{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Chapter 13 – Loading and Preprocessing Data with TensorFlow**\n",
"\n",
"_This notebook contains all the sample code and solutions to the exercises in chapter 13._"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"
\n",
"
\n",
" \n",
"
\n",
"
\n",
" \n",
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Setup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, let's import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures. We also check that Python 3.5 or later is installed (although Python 2.x may work, it is deprecated so we strongly recommend you use Python 3 instead), as well as Scikit-Learn ≥0.20 and TensorFlow ≥2.0."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Python ≥3.5 is required\n",
"import sys\n",
"assert sys.version_info >= (3, 5)\n",
"\n",
"# Is this notebook running on Colab or Kaggle?\n",
"IS_COLAB = \"google.colab\" in sys.modules\n",
"IS_KAGGLE = \"kaggle_secrets\" in sys.modules\n",
"\n",
"if IS_COLAB or IS_KAGGLE:\n",
" %pip install -q -U tfx\n",
" print(\"You can safely ignore the package incompatibility errors.\")\n",
"\n",
"# Scikit-Learn ≥0.20 is required\n",
"import sklearn\n",
"assert sklearn.__version__ >= \"0.20\"\n",
"\n",
"# TensorFlow ≥2.0 is required\n",
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"assert tf.__version__ >= \"2.0\"\n",
"\n",
"# Common imports\n",
"import numpy as np\n",
"import os\n",
"\n",
"# to make this notebook's output stable across runs\n",
"np.random.seed(42)\n",
"\n",
"# To plot pretty figures\n",
"%matplotlib inline\n",
"import matplotlib as mpl\n",
"import matplotlib.pyplot as plt\n",
"mpl.rc('axes', labelsize=14)\n",
"mpl.rc('xtick', labelsize=12)\n",
"mpl.rc('ytick', labelsize=12)\n",
"\n",
"# Where to save the figures\n",
"PROJECT_ROOT_DIR = \".\"\n",
"CHAPTER_ID = \"data\"\n",
"IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID)\n",
"os.makedirs(IMAGES_PATH, exist_ok=True)\n",
"\n",
"def save_fig(fig_id, tight_layout=True, fig_extension=\"png\", resolution=300):\n",
" path = os.path.join(IMAGES_PATH, fig_id + \".\" + fig_extension)\n",
" print(\"Saving figure\", fig_id)\n",
" if tight_layout:\n",
" plt.tight_layout()\n",
" plt.savefig(path, format=fig_extension, dpi=resolution)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Datasets"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X = tf.range(10)\n",
"dataset = tf.data.Dataset.from_tensor_slices(X)\n",
"dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Equivalently:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"dataset = tf.data.Dataset.range(10)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(0, shape=(), dtype=int64)\n",
"tf.Tensor(1, shape=(), dtype=int64)\n",
"tf.Tensor(2, shape=(), dtype=int64)\n",
"tf.Tensor(3, shape=(), dtype=int64)\n",
"tf.Tensor(4, shape=(), dtype=int64)\n",
"tf.Tensor(5, shape=(), dtype=int64)\n",
"tf.Tensor(6, shape=(), dtype=int64)\n",
"tf.Tensor(7, shape=(), dtype=int64)\n",
"tf.Tensor(8, shape=(), dtype=int64)\n",
"tf.Tensor(9, shape=(), dtype=int64)\n"
]
}
],
"source": [
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"tags": [
"raises-exception"
]
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor([0 1 2 3 4 5 6], shape=(7,), dtype=int64)\n",
"tf.Tensor([7 8 9 0 1 2 3], shape=(7,), dtype=int64)\n",
"tf.Tensor([4 5 6 7 8 9 0], shape=(7,), dtype=int64)\n",
"tf.Tensor([1 2 3 4 5 6 7], shape=(7,), dtype=int64)\n",
"tf.Tensor([8 9], shape=(2,), dtype=int64)\n"
]
}
],
"source": [
"dataset = dataset.repeat(3).batch(7)\n",
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"dataset = dataset.map(lambda x: x * 2)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor([ 0 2 4 6 8 10 12], shape=(7,), dtype=int64)\n",
"tf.Tensor([14 16 18 0 2 4 6], shape=(7,), dtype=int64)\n",
"tf.Tensor([ 8 10 12 14 16 18 0], shape=(7,), dtype=int64)\n",
"tf.Tensor([ 2 4 6 8 10 12 14], shape=(7,), dtype=int64)\n",
"tf.Tensor([16 18], shape=(2,), dtype=int64)\n"
]
}
],
"source": [
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"#dataset = dataset.apply(tf.data.experimental.unbatch()) # Now deprecated\n",
"dataset = dataset.unbatch()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"dataset = dataset.filter(lambda x: x < 10) # keep only items < 10"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(0, shape=(), dtype=int64)\n",
"tf.Tensor(2, shape=(), dtype=int64)\n",
"tf.Tensor(4, shape=(), dtype=int64)\n"
]
}
],
"source": [
