Update notebooks for TF 2.6

Author: fchollet

chapter02_mathematical-building-blocks.ipynb

@@ -1135,7 +1135,7 @@
    },
    "outputs": [],
    "source": [
-    "model = models.Sequential([\n",
+    "model = keras.Sequential([\n",
     "    layers.Dense(512, activation=\"relu\"),\n",
     "    layers.Dense(10, activation=\"softmax\")\n",
     "])"
@@ -1280,12 +1280,16 @@
    },
    "outputs": [],
    "source": [
+    "import math\n",
+    "\n",
     "class BatchGenerator:\n",
     "    def __init__(self, images, labels, batch_size=128):\n",
+    "        assert len(images) == len(labels)\n",
     "        self.index = 0\n",
     "        self.images = images\n",
     "        self.labels = labels\n",
     "        self.batch_size = batch_size\n",
+    "        self.num_batches = math.ceil(len(images) / batch_size)\n",
     "\n",
     "    def next(self):\n",
     "        images = self.images[self.index : self.index + self.batch_size]\n",
@@ -1374,7 +1378,7 @@
     "    for epoch_counter in range(epochs):\n",
     "        print(f\"Epoch {epoch_counter}\")\n",
     "        batch_generator = BatchGenerator(images, labels)\n",
-    "        for batch_counter in range(len(images) // batch_size):\n",
+    "        for batch_counter in range(batch_generator.num_batches):\n",
     "            images_batch, labels_batch = batch_generator.next()\n",
     "            loss = one_training_step(model, images_batch, labels_batch)\n",
     "            if batch_counter % 100 == 0:\n",

chapter08_intro-to-dl-for-computer-vision.ipynb

@@ -341,7 +341,7 @@
     "from tensorflow.keras import layers\n",
     "\n",
     "inputs = keras.Input(shape=(180, 180, 3))\n",
-    "x = layers.experimental.preprocessing.Rescaling(1./255)(inputs)\n",
+    "x = layers.Rescaling(1./255)(inputs)\n",
     "x = layers.Conv2D(filters=32, kernel_size=3, activation=\"relu\")(x)\n",
     "x = layers.MaxPooling2D(pool_size=2)(x)\n",
     "x = layers.Conv2D(filters=64, kernel_size=3, activation=\"relu\")(x)\n",
@@ -415,7 +415,7 @@
    },
    "outputs": [],
    "source": [
-    "from tensorflow.keras.preprocessing import image_dataset_from_directory\n",
+    "from tensorflow.keras.utils import image_dataset_from_directory\n",
     "\n",
     "train_dataset = image_dataset_from_directory(\n",
     "    new_base_dir / \"train\",\n",
@@ -663,9 +663,9 @@
    "source": [
     "data_augmentation = keras.Sequential(\n",
     "    [\n",
-    "        layers.experimental.preprocessing.RandomFlip(\"horizontal\"),\n",
-    "        layers.experimental.preprocessing.RandomRotation(0.1),\n",
-    "        layers.experimental.preprocessing.RandomZoom(0.2),\n",
+    "        layers.RandomFlip(\"horizontal\"),\n",
+    "        layers.RandomRotation(0.1),\n",
+    "        layers.RandomZoom(0.2),\n",
     "    ]\n",
     ")"
    ]
@@ -715,7 +715,7 @@
    "source": [
     "inputs = keras.Input(shape=(180, 180, 3))\n",
     "x = data_augmentation(inputs)\n",
-    "x = layers.experimental.preprocessing.Rescaling(1./255)(x)\n",
+    "x = layers.Rescaling(1./255)(x)\n",
     "x = layers.Conv2D(filters=32, kernel_size=3, activation=\"relu\")(x)\n",
     "x = layers.MaxPooling2D(pool_size=2)(x)\n",
     "x = layers.Conv2D(filters=64, kernel_size=3, activation=\"relu\")(x)\n",
@@ -1055,9 +1055,9 @@
    "source": [
     "data_augmentation = keras.Sequential(\n",
     "    [\n",
-    "        layers.experimental.preprocessing.RandomFlip(\"horizontal\"),\n",
-    "        layers.experimental.preprocessing.RandomRotation(0.1),\n",
-    "        layers.experimental.preprocessing.RandomZoom(0.2),\n",
+    "        layers.RandomFlip(\"horizontal\"),\n",
+    "        layers.RandomRotation(0.1),\n",
+    "        layers.RandomZoom(0.2),\n",
     "    ]\n",
     ")\n",
     "\n",

