alihan/deep-learning-with-python-notebooks
1
0
Fork 0
mirror of https://github.com/fchollet/deep-learning-with-python-notebooks.git synced 2021-07-27 01:28:40 +03:00
Code Issues Projects Releases Wiki Activity

Update notebooks for TF 2.6

Browse Source
This commit is contained in:
François Chollet
2021-06-25 14:03:50 -07:00
parent 91e35258ea
commit 564df50076
14 changed files with 68 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
chapter02_mathematical-building-blocks.ipynb
View File

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

18
chapter08_intro-to-dl-for-computer-vision.ipynb
View File

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

6
chapter09_part01_image-segmentation.ipynb
View File

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

12
chapter09_part02_modern-convnet-architecture-patterns.ipynb
View File

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

20
chapter09_part03_interpreting-what-convnets-learn.ipynb
View File

@@ -79,9 +79,9 @@
" origin=\"https://img-datasets.s3.amazonaws.com/cat.jpg\")\n", " origin=\"https://img-datasets.s3.amazonaws.com/cat.jpg\")\n",
"\n", "\n",
"def get_img_array(img_path, target_size):\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", " 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", " array = np.expand_dims(array, axis=0)\n",
" return array\n", " return array\n",
"\n", "\n",
@@ -493,7 +493,7 @@
" :,\n", " :,\n",
" ] = image\n", " ] = image\n",
"\n", "\n",
"keras.preprocessing.image.save_img(\n", "keras.utils.save_img(\n",
" f\"filters_for_layer_{layer_name}.png\", stitched_filters)" " f\"filters_for_layer_{layer_name}.png\", stitched_filters)"
] ]
}, },
@@ -548,8 +548,8 @@
" origin=\"https://img-datasets.s3.amazonaws.com/elephant.jpg\")\n", " origin=\"https://img-datasets.s3.amazonaws.com/elephant.jpg\")\n",
"\n", "\n",
"def get_img_array(img_path, target_size):\n", "def get_img_array(img_path, target_size):\n",
" img = keras.preprocessing.image.load_img(img_path, target_size=target_size)\n", " img = keras.utils.load_img(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", " array = np.expand_dims(array, axis=0)\n",
" array = keras.applications.xception.preprocess_input(array)\n", " array = keras.applications.xception.preprocess_input(array)\n",
" return array\n", " return array\n",
@@ -724,8 +724,8 @@
"source": [ "source": [
"import matplotlib.cm as cm\n", "import matplotlib.cm as cm\n",
"\n", "\n",
"img = keras.preprocessing.image.load_img(img_path)\n", "img = keras.utils.load_img(img_path)\n",
"img = keras.preprocessing.image.img_to_array(img)\n", "img = keras.utils.img_to_array(img)\n",
"\n", "\n",
"heatmap = np.uint8(255 * heatmap)\n", "heatmap = np.uint8(255 * heatmap)\n",
"\n", "\n",
@@ -733,12 +733,12 @@
"jet_colors = jet(np.arange(256))[:, :3]\n", "jet_colors = jet(np.arange(256))[:, :3]\n",
"jet_heatmap = jet_colors[heatmap]\n", "jet_heatmap = jet_colors[heatmap]\n",
"\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 = 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", "\n",
"superimposed_img = jet_heatmap * 0.4 + img\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", "\n",
"save_path = \"elephant_cam.jpg\"\n", "save_path = \"elephant_cam.jpg\"\n",
"superimposed_img.save(save_path)" "superimposed_img.save(save_path)"

8
chapter10_dl-for-timeseries.ipynb
View File

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

8
chapter11_part01_introduction.ipynb
View File

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

12
chapter11_part02_sequence-models.ipynb
View File

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

11
chapter11_part03_transformer.ipynb
View File

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

5
chapter11_part04_sequence-to-sequence-learning.ipynb
View File

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

4
chapter12_part01_text-generation.ipynb
View File

@@ -136,7 +136,7 @@
"source": [ "source": [
"import tensorflow as tf\n", "import tensorflow as tf\n",
"from tensorflow import keras\n", "from tensorflow import keras\n",
"dataset = keras.preprocessing.text_dataset_from_directory(\n", "dataset = keras.utils.text_dataset_from_directory(\n",
" directory=\"aclImdb\", label_mode=None, batch_size=256)\n", " directory=\"aclImdb\", label_mode=None, batch_size=256)\n",
"dataset = dataset.map(lambda x: tf.strings.regex_replace(x, \"<br />\", \" \"))" "dataset = dataset.map(lambda x: tf.strings.regex_replace(x, \"<br />\", \" \"))"
] ]
@@ -158,7 +158,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"from tensorflow.keras.layers.experimental.preprocessing import TextVectorization\n", "from tensorflow.keras.layers import TextVectorization\n",
"\n", "\n",
"sequence_length = 100\n", "sequence_length = 100\n",
"vocab_size = 15000\n", "vocab_size = 15000\n",