"for item in dataset.take(3):\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor([1 3 0 4 2 5 6], shape=(7,), dtype=int64)\n",
"tf.Tensor([8 7 1 0 3 2 5], shape=(7,), dtype=int64)\n",
"tf.Tensor([4 6 9 8 9 7 0], shape=(7,), dtype=int64)\n",
"tf.Tensor([3 1 4 5 2 8 7], shape=(7,), dtype=int64)\n",
"tf.Tensor([6 9], shape=(2,), dtype=int64)\n"
]
}
],
"source": [
"tf.random.set_seed(42)\n",
"\n",
"dataset = tf.data.Dataset.range(10).repeat(3)\n",
"dataset = dataset.shuffle(buffer_size=3, seed=42).batch(7)\n",
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Split the California dataset to multiple CSV files"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's start by loading and preparing the California housing dataset. We first load it, then split it into a training set, a validation set and a test set, and finally we scale it:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.datasets import fetch_california_housing\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"housing = fetch_california_housing()\n",
"X_train_full, X_test, y_train_full, y_test = train_test_split(\n",
" housing.data, housing.target.reshape(-1, 1), random_state=42)\n",
"X_train, X_valid, y_train, y_valid = train_test_split(\n",
" X_train_full, y_train_full, random_state=42)\n",
"\n",
"scaler = StandardScaler()\n",
"scaler.fit(X_train)\n",
"X_mean = scaler.mean_\n",
"X_std = scaler.scale_"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For a very large dataset that does not fit in memory, you will typically want to split it into many files first, then have TensorFlow read these files in parallel. To demonstrate this, let's start by splitting the housing dataset and save it to 20 CSV files:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"def save_to_multiple_csv_files(data, name_prefix, header=None, n_parts=10):\n",
" housing_dir = os.path.join(\"datasets\", \"housing\")\n",
" os.makedirs(housing_dir, exist_ok=True)\n",
" path_format = os.path.join(housing_dir, \"my_{}_{:02d}.csv\")\n",
"\n",
" filepaths = []\n",
" m = len(data)\n",
" for file_idx, row_indices in enumerate(np.array_split(np.arange(m), n_parts)):\n",
" part_csv = path_format.format(name_prefix, file_idx)\n",
" filepaths.append(part_csv)\n",
" with open(part_csv, \"wt\", encoding=\"utf-8\") as f:\n",
" if header is not None:\n",
" f.write(header)\n",
" f.write(\"\\n\")\n",
" for row_idx in row_indices:\n",
" f.write(\",\".join([repr(col) for col in data[row_idx]]))\n",
" f.write(\"\\n\")\n",
" return filepaths"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"train_data = np.c_[X_train, y_train]\n",
"valid_data = np.c_[X_valid, y_valid]\n",
"test_data = np.c_[X_test, y_test]\n",
"header_cols = housing.feature_names + [\"MedianHouseValue\"]\n",
"header = \",\".join(header_cols)\n",
"\n",
"train_filepaths = save_to_multiple_csv_files(train_data, \"train\", header, n_parts=20)\n",
"valid_filepaths = save_to_multiple_csv_files(valid_data, \"valid\", header, n_parts=10)\n",
"test_filepaths = save_to_multiple_csv_files(test_data, \"test\", header, n_parts=10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Okay, now let's take a peek at the first few lines of one of these CSV files:"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
MedInc
\n",
"
HouseAge
\n",
"
AveRooms
\n",
"
AveBedrms
\n",
"
Population
\n",
"
AveOccup
\n",
"
Latitude
\n",
"
Longitude
\n",
"
MedianHouseValue
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
3.5214
\n",
"
15.0
\n",
"
3.049945
\n",
"
1.106548
\n",
"
1447.0
\n",
"
1.605993
\n",
"
37.63
\n",
"
-122.43
\n",
"
1.442
\n",
"
\n",
"
\n",
"
1
\n",
"
5.3275
\n",
"
5.0
\n",
"
6.490060
\n",
"
0.991054
\n",
"
3464.0
\n",
"
3.443340
\n",
"
33.69
\n",
"
-117.39
\n",
"
1.687
\n",
"
\n",
"
\n",
"
2
\n",
"
3.1000
\n",
"
29.0
\n",
"
7.542373
\n",
"
1.591525
\n",
"
1328.0
\n",
"
2.250847
\n",
"
38.44
\n",
"
-122.98
\n",
"
1.621
\n",
"
\n",
"
\n",
"
3
\n",
"
7.1736
\n",
"
12.0
\n",
"
6.289003
\n",
"
0.997442
\n",
"
1054.0
\n",
"
2.695652
\n",
"
33.55
\n",
"
-117.70
\n",
"
2.621
\n",
"
\n",
"
\n",
"
4
\n",
"
2.0549
\n",
"
13.0
\n",
"
5.312457
\n",
"
1.085092
\n",
"
3297.0
\n",
"
2.244384
\n",
"
33.93
\n",
"
-116.93
\n",
"
0.956
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" MedInc HouseAge AveRooms AveBedrms Population AveOccup Latitude \\\n",
"0 3.5214 15.0 3.049945 1.106548 1447.0 1.605993 37.63 \n",
"1 5.3275 5.0 6.490060 0.991054 3464.0 3.443340 33.69 \n",
"2 3.1000 29.0 7.542373 1.591525 1328.0 2.250847 38.44 \n",
