Merge branch 'master' into changes-chap16

16_nlp_with_rnns_and_attention.ipynb

@@ -309,6 +309,20 @@
     "## Creating and Training the Model"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: the following code may take up to 24 hours to run, depending on your hardware. If you use a GPU, it may take just 1 or 2 hours, or less."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Note**: the `GRU` class will only use the GPU (if you have one) when using the default values for the following arguments: `activation`, `recurrent_activation`, `recurrent_dropout`, `unroll`, `use_bias` and `reset_after`. This is why I commented out `recurrent_dropout=0.2` (compared to the book)."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 18,
@@ -317,9 +331,11 @@
    "source": [
     "model = keras.models.Sequential([\n",
     "    keras.layers.GRU(128, return_sequences=True, input_shape=[None, max_id],\n",
-    "                     dropout=0.2, recurrent_dropout=0.2),\n",
+    "                     #dropout=0.2, recurrent_dropout=0.2),\n",
+    "                     dropout=0.2),\n",
     "    keras.layers.GRU(128, return_sequences=True,\n",
-    "                     dropout=0.2, recurrent_dropout=0.2),\n",
+    "                     #dropout=0.2, recurrent_dropout=0.2),\n",
+    "                     dropout=0.2),\n",
     "    keras.layers.TimeDistributed(keras.layers.Dense(max_id,\n",
     "                                                    activation=\"softmax\"))\n",
     "])\n",
@@ -346,6 +362,13 @@
     "    return tf.one_hot(X, max_id)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: the `predict_classes()` method is deprecated. Instead, we must use `np.argmax(model.predict(X_new), axis=-1)`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -353,6 +376,7 @@
    "outputs": [],
    "source": [
     "X_new = preprocess([\"How are yo\"])\n",
+    "#Y_pred = model.predict_classes(X_new)\n",
     "Y_pred = np.argmax(model.predict(X_new), axis=-1)\n",
     "tokenizer.sequences_to_texts(Y_pred + 1)[0][-1] # 1st sentence, last char"
    ]
@@ -614,7 +638,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "(X_train, y_test), (X_valid, y_test) = keras.datasets.imdb.load_data()"
+    "(X_train, y_train), (X_test, y_test) = keras.datasets.imdb.load_data()"
    ]
   },
   {
@@ -1785,6 +1809,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#ids = model.predict_classes(X_new)\n",
     "ids = np.argmax(model.predict(X_new), axis=-1)\n",
     "for date_str in ids_to_date_strs(ids):\n",
     "    print(date_str)"
@@ -1819,6 +1844,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#ids = model.predict_classes(X_new)\n",
     "ids = np.argmax(model.predict(X_new), axis=-1)\n",
     "for date_str in ids_to_date_strs(ids):\n",
     "    print(date_str)"
@@ -1847,6 +1873,7 @@
     "\n",
     "def convert_date_strs(date_strs):\n",
     "    X = prepare_date_strs_padded(date_strs)\n",
+    "    #ids = model.predict_classes(X)\n",
     "    ids = np.argmax(model.predict(X), axis=-1)\n",
     "    return ids_to_date_strs(ids)"
    ]
@@ -2226,7 +2253,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Warning**: due to a TF bug, this version only works using TensorFlow 2.2."
+    "**Warning**: due to a TF bug, this version only works using TensorFlow 2.2 or above."
    ]
   },
   {
@@ -2712,7 +2739,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.7.9"
   },
   "nav_menu": {},
   "toc": {