fix order when creating validation from train (keras-team#279)

* fix order when creating validation from train

* De-duplicate the data handling.

Co-authored-by: Mark Daoust <markdaoust@google.com>

guides/writing_a_training_loop_from_scratch.py

@@ -66,9 +66,21 @@
 (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
 x_train = np.reshape(x_train, (-1, 784))
 x_test = np.reshape(x_test, (-1, 784))
+
+# Reserve 10,000 samples for validation.
+x_val = x_train[-10000:]
+y_val = y_train[-10000:]
+x_train = x_train[:-10000]
+y_train = y_train[:-10000]
+
+# Prepare the training dataset.
 train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
 train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)
 
+# Prepare the validation dataset.
+val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
+val_dataset = val_dataset.batch(batch_size)
+
 """
 Here's our training loop:
 
@@ -152,20 +164,6 @@
 train_acc_metric = keras.metrics.SparseCategoricalAccuracy()
 val_acc_metric = keras.metrics.SparseCategoricalAccuracy()
 
-# Prepare the training dataset.
-batch_size = 64
-train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
-train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)
-
-# Prepare the validation dataset.
-# Reserve 10,000 samples for validation.
-x_val = x_train[-10000:]
-y_val = y_train[-10000:]
-x_train = x_train[:-10000]
-y_train = y_train[:-10000]
-val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
-val_dataset = val_dataset.batch(64)
-
 """
 Here's our training & evaluation loop:
 """