"3 7.1736 12.0 6.289003 0.997442 1054.0 2.695652 33.55 \n",
"4 2.0549 13.0 5.312457 1.085092 3297.0 2.244384 33.93 \n",
"\n",
" Longitude MedianHouseValue \n",
"0 -122.43 1.442 \n",
"1 -117.39 1.687 \n",
"2 -122.98 1.621 \n",
"3 -117.70 2.621 \n",
"4 -116.93 0.956 "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"pd.read_csv(train_filepaths[0]).head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Or in text mode:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"MedInc,HouseAge,AveRooms,AveBedrms,Population,AveOccup,Latitude,Longitude,MedianHouseValue\n",
"3.5214,15.0,3.0499445061043287,1.106548279689234,1447.0,1.6059933407325193,37.63,-122.43,1.442\n",
"5.3275,5.0,6.490059642147117,0.9910536779324056,3464.0,3.4433399602385686,33.69,-117.39,1.687\n",
"3.1,29.0,7.5423728813559325,1.5915254237288134,1328.0,2.2508474576271187,38.44,-122.98,1.621\n",
"7.1736,12.0,6.289002557544757,0.9974424552429667,1054.0,2.6956521739130435,33.55,-117.7,2.621\n"
]
}
],
"source": [
"with open(train_filepaths[0]) as f:\n",
" for i in range(5):\n",
" print(f.readline(), end=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['datasets/housing/my_train_00.csv',\n",
" 'datasets/housing/my_train_01.csv',\n",
" 'datasets/housing/my_train_02.csv',\n",
" 'datasets/housing/my_train_03.csv',\n",
" 'datasets/housing/my_train_04.csv',\n",
" 'datasets/housing/my_train_05.csv',\n",
" 'datasets/housing/my_train_06.csv',\n",
" 'datasets/housing/my_train_07.csv',\n",
" 'datasets/housing/my_train_08.csv',\n",
" 'datasets/housing/my_train_09.csv',\n",
" 'datasets/housing/my_train_10.csv',\n",
" 'datasets/housing/my_train_11.csv',\n",
" 'datasets/housing/my_train_12.csv',\n",
" 'datasets/housing/my_train_13.csv',\n",
" 'datasets/housing/my_train_14.csv',\n",
" 'datasets/housing/my_train_15.csv',\n",
" 'datasets/housing/my_train_16.csv',\n",
" 'datasets/housing/my_train_17.csv',\n",
" 'datasets/housing/my_train_18.csv',\n",
" 'datasets/housing/my_train_19.csv']"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_filepaths"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Building an Input Pipeline"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"filepath_dataset = tf.data.Dataset.list_files(train_filepaths, seed=42)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(b'datasets/housing/my_train_15.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_08.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_03.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_01.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_10.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_05.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_19.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_16.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_02.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_09.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_00.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_07.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_12.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_04.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_17.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_11.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_14.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_18.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_06.csv', shape=(), dtype=string)\n",
"tf.Tensor(b'datasets/housing/my_train_13.csv', shape=(), dtype=string)\n"
]
}
],
"source": [
"for filepath in filepath_dataset:\n",
" print(filepath)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"n_readers = 5\n",
"dataset = filepath_dataset.interleave(\n",
" lambda filepath: tf.data.TextLineDataset(filepath).skip(1),\n",
" cycle_length=n_readers)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"b'4.6477,38.0,5.03728813559322,0.911864406779661,745.0,2.5254237288135593,32.64,-117.07,1.504'\n",
"b'8.72,44.0,6.163179916317992,1.0460251046025104,668.0,2.794979079497908,34.2,-118.18,4.159'\n",
"b'3.8456,35.0,5.461346633416459,0.9576059850374065,1154.0,2.8778054862842892,37.96,-122.05,1.598'\n",
"b'3.3456,37.0,4.514084507042254,0.9084507042253521,458.0,3.2253521126760565,36.67,-121.7,2.526'\n",
"b'3.6875,44.0,4.524475524475524,0.993006993006993,457.0,3.195804195804196,34.04,-118.15,1.625'\n"
]
}
],
"source": [
"for line in dataset.take(5):\n",
" print(line.numpy())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Notice that field 4 is interpreted as a string."
