 Lihat di TensorFlow.org |  Jalankan di Google Colab |  Lihat sumber di GitHub |  Unduh buku catatan |
Tutorial ini menunjukkan dua cara untuk memuat dan memproses teks sebelumnya.
- Pertama, Anda akan menggunakan utilitas Keras dan lapisan preprocessing. Ini termasuk
tf.keras.utils.text_dataset_from_directoryuntuk mengubah data menjaditf.data.Datasetdantf.keras.layers.TextVectorizationuntuk standarisasi data, tokenisasi, dan vektorisasi. Jika Anda baru mengenal TensorFlow, Anda harus mulai dengan ini. - Kemudian, Anda akan menggunakan utilitas tingkat yang lebih rendah seperti
tf.data.TextLineDatasetuntuk memuat file teks, dan TensorFlow Text API, sepertitext.UnicodeScriptTokenizerdantext.case_fold_utf8, untuk melakukan praproses data untuk kontrol butir yang lebih halus.
# Be sure you're using the stable versions of both `tensorflow` and# `tensorflow-text`, for binary compatibility.pip uninstall -y tf-nightly keras-nightlypip install tensorflowpip install tensorflow-text
import collections
import pathlib
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import losses
from tensorflow.keras import utils
from tensorflow.keras.layers import TextVectorization
import tensorflow_datasets as tfds
import tensorflow_text as tf_text
Contoh 1: Prediksi tag untuk pertanyaan Stack Overflow
Sebagai contoh pertama, Anda akan mengunduh kumpulan data pertanyaan pemrograman dari Stack Overflow. Setiap pertanyaan ( "Bagaimana cara mengurutkan kamus berdasarkan nilai?" ) diberi label dengan tepat satu tag ( Python , CSharp , JavaScript , atau Java ). Tugas Anda adalah mengembangkan model yang memprediksi tag untuk sebuah pertanyaan. Ini adalah contoh klasifikasi multi-kelas—jenis masalah pembelajaran mesin yang penting dan dapat diterapkan secara luas.
Unduh dan jelajahi kumpulan data
Mulailah dengan mengunduh kumpulan data Stack Overflow menggunakan tf.keras.utils.get_file , dan menjelajahi struktur direktori:
data_url = 'https://storage.googleapis.com/download.tensorflow.org/data/stack_overflow_16k.tar.gz'
dataset_dir = utils.get_file(
origin=data_url,
untar=True,
cache_dir='stack_overflow',
cache_subdir='')
dataset_dir = pathlib.Path(dataset_dir).parent
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/stack_overflow_16k.tar.gz 6053888/6053168 [==============================] - 0s 0us/step 6062080/6053168 [==============================] - 0s 0us/step
list(dataset_dir.iterdir())
[PosixPath('/tmp/.keras/train'),
PosixPath('/tmp/.keras/README.md'),
PosixPath('/tmp/.keras/stack_overflow_16k.tar.gz'),
PosixPath('/tmp/.keras/test')]
train_dir = dataset_dir/'train'
list(train_dir.iterdir())
[PosixPath('/tmp/.keras/train/java'),
PosixPath('/tmp/.keras/train/csharp'),
PosixPath('/tmp/.keras/train/javascript'),
PosixPath('/tmp/.keras/train/python')]
Direktori train/csharp , train/java , train/python dan train/javascript berisi banyak file teks, yang masing-masing merupakan pertanyaan Stack Overflow.
Cetak file contoh dan periksa datanya:
sample_file = train_dir/'python/1755.txt'
with open(sample_file) as f:
print(f.read())
why does this blank program print true x=true.def stupid():. x=false.stupid().print x
Muat kumpulan data
Selanjutnya, Anda akan memuat data dari disk dan menyiapkannya ke dalam format yang sesuai untuk pelatihan. Untuk melakukannya, Anda akan menggunakan utilitas tf.keras.utils.text_dataset_from_directory untuk membuat tf.data.Dataset berlabel. Jika Anda baru tf.data , ini adalah kumpulan alat yang ampuh untuk membangun saluran input. (Pelajari lebih lanjut di tf.data: Membangun panduan pipeline input TensorFlow .)
tf.keras.utils.text_dataset_from_directory API mengharapkan struktur direktori sebagai berikut:
train/
...csharp/
......1.txt
......2.txt
...java/
......1.txt
......2.txt
...javascript/
......1.txt
......2.txt
...python/
......1.txt
......2.txt
Saat menjalankan eksperimen pembelajaran mesin, praktik terbaik adalah membagi set data Anda menjadi tiga bagian: pelatihan , validasi , dan pengujian .
Set data Stack Overflow telah dibagi menjadi set pelatihan dan pengujian, tetapi tidak memiliki set validasi.