chapter09_part01_image-segmentation.ipynb

@@ -82,7 +82,7 @@
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
-    "from tensorflow.keras.preprocessing.image import load_img, img_to_array\n",
+    "from tensorflow.keras.utils import load_img, img_to_array\n",
     "\n",
     "plt.axis(\"off\")\n",
     "plt.imshow(load_img(input_img_paths[9]))"
@@ -157,7 +157,7 @@
     "\n",
     "def get_model(img_size, num_classes):\n",
     "    inputs = keras.Input(shape=img_size + (3,))\n",
-    "    x = layers.experimental.preprocessing.Rescaling(1./255)(inputs)\n",
+    "    x = layers.Rescaling(1./255)(inputs)\n",
     "\n",
     "    x = layers.Conv2D(64, 3, strides=2, activation=\"relu\", padding=\"same\")(x)\n",
     "    x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
@@ -230,7 +230,7 @@
    },
    "outputs": [],
    "source": [
-    "from tensorflow.keras.preprocessing.image import array_to_img\n",
+    "from tensorflow.keras.utils import array_to_img\n",
     "\n",
     "model = keras.models.load_model(\"oxford_segmentation.keras\")\n",
     "\n",

chapter09_part02_modern-convnet-architecture-patterns.ipynb

@@ -99,7 +99,7 @@
    "outputs": [],
    "source": [
     "inputs = keras.Input(shape=(32, 32, 3))\n",
-    "x = layers.experimental.preprocessing.Rescaling(1./255)(inputs)\n",
+    "x = layers.Rescaling(1./255)(inputs)\n",
     "\n",
     "def residual_block(x, filters, pooling=False):\n",
     "    residual = x\n",
@@ -186,7 +186,7 @@
    "outputs": [],
    "source": [
     "import os, shutil, pathlib\n",
-    "from tensorflow.keras.preprocessing import image_dataset_from_directory\n",
+    "from tensorflow.keras.utils import image_dataset_from_directory\n",
     "\n",
     "original_dir = pathlib.Path(\"train\")\n",
     "new_base_dir = pathlib.Path(\"cats_vs_dogs_small\")\n",
@@ -228,9 +228,9 @@
    "source": [
     "data_augmentation = keras.Sequential(\n",
     "    [\n",
-    "        layers.experimental.preprocessing.RandomFlip(\"horizontal\"),\n",
-    "        layers.experimental.preprocessing.RandomRotation(0.1),\n",
-    "        layers.experimental.preprocessing.RandomZoom(0.2),\n",
+    "        layers.RandomFlip(\"horizontal\"),\n",
+    "        layers.RandomRotation(0.1),\n",
+    "        layers.RandomZoom(0.2),\n",
     "    ]\n",
     ")"
    ]
@@ -246,7 +246,7 @@
     "inputs = keras.Input(shape=(180, 180, 3))\n",
     "x = data_augmentation(inputs)\n",
     "\n",
-    "x = layers.experimental.preprocessing.Rescaling(1./255)(x)\n",
+    "x = layers.Rescaling(1./255)(x)\n",
     "x = layers.Conv2D(filters=32, kernel_size=5, use_bias=False)(x)\n",
     "\n",
     "for size in [32, 64, 128, 256, 512]:\n",