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[,\n",
" ,\n",
" ,\n",
" ,\n",
" ]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"record_defaults=[0, np.nan, tf.constant(np.nan, dtype=tf.float64), \"Hello\", tf.constant([])]\n",
"parsed_fields = tf.io.decode_csv('1,2,3,4,5', record_defaults)\n",
"parsed_fields"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Notice that all missing fields are replaced with their default value, when provided:"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[,\n",
" ,\n",
" ,\n",
" ,\n",
" ]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parsed_fields = tf.io.decode_csv(',,,,5', record_defaults)\n",
"parsed_fields"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The 5th field is compulsory (since we provided `tf.constant([])` as the \"default value\"), so we get an exception if we do not provide it:"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Field 4 is required but missing in record 0! [Op:DecodeCSV]\n"
]
}
],
"source": [
"try:\n",
" parsed_fields = tf.io.decode_csv(',,,,', record_defaults)\n",
"except tf.errors.InvalidArgumentError as ex:\n",
" print(ex)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The number of fields should match exactly the number of fields in the `record_defaults`:"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Expect 5 fields but have 7 in record 0 [Op:DecodeCSV]\n"
]
}
],
"source": [
"try:\n",
" parsed_fields = tf.io.decode_csv('1,2,3,4,5,6,7', record_defaults)\n",
"except tf.errors.InvalidArgumentError as ex:\n",
" print(ex)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"n_inputs = 8 # X_train.shape[-1]\n",
"\n",
"@tf.function\n",
"def preprocess(line):\n",
" defs = [0.] * n_inputs + [tf.constant([], dtype=tf.float32)]\n",
" fields = tf.io.decode_csv(line, record_defaults=defs)\n",
" x = tf.stack(fields[:-1])\n",
" y = tf.stack(fields[-1:])\n",
" return (x - X_mean) / X_std, y"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(,\n",
" )"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"preprocess(b'4.2083,44.0,5.3232,0.9171,846.0,2.3370,37.47,-122.2,2.782')"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"def csv_reader_dataset(filepaths, repeat=1, n_readers=5,\n",
" n_read_threads=None, shuffle_buffer_size=10000,\n",
" n_parse_threads=5, batch_size=32):\n",
" dataset = tf.data.Dataset.list_files(filepaths).repeat(repeat)\n",
" dataset = dataset.interleave(\n",
" lambda filepath: tf.data.TextLineDataset(filepath).skip(1),\n",
" cycle_length=n_readers, num_parallel_calls=n_read_threads)\n",
" dataset = dataset.shuffle(shuffle_buffer_size)\n",
" dataset = dataset.map(preprocess, num_parallel_calls=n_parse_threads)\n",
" dataset = dataset.batch(batch_size)\n",
" return dataset.prefetch(1)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"X = tf.Tensor(\n",
"[[ 0.5804519 -0.20762321 0.05616303 -0.15191229 0.01343246 0.00604472\n",
" 1.2525111 -1.3671792 ]\n",
" [ 5.818099 1.8491895 1.1784915 0.28173092 -1.2496178 -0.3571987\n",
" 0.7231292 -1.0023477 ]\n",
" [-0.9253566 0.5834586 -0.7807257 -0.28213993 -0.36530012 0.27389365\n",
" -0.76194876 0.72684526]], shape=(3, 8), dtype=float32)\n",
"y = tf.Tensor(\n",
"[[1.752]\n",
" [1.313]\n",
" [1.535]], shape=(3, 1), dtype=float32)\n",
"\n",
"X = tf.Tensor(\n",
"[[-0.8324941 0.6625668 -0.20741376 -0.18699841 -0.14536144 0.09635526\n",
" 0.9807942 -0.67250353]\n",
" [-0.62183803 0.5834586 -0.19862501 -0.3500319 -1.1437552 -0.3363751\n",
" 1.107282 -0.8674123 ]\n",
" [ 0.8683102 0.02970133 0.3427381 -0.29872298 0.7124906 0.28026953\n",
" -0.72915536 0.86178064]], shape=(3, 8), dtype=float32)\n",
"y = tf.Tensor(\n",
"[[0.919]\n",
" [1.028]\n",
" [2.182]], shape=(3, 1), dtype=float32)\n",
"\n"
]
}
],
"source": [
"tf.random.set_seed(42)\n",
"\n",
"train_set = csv_reader_dataset(train_filepaths, batch_size=3)\n",
"for X_batch, y_batch in train_set.take(2):\n",
" print(\"X =\", X_batch)\n",
" print(\"y =\", y_batch)\n",
" print()"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"train_set = csv_reader_dataset(train_filepaths, repeat=None)\n",
"valid_set = csv_reader_dataset(valid_filepaths)\n",
"test_set = csv_reader_dataset(test_filepaths)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"keras.backend.clear_session()\n",
"np.random.seed(42)\n",
"tf.random.set_seed(42)\n",
"\n",
"model = keras.models.Sequential([\n",
" keras.layers.Dense(30, activation=\"relu\", input_shape=X_train.shape[1:]),\n",
" keras.layers.Dense(1),\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n",
