Merge pull request #4943 from DecentGradient/patch-2

Explain why input_shape is needed here.

Merge pull request #4943 from DecentGradient/patch-2
Explain why input_shape is needed here.
887bbcb9 · Mark Daoust · GitHub · af41cc00 · 1be8e32a · 887bbcb9
Unverified Commit 887bbcb9 authored Jul 30, 2018 by Mark Daoust Committed by GitHub Jul 30, 2018
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 0 deletions

samples/core/tutorials/keras/overfit_and_underfit.ipynb samples/core/tutorials/keras/overfit_and_underfit.ipynb +1 -0

No files found.
--- a/samples/core/tutorials/keras/overfit_and_underfit.ipynb
+++ b/samples/core/tutorials/keras/overfit_and_underfit.ipynb
@@ -294,6 +294,7 @@
      "cell_type": "code",
      "source": [
        "baseline_model = keras.Sequential([\n",
+        "    # `input_shape` is only required here so that `.summary` works. \n"
        "    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),\n",
        "    keras.layers.Dense(16, activation=tf.nn.relu),\n",
        "    keras.layers.Dense(1, activation=tf.nn.sigmoid)\n",