8
chapter12_part02_deep-dream.ipynb
View File

@@ -42,7 +42,7 @@
" \"coast.jpg\", origin=\"https://img-datasets.s3.amazonaws.com/coast.jpg\")\n", " \"coast.jpg\", origin=\"https://img-datasets.s3.amazonaws.com/coast.jpg\")\n",
"\n", "\n",
"plt.axis(\"off\")\n", "plt.axis(\"off\")\n",
"plt.imshow(keras.preprocessing.image.load_img(base_image_path))" "plt.imshow(keras.utils.load_img(base_image_path))"
] ]
}, },
{ {
@@ -154,8 +154,8 @@
"import numpy as np\n", "import numpy as np\n",
"\n", "\n",
"def preprocess_image(image_path):\n", "def preprocess_image(image_path):\n",
" img = keras.preprocessing.image.load_img(image_path)\n", " img = keras.utils.load_img(image_path)\n",
" img = keras.preprocessing.image.img_to_array(img)\n", " img = keras.utils.img_to_array(img)\n",
" img = np.expand_dims(img, axis=0)\n", " img = np.expand_dims(img, axis=0)\n",
" img = keras.applications.inception_v3.preprocess_input(img)\n", " img = keras.applications.inception_v3.preprocess_input(img)\n",
" return img\n", " return img\n",
@@ -201,7 +201,7 @@
" img += lost_detail\n", " img += lost_detail\n",
" shrunk_original_img = tf.image.resize(original_img, shape)\n", " shrunk_original_img = tf.image.resize(original_img, shape)\n",
"\n", "\n",
"keras.preprocessing.image.save_img(\"dream.png\", deprocess_image(img.numpy()))" "keras.utils.save_img(\"dream.png\", deprocess_image(img.numpy()))"
] ]
}, },
{ {

8
chapter12_part03_neural-style-transfer.ipynb
View File

@@ -69,7 +69,7 @@
"style_reference_image_path = keras.utils.get_file(\n", "style_reference_image_path = keras.utils.get_file(\n",
" \"starry_night.jpg\", origin=\"https://img-datasets.s3.amazonaws.com/starry_night.jpg\")\n", " \"starry_night.jpg\", origin=\"https://img-datasets.s3.amazonaws.com/starry_night.jpg\")\n",
"\n", "\n",
"original_width, original_height = keras.preprocessing.image.load_img(base_image_path).size\n", "original_width, original_height = keras.utils.load_img(base_image_path).size\n",
"img_height = 400\n", "img_height = 400\n",
"img_width = round(original_width * img_height / original_height)" "img_width = round(original_width * img_height / original_height)"
] ]
@@ -94,9 +94,9 @@
"import numpy as np\n", "import numpy as np\n",
"\n", "\n",
"def preprocess_image(image_path):\n", "def preprocess_image(image_path):\n",
" img = keras.preprocessing.image.load_img(\n", " img = keras.utils.load_img(\n",
" image_path, target_size=(img_height, img_width))\n", " image_path, target_size=(img_height, img_width))\n",
" img = keras.preprocessing.image.img_to_array(img)\n", " img = keras.utils.img_to_array(img)\n",
" img = np.expand_dims(img, axis=0)\n", " img = np.expand_dims(img, axis=0)\n",
" img = keras.applications.vgg19.preprocess_input(img)\n", " img = keras.applications.vgg19.preprocess_input(img)\n",
" return img\n", " return img\n",
@@ -312,7 +312,7 @@
" print(f\"Iteration {i}: loss={loss:.2f}\")\n", " print(f\"Iteration {i}: loss={loss:.2f}\")\n",
" img = deprocess_image(combination_image.numpy())\n", " img = deprocess_image(combination_image.numpy())\n",
" fname = f\"combination_image_at_iteration_{i}.png\"\n", " fname = f\"combination_image_at_iteration_{i}.png\"\n",
" keras.preprocessing.image.save_img(fname, img)" " keras.utils.save_img(fname, img)"
] ]
}, },
{ {

4
chapter12_part05_gans.ipynb
View File

@@ -85,7 +85,7 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"from tensorflow import keras\n", "from tensorflow import keras\n",
"dataset = keras.preprocessing.image_dataset_from_directory(\n", "dataset = keras.utils_dataset_from_directory(\n",
" \"celeba_gan\",\n", " \"celeba_gan\",\n",
" label_mode=None,\n", " label_mode=None,\n",
" image_size=(64, 64),\n", " image_size=(64, 64),\n",
@@ -357,7 +357,7 @@
" generated_images *= 255\n", " generated_images *= 255\n",
" generated_images.numpy()\n", " generated_images.numpy()\n",
" for i in range(self.num_img):\n", " for i in range(self.num_img):\n",
" img = keras.preprocessing.image.array_to_img(generated_images[i])\n", " img = keras.utils.array_to_img(generated_images[i])\n",
" img.save(f\"generated_img_{epoch:03d}_{i}.png\")" " img.save(f\"generated_img_{epoch:03d}_{i}.png\")"
] ]
}, },