Buat set validasi menggunakan pemisahan 80:20 dari data pelatihan dengan menggunakan tf.keras.utils.text_dataset_from_directory dengan validation_split disetel ke 0.2 (yaitu 20%):
batch_size = 32
seed = 42
raw_train_ds = utils.text_dataset_from_directory(
train_dir,
batch_size=batch_size,
validation_split=0.2,
subset='training',
seed=seed)
Found 8000 files belonging to 4 classes. Using 6400 files for training.
Seperti yang disarankan oleh keluaran sel sebelumnya, ada 8.000 contoh di folder pelatihan, di mana Anda akan menggunakan 80% (atau 6.400) untuk pelatihan. Anda akan segera mengetahui bahwa Anda dapat melatih model dengan meneruskan tf.data.Dataset langsung ke Model.fit .
Pertama, ulangi dataset dan cetak beberapa contoh, untuk merasakan datanya.
for text_batch, label_batch in raw_train_ds.take(1):
for i in range(10):
print("Question: ", text_batch.numpy()[i])
print("Label:", label_batch.numpy()[i])
Question: b'"my tester is going to the wrong constructor i am new to programming so if i ask a question that can be easily fixed, please forgive me. my program has a tester class with a main. when i send that to my regularpolygon class, it sends it to the wrong constructor. i have two constructors. 1 without perameters..public regularpolygon(). {. mynumsides = 5;. mysidelength = 30;. }//end default constructor...and my second, with perameters. ..public regularpolygon(int numsides, double sidelength). {. mynumsides = numsides;. mysidelength = sidelength;. }// end constructor...in my tester class i have these two lines:..regularpolygon shape = new regularpolygon(numsides, sidelength);. shape.menu();...numsides and sidelength were declared and initialized earlier in the testing class...so what i want to happen, is the tester class sends numsides and sidelength to the second constructor and use it in that class. but it only uses the default constructor, which therefor ruins the whole rest of the program. can somebody help me?..for those of you who want to see more of my code: here you go..public double vertexangle(). {. system.out.println(""the vertex angle method: "" + mynumsides);// prints out 5. system.out.println(""the vertex angle method: "" + mysidelength); // prints out 30.. double vertexangle;. vertexangle = ((mynumsides - 2.0) / mynumsides) * 180.0;. return vertexangle;. }//end method vertexangle..public void menu().{. system.out.println(mynumsides); // prints out what the user puts in. system.out.println(mysidelength); // prints out what the user puts in. gotographic();. calcr(mynumsides, mysidelength);. calcr(mynumsides, mysidelength);. print(); .}// end menu...this is my entire tester class:..public static void main(string[] arg).{. int numsides;. double sidelength;. scanner keyboard = new scanner(system.in);.. system.out.println(""welcome to the regular polygon program!"");. system.out.println();.. system.out.print(""enter the number of sides of the polygon ==> "");. numsides = keyboard.nextint();. system.out.println();.. system.out.print(""enter the side length of each side ==> "");. sidelength = keyboard.nextdouble();. system.out.println();.. regularpolygon shape = new regularpolygon(numsides, sidelength);. shape.menu();.}//end main...for testing it i sent it numsides 4 and sidelength 100."\n'
Label: 1
Question: b'"blank code slow skin detection this code changes the color space to lab and using a threshold finds the skin area of an image. but it\'s ridiculously slow. i don\'t know how to make it faster ? ..from colormath.color_objects import *..def skindetection(img, treshold=80, color=[255,20,147]):.. print img.shape. res=img.copy(). for x in range(img.shape[0]):. for y in range(img.shape[1]):. rgbimg=rgbcolor(img[x,y,0],img[x,y,1],img[x,y,2]). labimg=rgbimg.convert_to(\'lab\', debug=false). if (labimg.lab_l > treshold):. res[x,y,:]=color. else: . res[x,y,:]=img[x,y,:].. return res"\n'
Label: 3
Question: b'"option and validation in blank i want to add a new option on my system where i want to add two text files, both rental.txt and customer.txt. inside each text are id numbers of the customer, the videotape they need and the price...i want to place it as an option on my code. right now i have:...add customer.rent return.view list.search.exit...i want to add this as my sixth option. say for example i ordered a video, it would display the price and would let me confirm the price and if i am going to buy it or not...here is my current code:.. import blank.io.