chapter09_part03_interpreting-what-convnets-learn.ipynb

@@ -79,9 +79,9 @@
     "    origin=\"https://img-datasets.s3.amazonaws.com/cat.jpg\")\n",
     "\n",
     "def get_img_array(img_path, target_size):\n",
-    "    img = keras.preprocessing.image.load_img(\n",
+    "    img = keras.utils.load_img(\n",
     "        img_path, target_size=target_size)\n",
-    "    array = keras.preprocessing.image.img_to_array(img)\n",
+    "    array = keras.utils.img_to_array(img)\n",
     "    array = np.expand_dims(array, axis=0)\n",
     "    return array\n",
     "\n",
@@ -493,7 +493,7 @@
     "            :,\n",
     "        ] = image\n",
     "\n",
-    "keras.preprocessing.image.save_img(\n",
+    "keras.utils.save_img(\n",
     "    f\"filters_for_layer_{layer_name}.png\", stitched_filters)"
    ]
   },
@@ -548,8 +548,8 @@
     "    origin=\"https://img-datasets.s3.amazonaws.com/elephant.jpg\")\n",
     "\n",
     "def get_img_array(img_path, target_size):\n",
-    "    img = keras.preprocessing.image.load_img(img_path, target_size=target_size)\n",
-    "    array = keras.preprocessing.image.img_to_array(img)\n",
+    "    img = keras.utils.load_img(img_path, target_size=target_size)\n",
+    "    array = keras.utils.img_to_array(img)\n",
     "    array = np.expand_dims(array, axis=0)\n",
     "    array = keras.applications.xception.preprocess_input(array)\n",
     "    return array\n",
@@ -724,21 +724,21 @@
    "source": [
     "import matplotlib.cm as cm\n",
     "\n",
-    "img = keras.preprocessing.image.load_img(img_path)\n",
-    "img = keras.preprocessing.image.img_to_array(img)\n",
+    "img = keras.utils.load_img(img_path)\n",
+    "img = keras.utils.img_to_array(img)\n",
     "\n",
     "heatmap = np.uint8(255 * heatmap)\n",
     "\n",
     "jet = cm.get_cmap(\"jet\")\n",
     "jet_colors = jet(np.arange(256))[:, :3]\n",
     "jet_heatmap = jet_colors[heatmap]\n",
     "\n",
-    "jet_heatmap = keras.preprocessing.image.array_to_img(jet_heatmap)\n",
+    "jet_heatmap = keras.utils.array_to_img(jet_heatmap)\n",
     "jet_heatmap = jet_heatmap.resize((img.shape[1], img.shape[0]))\n",
-    "jet_heatmap = keras.preprocessing.image.img_to_array(jet_heatmap)\n",
+    "jet_heatmap = keras.utils.img_to_array(jet_heatmap)\n",
     "\n",
     "superimposed_img = jet_heatmap * 0.4 + img\n",
-    "superimposed_img = keras.preprocessing.image.array_to_img(superimposed_img)\n",
+    "superimposed_img = keras.utils.array_to_img(superimposed_img)\n",
     "\n",
     "save_path = \"elephant_cam.jpg\"\n",
     "superimposed_img.save(save_path)"

chapter10_dl-for-timeseries.ipynb

@@ -213,7 +213,7 @@
     "import numpy as np\n",
     "from tensorflow import keras\n",
     "int_sequence = np.arange(10)\n",
-    "dummy_dataset = keras.preprocessing.timeseries_dataset_from_array(\n",
+    "dummy_dataset = keras.utils.timeseries_dataset_from_array(\n",
     "    data=int_sequence[:-3],\n",
     "    targets=int_sequence[3:],\n",
     "    sequence_length=3,\n",
@@ -247,7 +247,7 @@
     "delay = sampling_rate * (sequence_length + 24 - 1)\n",
     "batch_size = 256\n",
     "\n",
-    "train_dataset = keras.preprocessing.timeseries_dataset_from_array(\n",
+    "train_dataset = keras.utils.timeseries_dataset_from_array(\n",
     "    raw_data[:-delay],\n",
     "    targets=temperature[delay:],\n",
     "    sampling_rate=sampling_rate,\n",
@@ -257,7 +257,7 @@
     "    start_index=0,\n",
     "    end_index=num_train_samples)\n",
     "\n",
-    "val_dataset = keras.preprocessing.timeseries_dataset_from_array(\n",
+    "val_dataset = keras.utils.timeseries_dataset_from_array(\n",
     "    raw_data[:-delay],\n",
     "    targets=temperature[delay:],\n",
     "    sampling_rate=sampling_rate,\n",
@@ -267,7 +267,7 @@
     "    start_index=num_train_samples,\n",
     "    end_index=num_train_samples + num_val_samples)\n",
     "\n",
-    "test_dataset = keras.preprocessing.timeseries_dataset_from_array(\n",
+    "test_dataset = keras.utils.timeseries_dataset_from_array(\n",
     "    raw_data[:-delay],\n",
     "    targets=temperature[delay:],\n",
     "    sampling_rate=sampling_rate,\n",

