Fixing wide-and-deep to use normalized inputs

Thanks for this great book/repo. I noticed the wide and deep example is using non-normalized inputs which leads to performance degradation.
2022-06-27 09:27:51 -05:00 · 2022-06-27 09:27:51 -05:00 · bdd246bf07
parent eabcc492aa
commit bdd246bf07
1 changed files with 1 additions and 1 deletions
--- a/10_neural_nets_with_keras.ipynb
+++ b/10_neural_nets_with_keras.ipynb
@ -1568,7 +1568,7 @@
    "normalized = normalization_layer(input_)\n",
    "hidden1 = hidden_layer1(normalized)\n",
    "hidden2 = hidden_layer2(hidden1)\n",
-    "concat = concat_layer([input_, hidden2])\n",
+    "concat = concat_layer([normalized, hidden2])\n",
    "output = output_layer(concat)\n",
    "\n",
    "model = tf.keras.Model(inputs=[input_], outputs=[output])"