*;. import blank.util.arraylist;. import static blank.lang.system.out;.. public class rentalsystem{. static bufferedreader input = new bufferedreader(new inputstreamreader(system.in));. static file file = new file(""file.txt"");. static arraylist<string> list = new arraylist<string>();. static int rows;.. public static void main(string[] args) throws exception{. introduction();. system.out.print(""nn"");. login();. system.out.print(""nnnnnnnnnnnnnnnnnnnnnn"");. introduction();. string repeat;. do{. loadfile();. system.out.print(""nwhat do you want to do?nn"");. system.out.print(""n - - - - - - - - - - - - - - - - - - - - - - -"");. system.out.print(""nn | 1. add customer | 2. rent return |n"");. system.out.print(""n - - - - - - - - - - - - - - - - - - - - - - -"");. system.out.print(""nn | 3. view list | 4. search |n"");. system.out.print(""n - - - - - - - - - - - - - - - - - - - - - - -"");. system.out.print(""nn | 5. exit |n"");. system.out.print(""n - - - - - - - - - -"");. system.out.print(""nnchoice:"");. int choice = integer.parseint(input.readline());. switch(choice){. case 1:. writedata();. break;. case 2:. rentdata();. break;. case 3:. viewlist();. break;. case 4:. search();. break;. case 5:. system.out.println(""goodbye!"");. system.exit(0);. default:. system.out.print(""invalid choice: "");. break;. }. system.out.print(""ndo another task? [y/n] "");. repeat = input.readline();. }while(repeat.equals(""y""));.. if(repeat!=""y"") system.out.println(""ngoodbye!"");.. }.. public static void writedata() throws exception{. system.out.print(""nname: "");. string cname = input.readline();. system.out.print(""address: "");. string add = input.readline();. system.out.print(""phone no.: "");. string pno = input.readline();. system.out.print(""rental amount: "");. string ramount = input.readline();. system.out.print(""tapenumber: "");. string tno = input.readline();. system.out.print(""title: "");. string title = input.readline();. system.out.print(""date borrowed: "");. string dborrowed = input.readline();. system.out.print(""due date: "");. string ddate = input.readline();. createline(cname, add, pno, ramount,tno, title, dborrowed, ddate);. rentdata();. }.. public static void createline(string name, string address, string phone , string rental, string tapenumber, string title, string borrowed, string due) throws exception{. filewriter fw = new filewriter(file, true);. fw.write(""nname: ""+name + ""naddress: "" + address +""nphone no.: ""+ phone+""nrentalamount: ""+rental+""ntape no.: ""+ tapenumber+""ntitle: ""+ title+""ndate borrowed: ""+borrowed +""ndue date: ""+ due+"":rn"");. fw.close();. }.. public static void loadfile() throws exception{. try{. list.clear();. fileinputstream fstream = new fileinputstream(file);. bufferedreader br = new bufferedreader(new inputstreamreader(fstream));. rows = 0;. while( br.ready()). {. list.add(br.readline());. rows++;. }. br.close();. } catch(exception e){. system.out.println(""list not yet loaded."");. }. }.. public static void viewlist(){. system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. system.out.print("" |list of all costumers|"");. system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. for(int i = 0; i <rows; i++){. system.out.println(list.get(i));. }. }. public static void rentdata()throws exception. { system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. system.out.print("" |rent data list|"");. system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. system.out.print(""nenter customer name: "");. string cname = input.readline();. system.out.print(""date borrowed: "");. string dborrowed = input.readline();. system.out.print(""due date: "");. string ddate = input.readline();. system.out.print(""return date: "");. string rdate = input.readline();. system.out.print(""rent amount: "");. string ramount = input.readline();.. system.out.print(""you pay:""+ramount);... }. public static void search()throws exception. { system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. system.out.print("" |search costumers|"");. system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");. system.out.print(""nenter costumer name: "");. string cname = input.readline();. boolean found = false;.. for(int i=0; i < rows; i++){. string temp[] = list.get(i).split("","");.. if(cname.equals(temp[0])){. system.out.println(""search result:nyou are "" + temp[0] + "" from "" + temp[1] + "".""+ temp[2] + "".""+ temp[3] + "".""+ temp[4] + "".""+ temp[5] + "" is "" + temp[6] + "".""+ temp[7] + "" is "" + temp[8] + ""."");. found = true;. }. }.. if(!found){. system.out.print(""no results."");. }.. }.. public static boolean evaluate(string uname, string pass){. if (uname.equals(""admin"")&&pass.equals(""12345"")) return true;. else return false;. }.. public static string login()throws exception{. bufferedreader input=new bufferedreader(new inputstreamreader(system.in));. int counter=0;. do{. system.out.print(""username:"");. string uname =input.readline();. system.out.print(""password:"");. string pass =input.readline();.. boolean accept= evaluate(uname,pass);.. if(accept){. break;. }else{. system.out.println(""incorrect username or password!"");. counter ++;. }. }while(counter<3);.. if(counter !=3) return ""login successful"";. else return ""login failed"";. }. public static void introduction() throws exception{.. system.out.println("" - - - - - - - - - - - - - - - - - - - - - - - - -"");. system.out.println("" ! r e n t a l !"");. system.out.println("" ! ~ ~ ~ ~ ~ ! ================= ! ~ ~ ~ ~ ~ !"");. system.out.println("" ! s y s t e m !"");. system.out.println("" - - - - - - - - - - - - - - - - - - - - - - - - -"");. }..}"\n'