"362/362 [==============================] - 1s 3ms/step - loss: 2.0914 - val_loss: 21.5124\n",
"Epoch 2/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.8428 - val_loss: 0.6648\n",
"Epoch 3/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.6329 - val_loss: 0.6196\n",
"Epoch 4/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.5922 - val_loss: 0.5669\n",
"Epoch 5/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.5622 - val_loss: 0.5402\n",
"Epoch 6/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.5698 - val_loss: 0.5209\n",
"Epoch 7/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.5195 - val_loss: 0.6130\n",
"Epoch 8/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.5155 - val_loss: 0.4818\n",
"Epoch 9/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.4965 - val_loss: 0.4904\n",
"Epoch 10/10\n",
"362/362 [==============================] - 0s 1ms/step - loss: 0.4925 - val_loss: 0.4585\n"
]
},
{
"data": {
"text/plain": [
""
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"batch_size = 32\n",
"model.fit(train_set, steps_per_epoch=len(X_train) // batch_size, epochs=10,\n",
" validation_data=valid_set)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"161/161 [==============================] - 0s 589us/step - loss: 0.4788\n"
]
},
{
"data": {
"text/plain": [
"0.4787752032279968"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.evaluate(test_set, steps=len(X_test) // batch_size)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[2.3576407],\n",
" [2.255291 ],\n",
" [1.4437605],\n",
" ...,\n",
" [0.5654393],\n",
" [3.9442453],\n",
" [1.0232248]], dtype=float32)"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_set = test_set.map(lambda X, y: X) # we could instead just pass test_set, Keras would ignore the labels\n",
"X_new = X_test\n",
"model.predict(new_set, steps=len(X_new) // batch_size)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Global step 1810/1810"
]
}
],
"source": [
"optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n",
"loss_fn = keras.losses.mean_squared_error\n",
"\n",
"n_epochs = 5\n",
"batch_size = 32\n",
"n_steps_per_epoch = len(X_train) // batch_size\n",
"total_steps = n_epochs * n_steps_per_epoch\n",
"global_step = 0\n",
"for X_batch, y_batch in train_set.take(total_steps):\n",
" global_step += 1\n",
" print(\"\\rGlobal step {}/{}\".format(global_step, total_steps), end=\"\")\n",
" with tf.GradientTape() as tape:\n",
" y_pred = model(X_batch)\n",
" main_loss = tf.reduce_mean(loss_fn(y_batch, y_pred))\n",
" loss = tf.add_n([main_loss] + model.losses)\n",
" gradients = tape.gradient(loss, model.trainable_variables)\n",
" optimizer.apply_gradients(zip(gradients, model.trainable_variables))"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"keras.backend.clear_session()\n",
"np.random.seed(42)\n",
"tf.random.set_seed(42)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n",
"loss_fn = keras.losses.mean_squared_error\n",
"\n",
"@tf.function\n",
"def train(model, n_epochs, batch_size=32,\n",
" n_readers=5, n_read_threads=5, shuffle_buffer_size=10000, n_parse_threads=5):\n",
" train_set = csv_reader_dataset(train_filepaths, repeat=n_epochs, n_readers=n_readers,\n",
" n_read_threads=n_read_threads, shuffle_buffer_size=shuffle_buffer_size,\n",
" n_parse_threads=n_parse_threads, batch_size=batch_size)\n",
" for X_batch, y_batch in train_set:\n",
" with tf.GradientTape() as tape:\n",
" y_pred = model(X_batch)\n",
" main_loss = tf.reduce_mean(loss_fn(y_batch, y_pred))\n",
" loss = tf.add_n([main_loss] + model.losses)\n",
" gradients = tape.gradient(loss, model.trainable_variables)\n",
" optimizer.apply_gradients(zip(gradients, model.trainable_variables))\n",
"\n",
"train(model, 5)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"keras.backend.clear_session()\n",
"np.random.seed(42)\n",
"tf.random.set_seed(42)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Global step 100 / 1810\n",
"Global step 200 / 1810\n",
"Global step 300 / 1810\n",
"Global step 400 / 1810\n",
"Global step 500 / 1810\n",
"Global step 600 / 1810\n",
"Global step 700 / 1810\n",
"Global step 800 / 1810\n",
"Global step 900 / 1810\n",
"Global step 1000 / 1810\n",
"Global step 1100 / 1810\n",
"Global step 1200 / 1810\n",
"Global step 1300 / 1810\n",
"Global step 1400 / 1810\n",
"Global step 1500 / 1810\n",
"Global step 1600 / 1810\n",
"Global step 1700 / 1810\n",
"Global step 1800 / 1810\n"
]
}
],
"source": [
"optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n",
"loss_fn = keras.losses.mean_squared_error\n",