chapter11_part01_introduction.ipynb

@@ -153,7 +153,7 @@
    },
    "outputs": [],
    "source": [
-    "from tensorflow.keras.layers.experimental.preprocessing import TextVectorization\n",
+    "from tensorflow.keras.layers import TextVectorization\n",
     "text_vectorization = TextVectorization(\n",
     "    output_mode=\"int\",\n",
     ")"
@@ -336,13 +336,13 @@
     "from tensorflow import keras\n",
     "batch_size = 32\n",
     "\n",
-    "train_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "train_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/train\", batch_size=batch_size\n",
     ")\n",
-    "val_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "val_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/val\", batch_size=batch_size\n",
     ")\n",
-    "test_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "test_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/test\", batch_size=batch_size\n",
     ")"
    ]

chapter11_part02_sequence-models.ipynb

@@ -82,13 +82,13 @@
     "        shutil.move(train_dir / category / fname,\n",
     "                    val_dir / category / fname)\n",
     "\n",
-    "train_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "train_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/train\", batch_size=batch_size\n",
     ")\n",
-    "val_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "val_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/val\", batch_size=batch_size\n",
     ")\n",
-    "test_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "test_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/test\", batch_size=batch_size\n",
     ")\n",
     "text_only_train_ds = train_ds.map(lambda x, y: x)"
@@ -111,10 +111,11 @@
    },
    "outputs": [],
    "source": [
-    "from tensorflow.keras.layers.experimental.preprocessing import TextVectorization\n",
+    "from tensorflow.keras import layers\n",
+    "\n",
     "max_length = 600\n",
     "max_tokens = 20000\n",
-    "text_vectorization = TextVectorization(\n",
+    "text_vectorization = layers.TextVectorization(\n",
     "    max_tokens=max_tokens,\n",
     "    output_mode=\"int\",\n",
     "    output_sequence_length=max_length,\n",
@@ -144,7 +145,6 @@
    "outputs": [],
    "source": [
     "import tensorflow as tf\n",
-    "from tensorflow.keras import layers\n",
     "inputs = keras.Input(shape=(None,), dtype=\"int64\")\n",
     "embedded = tf.one_hot(inputs, depth=max_tokens)\n",
     "x = layers.Bidirectional(layers.LSTM(32))(embedded)\n",

chapter11_part03_transformer.ipynb

@@ -109,13 +109,13 @@
     "        shutil.move(train_dir / category / fname,\n",
     "                    val_dir / category / fname)\n",
     "\n",
-    "train_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "train_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/train\", batch_size=batch_size\n",
     ")\n",
-    "val_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "val_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/val\", batch_size=batch_size\n",
     ")\n",
-    "test_ds = keras.preprocessing.text_dataset_from_directory(\n",
+    "test_ds = keras.utils.text_dataset_from_directory(\n",
     "    \"aclImdb/test\", batch_size=batch_size\n",
     ")\n",
     "text_only_train_ds = train_ds.map(lambda x, y: x)"
@@ -138,10 +138,11 @@
    },
    "outputs": [],
    "source": [
-    "from tensorflow.keras.layers.experimental.preprocessing import TextVectorization\n",
+    "from tensorflow.keras import layers\n",
+    "\n",
     "max_length = 600\n",
     "max_tokens = 20000\n",
-    "text_vectorization = TextVectorization(\n",
+    "text_vectorization = layers.TextVectorization(\n",
     "    max_tokens=max_tokens,\n",
     "    output_mode=\"int\",\n",
     "    output_sequence_length=max_length,\n",

chapter11_part04_sequence-to-sequence-learning.ipynb

@@ -103,7 +103,6 @@
    },
    "outputs": [],
    "source": [
-    "from keras.layers.experimental.preprocessing import TextVectorization\n",
     "import tensorflow as tf\n",
     "import string\n",
     "import re\n",
@@ -120,12 +119,12 @@
     "vocab_size = 15000\n",
     "sequence_length = 20\n",
     "\n",
-    "source_vectorization = TextVectorization(\n",
+    "source_vectorization = layers.TextVectorization(\n",
     "    max_tokens=vocab_size,\n",
     "    output_mode=\"int\",\n",
     "    output_sequence_length=sequence_length,\n",
     ")\n",
-    "target_vectorization = TextVectorization(\n",
+    "target_vectorization = layers.TextVectorization(\n",
     "    max_tokens=vocab_size,\n",
     "    output_mode=\"int\",\n",
     "    output_sequence_length=sequence_length + 1,\n",