Merge pull request #4933 from DecentGradient/patch-1

Use NUM_WORDS in input_shape

Merge pull request #4933 from DecentGradient/patch-1
Use NUM_WORDS in input_shape
89e30510 · Mark Daoust · GitHub · 22e248ce · c94d1d29 · 89e30510
Unverified Commit 89e30510 authored Jul 30, 2018 by Mark Daoust Committed by GitHub Jul 30, 2018
Hide whitespace changes
Inline Side-by-side

Showing with 5 additions and 5 deletions

samples/core/tutorials/keras/overfit_and_underfit.ipynb samples/core/tutorials/keras/overfit_and_underfit.ipynb +5 -5

No files found.
--- a/samples/core/tutorials/keras/overfit_and_underfit.ipynb
+++ b/samples/core/tutorials/keras/overfit_and_underfit.ipynb
@@ -294,7 +294,7 @@
      "cell_type": "code",
      "source": [
        "baseline_model = keras.Sequential([\n",
-        "    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(10000,)),\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",
        "])\n",
@@ -365,7 +365,7 @@
      "cell_type": "code",
      "source": [
        "smaller_model = keras.Sequential([\n",
-        "    keras.layers.Dense(4, activation=tf.nn.relu, input_shape=(10000,)),\n",
+        "    keras.layers.Dense(4, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),\n",
        "    keras.layers.Dense(4, activation=tf.nn.relu),\n",
        "    keras.layers.Dense(1, activation=tf.nn.sigmoid)\n",
        "])\n",
@@ -438,7 +438,7 @@
      "cell_type": "code",
      "source": [
        "bigger_model = keras.models.Sequential([\n",
-        "    keras.layers.Dense(512, activation=tf.nn.relu, input_shape=(10000,)),\n",
+        "    keras.layers.Dense(512, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),\n",
        "    keras.layers.Dense(512, activation=tf.nn.relu),\n",
        "    keras.layers.Dense(1, activation=tf.nn.sigmoid)\n",
        "])\n",
@@ -606,7 +606,7 @@
      "source": [
        "l2_model = keras.models.Sequential([\n",
        "    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),\n",
-        "                       activation=tf.nn.relu, input_shape=(10000,)),\n",
+        "                       activation=tf.nn.relu, input_shape=(NUM_WORDS,)),\n",
        "    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),\n",
        "                       activation=tf.nn.relu),\n",
        "    keras.layers.Dense(1, activation=tf.nn.sigmoid)\n",
@@ -697,7 +697,7 @@
      "cell_type": "code",
      "source": [
        "dpt_model = keras.models.Sequential([\n",
-        "    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(10000,)),\n",
+        "    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),\n",
        "    keras.layers.Dropout(0.5),\n",
        "    keras.layers.Dense(16, activation=tf.nn.relu),\n",
        "    keras.layers.Dropout(0.5),\n",