"\n",
"@tf.function\n",
"def train(model, n_epochs, batch_size=32,\n",
" n_readers=5, n_read_threads=5, shuffle_buffer_size=10000, n_parse_threads=5):\n",
" train_set = csv_reader_dataset(train_filepaths, repeat=n_epochs, n_readers=n_readers,\n",
" n_read_threads=n_read_threads, shuffle_buffer_size=shuffle_buffer_size,\n",
" n_parse_threads=n_parse_threads, batch_size=batch_size)\n",
" n_steps_per_epoch = len(X_train) // batch_size\n",
" total_steps = n_epochs * n_steps_per_epoch\n",
" global_step = 0\n",
" for X_batch, y_batch in train_set.take(total_steps):\n",
" global_step += 1\n",
" if tf.equal(global_step % 100, 0):\n",
" tf.print(\"\\rGlobal step\", global_step, \"/\", total_steps)\n",
" with tf.GradientTape() as tape:\n",
" y_pred = model(X_batch)\n",
" main_loss = tf.reduce_mean(loss_fn(y_batch, y_pred))\n",
" loss = tf.add_n([main_loss] + model.losses)\n",
" gradients = tape.gradient(loss, model.trainable_variables)\n",
" optimizer.apply_gradients(zip(gradients, model.trainable_variables))\n",
"\n",
"train(model, 5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here is a short description of each method in the `Dataset` class:"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"● apply() Applies a transformation function to this dataset.\n",
"● as_numpy_iterator() Returns an iterator which converts all elements of the dataset to numpy.\n",
"● batch() Combines consecutive elements of this dataset into batches.\n",
"● cache() Caches the elements in this dataset.\n",
"● cardinality() Returns the cardinality of the dataset, if known.\n",
"● concatenate() Creates a `Dataset` by concatenating the given dataset with this dataset.\n",
"● element_spec() The type specification of an element of this dataset.\n",
"● enumerate() Enumerates the elements of this dataset.\n",
"● filter() Filters this dataset according to `predicate`.\n",
"● flat_map() Maps `map_func` across this dataset and flattens the result.\n",
"● from_generator() Creates a `Dataset` whose elements are generated by `generator`. (deprecated arguments)\n",
"● from_tensor_slices() Creates a `Dataset` whose elements are slices of the given tensors.\n",
"● from_tensors() Creates a `Dataset` with a single element, comprising the given tensors.\n",
"● interleave() Maps `map_func` across this dataset, and interleaves the results.\n",
"● list_files() A dataset of all files matching one or more glob patterns.\n",
"● map() Maps `map_func` across the elements of this dataset.\n",
"● options() Returns the options for this dataset and its inputs.\n",
"● padded_batch() Combines consecutive elements of this dataset into padded batches.\n",
"● prefetch() Creates a `Dataset` that prefetches elements from this dataset.\n",
"● range() Creates a `Dataset` of a step-separated range of values.\n",
"● reduce() Reduces the input dataset to a single element.\n",
"● repeat() Repeats this dataset so each original value is seen `count` times.\n",
"● shard() Creates a `Dataset` that includes only 1/`num_shards` of this dataset.\n",
"● shuffle() Randomly shuffles the elements of this dataset.\n",
"● skip() Creates a `Dataset` that skips `count` elements from this dataset.\n",
"● take() Creates a `Dataset` with at most `count` elements from this dataset.\n",
"● unbatch() Splits elements of a dataset into multiple elements.\n",
"● window() Combines (nests of) input elements into a dataset of (nests of) windows.\n",
"● with_options() Returns a new `tf.data.Dataset` with the given options set.\n",
"● zip() Creates a `Dataset` by zipping together the given datasets.\n"
]
}
],
"source": [
"for m in dir(tf.data.Dataset):\n",
" if not (m.startswith(\"_\") or m.endswith(\"_\")):\n",
" func = getattr(tf.data.Dataset, m)\n",
" if hasattr(func, \"__doc__\"):\n",
" print(\"● {:21s}{}\".format(m + \"()\", func.__doc__.split(\"\\n\")[0]))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## The `TFRecord` binary format"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A TFRecord file is just a list of binary records. You can create one using a `tf.io.TFRecordWriter`:"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"with tf.io.TFRecordWriter(\"my_data.tfrecord\") as f:\n",
" f.write(b\"This is the first record\")\n",
" f.write(b\"And this is the second record\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And you can read it using a `tf.data.TFRecordDataset`:"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(b'This is the first record', shape=(), dtype=string)\n",
"tf.Tensor(b'And this is the second record', shape=(), dtype=string)\n"
