Added data pipeline

lmoroney · Jun 9, 2020 · 9d4e9b6 · 9d4e9b6 · GzuPark · Sep 14, 2020
1 parent 1d9afb0
commit 9d4e9b6
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 0 deletions.
diff --git a/... Practice/Course 3 - NLP/.ipynb_checkpoints/Course 3 - Week 2 - Lesson 3-checkpoint.ipynb b/... Practice/Course 3 - NLP/.ipynb_checkpoints/Course 3 - Week 2 - Lesson 3-checkpoint.ipynb
@@ -151,6 +151,20 @@
     "  print ('{} ----> {}'.format(ts, tokenizer.decode([ts])))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "BUFFER_SIZE = 10000\n",
+    "BATCH_SIZE = 64\n",
+    "\n",
+    "train_dataset = train_data.shuffle(BUFFER_SIZE)\n",
+    "train_dataset = train_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(train_dataset))\n",
+    "test_dataset = test_data.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(test_data))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,

diff --git a/TensorFlow In Practice/Course 3 - NLP/Course 3 - Week 2 - Lesson 3.ipynb b/TensorFlow In Practice/Course 3 - NLP/Course 3 - Week 2 - Lesson 3.ipynb
@@ -151,6 +151,20 @@
     "  print ('{} ----> {}'.format(ts, tokenizer.decode([ts])))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "BUFFER_SIZE = 10000\n",
+    "BATCH_SIZE = 64\n",
+    "\n",
+    "train_dataset = train_data.shuffle(BUFFER_SIZE)\n",
+    "train_dataset = train_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(train_dataset))\n",
+    "test_dataset = test_data.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(test_data))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,