 6ms/step - loss: 1.0327 - mae: 1.0327
Epoch 179/200
2/2 [==============================] - 0s 9ms/step - loss: 0.4363 - mae: 0.4363
Epoch 180/200
2/2 [==============================] - 0s 7ms/step - loss: 0.5013 - mae: 0.5013
Epoch 181/200
2/2 [==============================] - 0s 7ms/step - loss: 0.8895 - mae: 0.8895
Epoch 182/200
2/2 [==============================] - 0s 13ms/step - loss: 1.3899 - mae: 1.3899
Epoch 183/200
2/2 [==============================] - 0s 12ms/step - loss: 1.7968 - mae: 1.7968
Epoch 184/200
2/2 [==============================] - 0s 11ms/step - loss: 1.6880 - mae: 1.6880
Epoch 185/200
2/2 [==============================] - 0s 9ms/step - loss: 1.6186 - mae: 1.6186
Epoch 186/200
2/2 [==============================] - 0s 5ms/step - loss: 1.2189 - mae: 1.2189
Epoch 187/200
2/2 [==============================] - 0s 5ms/step - loss: 1.5934 - mae: 1.5934
Epoch 188/200
2/2 [==============================] - 0s 4ms/step - loss: 0.9925 - mae: 0.9925
Epoch 189/200
2/2 [==============================] - 0s 6ms/step - loss: 1.4474 - mae: 1.4474
Epoch 190/200
2/2 [==============================] - 0s 9ms/step - loss: 0.6325 - mae: 0.6325
Epoch 191/200
2/2 [==============================] - 0s 13ms/step - loss: 0.6227 - mae: 0.6227
Epoch 192/200
2/2 [==============================] - 0s 17ms/step - loss: 0.4163 - mae: 0.4163
Epoch 193/200
2/2 [==============================] - 0s 17ms/step - loss: 0.5070 - mae: 0.5070
Epoch 194/200
2/2 [==============================] - 0s 8ms/step - loss: 0.3083 - mae: 0.3083
Epoch 195/200
2/2 [==============================] - 0s 6ms/step - loss: 0.3470 - mae: 0.3470
Epoch 196/200
2/2 [==============================] - 0s 11ms/step - loss: 0.5570 - mae: 0.5570
Epoch 197/200
2/2 [==============================] - 0s 7ms/step - loss: 0.4510 - mae: 0.4510
Epoch 198/200
2/2 [==============================] - 0s 6ms/step - loss: 0.6438 - mae: 0.6438
Epoch 199/200
2/2 [==============================] - 0s 5ms/step - loss: 0.4387 - mae: 0.4387
Epoch 200/200
2/2 [==============================] - 0s 5ms/step - loss: 1.3176 - mae: 1.3176

Out[35]:

<tensorflow.python.keras.callbacks.History at 0x7f8c63355210>

In [36]:

model_1.summary()

model_1.summary()

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_9 (Dense)              (None, 100)               200       
_________________________________________________________________
dense_10 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_11 (Dense)             (None, 1)                 101       
=================================================================
Total params: 10,401
Trainable params: 10,401
Non-trainable params: 0
_________________________________________________________________

In [37]:

model_2.summary()

model_2.summary()

Model: "sequential_4"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_12 (Dense)             (None, 100)               200       
_________________________________________________________________
dense_13 (Dense)             (None, 50)                5050      
_________________________________________________________________
dense_14 (Dense)             (None, 1)                 51        
=================================================================
Total params: 5,301
Trainable params: 5,301
Non-trainable params: 0
_________________________________________________________________

In [38]:

model_3.summary()

model_3.summary()

Model: "sequential_5"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_15 (Dense)             (None, 75)                150       
_________________________________________________________________
dense_16 (Dense)             (None, 75)                5700      
_________________________________________________________________
dense_17 (Dense)             (None, 1)                 76        
=================================================================
Total params: 5,926
Trainable params: 5,926
Non-trainable params: 0
_________________________________________________________________

In [39]:

X_test2 = tf.range(100, 200, 4)
X_test2

X_test2 = tf.range(100, 200, 4) X_test2

Out[39]:

<tf.Tensor: shape=(25,), dtype=int32, numpy=
array([100, 104, 108, 112, 116, 120, 124, 128, 132, 136, 140, 144, 148,
       152, 156, 160, 164, 168, 172, 176, 180, 184, 188, 192, 196],
      dtype=int32)>

In [40]:

y_test2 = X_test2 + 10
y_test2

y_test2 = X_test2 + 10 y_test2

Out[40]:

<tf.Tensor: shape=(25,), dtype=int32, numpy=
array([110, 114, 118, 122, 126, 130, 134, 138, 142, 146, 150, 154, 158,
       162, 166, 170, 174, 178, 182, 186, 190, 194, 198, 202, 206],
      dtype=int32)>

In [41]:

plt.scatter(X_test2, y_test2);

plt.scatter(X_test2, y_test2);

In [42]:

y_preds_1 = tf.squeeze(model_1.predict(X_test))

y_preds_1 = tf.squeeze(model_1.predict(X_test))

In [43]:

plt.figure(figsize=(10,7))
# Training data 
plt.scatter(X_train, y_train, c="b", label="Training data")
# Testing data 
plt.scatter(X_test, y_test, c="g", label="Testing data")
# Show a legend 
plt.legend()

plt.figure(figsize=(10,7)) # Training data plt.scatter(X_train, y_train, c="b", label="Training data") # Testing data plt.scatter(X_test, y_test, c="g", label="Testing data") # Show a legend plt.legend()

Out[43]:

<matplotlib.legend.Legend at 0x7f8c5b503c50>

In [44]:

def plot_predictions(train_data=X_train, 
                     train_labels=y_train, 
                     test_data=X_test, 
                     test_labels=y_test, 
                     predictions=y_preds_1,
                     name="Model"):
  """
  Plots training data, test data and compares predictions.
  """
  plt.figure(figsize=(10, 7),)
  plt.title(name)
  # Plot training data in blue
  plt.scatter(train_data, train_labels, c="b", label="Training data")
  # Plot test data in green
  plt.scatter(test_data, test_labels, c="g", label="Testing data")
  # Plot the predictions in red (predictions were made on the test data)
  plt.scatter(test_data, predictions, c="r", label="Predictions")
  # Show the legend
  plt.legend();

def plot_predictions(train_data=X_train, train_labels=y_train, test_data=X_test, test_labels=y_test, predictions=y_preds_1, name="Model"): """ Plots training data, test data and compares predictions. """ plt.figure(figsize=(10, 7),) plt.title(name) # Plot training data in blue plt.scatter(train_data, train_labels, c="b", label="Training data") # Plot test data in green plt.scatter(test_data, test_labels, c="g", label="Testing data") # Plot the predictions in red (predictions were made on the test data) plt.scatter(test_data, predictions, c="r", label="Predictions") # Show the legend plt.legend();

In [45]:

y_preds_1 = tf.squeeze(model_1.predict(X_test))
y_preds_2 = tf.squeeze(model_2.predict(X_test))
y_preds_3 = tf.squeeze(model_3.predict(X_test))

y_preds_1 = tf.squeeze(model_1.predict(X_test)) y_preds_2 = tf.squeeze(model_2.predict(X_test)) y_preds_3 = tf.squeeze(model_3.predict(X_test))

WARNING:tensorflow:5 out of the last 7 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7f8c5dfe10e0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
WARNING:tensorflow:6 out of the last 8 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7f8c5b489cb0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

In [46]:

# Model 1
plot_predictions(predictions=y_preds_1, name="model_1")

# Model 1 plot_predictions(predictions=y_preds_1, name="model_1")

In [47]:

# Model 2
plot_predictions(predictions=y_preds_2, name="model_2")

# Model 2 plot_predictions(predictions=y_preds_2, name="model_2")

In [48]:

# Model 3
plot_predictions(predictions=y_preds_3, name="model_3")

# Model 3 plot_predictions(predictions=y_preds_3, name="model_3")