]
}
],
"source": [
"filepaths = [\"my_data.tfrecord\"]\n",
"dataset = tf.data.TFRecordDataset(filepaths)\n",
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can read multiple TFRecord files with just one `TFRecordDataset`. By default it will read them one at a time, but if you set `num_parallel_reads=3`, it will read 3 at a time in parallel and interleave their records:"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(b'File 0 record 0', shape=(), dtype=string)\n",
"tf.Tensor(b'File 1 record 0', shape=(), dtype=string)\n",
"tf.Tensor(b'File 2 record 0', shape=(), dtype=string)\n",
"tf.Tensor(b'File 0 record 1', shape=(), dtype=string)\n",
"tf.Tensor(b'File 1 record 1', shape=(), dtype=string)\n",
"tf.Tensor(b'File 2 record 1', shape=(), dtype=string)\n",
"tf.Tensor(b'File 0 record 2', shape=(), dtype=string)\n",
"tf.Tensor(b'File 1 record 2', shape=(), dtype=string)\n",
"tf.Tensor(b'File 2 record 2', shape=(), dtype=string)\n",
"tf.Tensor(b'File 3 record 0', shape=(), dtype=string)\n",
"tf.Tensor(b'File 4 record 0', shape=(), dtype=string)\n",
"tf.Tensor(b'File 3 record 1', shape=(), dtype=string)\n",
"tf.Tensor(b'File 4 record 1', shape=(), dtype=string)\n",
"tf.Tensor(b'File 3 record 2', shape=(), dtype=string)\n",
"tf.Tensor(b'File 4 record 2', shape=(), dtype=string)\n"
]
}
],
"source": [
"filepaths = [\"my_test_{}.tfrecord\".format(i) for i in range(5)]\n",
"for i, filepath in enumerate(filepaths):\n",
" with tf.io.TFRecordWriter(filepath) as f:\n",
" for j in range(3):\n",
" f.write(\"File {} record {}\".format(i, j).encode(\"utf-8\"))\n",
"\n",
"dataset = tf.data.TFRecordDataset(filepaths, num_parallel_reads=3)\n",
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"options = tf.io.TFRecordOptions(compression_type=\"GZIP\")\n",
"with tf.io.TFRecordWriter(\"my_compressed.tfrecord\", options) as f:\n",
" f.write(b\"This is the first record\")\n",
" f.write(b\"And this is the second record\")"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tf.Tensor(b'This is the first record', shape=(), dtype=string)\n",
"tf.Tensor(b'And this is the second record', shape=(), dtype=string)\n"
]
}
],
"source": [
"dataset = tf.data.TFRecordDataset([\"my_compressed.tfrecord\"],\n",
" compression_type=\"GZIP\")\n",
"for item in dataset:\n",
" print(item)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### A Brief Intro to Protocol Buffers"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For this section you need to [install protobuf](https://developers.google.com/protocol-buffers/docs/downloads). In general you will not have to do so when using TensorFlow, as it comes with functions to create and parse protocol buffers of type `tf.train.Example`, which are generally sufficient. However, in this section we will learn about protocol buffers by creating our own simple protobuf definition, so we need the protobuf compiler (`protoc`): we will use it to compile the protobuf definition to a Python module that we can then use in our code."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First let's write a simple protobuf definition:"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Overwriting person.proto\n"
]
}
],
"source": [
"%%writefile person.proto\n",
"syntax = \"proto3\";\n",
"message Person {\n",
" string name = 1;\n",
" int32 id = 2;\n",
" repeated string email = 3;\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And let's compile it (the `--descriptor_set_out` and `--include_imports` options are only required for the `tf.io.decode_proto()` example below):"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"!protoc person.proto --python_out=. --descriptor_set_out=person.desc --include_imports"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"person.desc person.proto person_pb2.py\n"
]
}
],
"source": [
"!ls person*"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"name: \"Al\"\n",
"id: 123\n",
"email: \"a@b.com\"\n",
"\n"
]
}
],
"source": [
"from person_pb2 import Person\n",
"\n",
"person = Person(name=\"Al\", id=123, email=[\"a@b.com\"]) # create a Person\n",
"print(person) # display the Person"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Al'"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"person.name # read a field"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"person.name = \"Alice\" # modify a field"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'a@b.com'"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"person.email[0] # repeated fields can be accessed like arrays"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
"person.email.append(\"c@d.com\") # add an email address"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"b'\\n\\x05Alice\\x10{\\x1a\\x07a@b.com\\x1a\\x07c@d.com'"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s = person.SerializeToString() # serialize to a byte string\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"27"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"person2 = Person() # create a new Person\n",
"person2.ParseFromString(s) # parse the byte string (27 bytes)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"person == person2 # now they are equal"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Custom protobuf"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In rare cases, you may want to parse a custom protobuf (like the one we just created) in TensorFlow. For this you can use the `tf.io.decode_proto()` function:"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[,\n",
" ,\n",
" ]"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"person_tf = tf.io.decode_proto(\n",
" bytes=s,\n",
" message_type=\"Person\",\n",
" field_names=[\"name\", \"id\", \"email\"],\n",
" output_types=[tf.string, tf.int32, tf.string],\n",
" descriptor_source=\"person.desc\")\n",
"\n",
"person_tf.values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For more details, see the [`tf.io.decode_proto()`](https://www.tensorflow.org/api_docs/python/tf/io/decode_proto) documentation."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### TensorFlow Protobufs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here is the definition of the tf.train.Example protobuf:"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"```proto\n",
"syntax = \"proto3\";\n",
"\n",
"message BytesList { repeated bytes value = 1; }\n",
"message FloatList { repeated float value = 1 [packed = true]; }\n",
"message Int64List { repeated int64 value = 1 [packed = true]; }\n",
"message Feature {\n",
" oneof kind {\n",
" BytesList bytes_list = 1;\n",
" FloatList float_list = 2;\n",
" Int64List int64_list = 3;\n",
" }\n",
"};\n",
"message Features { map feature = 1; };\n",
"message Example { Features features = 1; };\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Warning**: in TensorFlow 2.0 and 2.1, there was a bug preventing `from tensorflow.train import X` so we work around it by writing `X = tf.train.X`. See https://github.com/tensorflow/tensorflow/issues/33289 for more details."
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": [
"#from tensorflow.train import BytesList, FloatList, Int64List\n",
"#from tensorflow.train import Feature, Features, Example\n",
"BytesList = tf.train.BytesList\n",
"FloatList = tf.train.FloatList\n",
"Int64List = tf.train.Int64List\n",
"Feature = tf.train.Feature\n",
"Features = tf.train.Features\n",
"Example = tf.train.Example\n",
"\n",
"person_example = Example(\n",
" features=Features(\n",
" feature={\n",
" \"name\": Feature(bytes_list=BytesList(value=[b\"Alice\"])),\n",
" \"id\": Feature(int64_list=Int64List(value=[123])),\n",
" \"emails\": Feature(bytes_list=BytesList(value=[b\"a@b.com\", b\"c@d.com\"]))\n",
" }))\n",
"\n",
"with tf.io.TFRecordWriter(\"my_contacts.tfrecord\") as f:\n",
" f.write(person_example.SerializeToString())"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [],
"source": [
"feature_description = {\n",
" \"name\": tf.io.FixedLenFeature([], tf.string, default_value=\"\"),\n",
" \"id\": tf.io.FixedLenFeature([], tf.int64, default_value=0),\n",
" \"emails\": tf.io.VarLenFeature(tf.string),\n",
"}\n",
"for serialized_example in tf.data.TFRecordDataset([\"my_contacts.tfrecord\"]):\n",
" parsed_example = tf.io.parse_single_example(serialized_example,\n",
" feature_description)"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'emails': ,\n",
" 'id': ,\n",
" 'name': }"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parsed_example"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"{'emails': ,\n",
" 'id': ,\n",
" 'name': }"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parsed_example"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parsed_example[\"emails\"].values[0]"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tf.sparse.to_dense(parsed_example[\"emails\"], default_value=b\"\")"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parsed_example[\"emails\"].values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Putting Images in TFRecords"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"