Label: 1
Question: b'"exception: dynamic sql generation for the updatecommand is not supported against a selectcommand that does not return any key i dont know what is the problem this my code : ..string nomtable;..datatable listeetablissementtable = new datatable();.datatable listeinteretstable = new datatable();.dataset ds = new dataset();.sqldataadapter da;.sqlcommandbuilder cmdb;..private void listeinterets_click(object sender, eventargs e).{. nomtable = ""listeinteretstable"";. d.cnx.open();. da = new sqldataadapter(""select nome from offices"", d.cnx);. ds = new dataset();. da.fill(ds, nomtable);. datagridview1.datasource = ds.tables[nomtable];.}..private void sauvgarder_click(object sender, eventargs e).{. d.cnx.open();. cmdb = new sqlcommandbuilder(da);. da.update(ds, nomtable);. d.cnx.close();.}"\n'
Label: 0
Question: b'"parameter with question mark and super in blank, i\'ve come across a method that is formatted like this:..public final subscription subscribe(final action1<? super t> onnext, final action1<throwable> onerror) {.}...in the first parameter, what does the question mark and super mean?"\n'
Label: 1
Question: b'call two objects wsdl the first time i got a very strange wsdl. ..i would like to call the object (interface - invoicecheck_out) do you know how?....i would like to call the object (variable) do you know how?..try to call (it`s ok)....try to call (how call this?)\n'
Label: 0
Question: b"how to correctly make the icon for systemtray in blank using icon sizes of any dimension for systemtray doesn't look good overall. .what is the correct way of making icons for windows system tray?..screenshots: http://imgur.com/zsibwn9..icon: http://imgur.com/vsh4zo8\n"
Label: 0
Question: b'"is there a way to check a variable that exists in a different script than the original one? i\'m trying to check if a variable, which was previously set to true in 2.py in 1.py, as 1.py is only supposed to continue if the variable is true...2.py..import os..completed = false..#some stuff here..completed = true...1.py..import 2 ..if completed == true. #do things...however i get a syntax error at ..if completed == true"\n'
Label: 3
Question: b'"blank control flow i made a number which asks for 2 numbers with blank and responds with the corresponding message for the case. how come it doesnt work for the second number ? .regardless what i enter for the second number , i am getting the message ""your number is in the range 0-10""...using system;.using system.collections.generic;.using system.linq;.using system.text;..namespace consoleapplication1.{. class program. {. static void main(string[] args). {. string myinput; // declaring the type of the variables. int myint;.. string number1;. int number;... console.writeline(""enter a number"");. myinput = console.readline(); //muyinput is a string which is entry input. myint = int32.parse(myinput); // myint converts the string into an integer.. if (myint > 0). console.writeline(""your number {0} is greater than zero."", myint);. else if (myint < 0). console.writeline(""your number {0} is less than zero."", myint);. else. console.writeline(""your number {0} is equal zero."", myint);.. console.writeline(""enter another number"");. number1 = console.readline(); . number = int32.parse(myinput); .. if (number < 0 || number == 0). console.writeline(""your number {0} is less than zero or equal zero."", number);. else if (number > 0 && number <= 10). console.writeline(""your number {0} is in the range from 0 to 10."", number);. else. console.writeline(""your number {0} is greater than 10."", number);.. console.writeline(""enter another number"");.. }. } .}"\n'
Label: 0
Question: b'"credentials cannot be used for ntlm authentication i am getting org.apache.commons.httpclient.auth.invalidcredentialsexception: credentials cannot be used for ntlm authentication: exception in eclipse..whether it is possible mention eclipse to take system proxy settings directly?..public class httpgetproxy {. private static final string proxy_host = ""proxy.****.com"";. private static final int proxy_port = 6050;.. public static void main(string[] args) {. httpclient client = new httpclient();. httpmethod method = new getmethod(""https://kodeblank.org"");.. hostconfiguration config = client.gethostconfiguration();. config.setproxy(proxy_host, proxy_port);.. string username = ""*****"";. string password = ""*****"";. credentials credentials = new usernamepasswordcredentials(username, password);. authscope authscope = new authscope(proxy_host, proxy_port);.. client.getstate().setproxycredentials(authscope, credentials);.. try {. client.executemethod(method);.. if (method.getstatuscode() == httpstatus.sc_ok) {. string response = method.getresponsebodyasstring();. system.out.println(""response = "" + response);. }. } catch (ioexception e) {. e.printstacktrace();. } finally {. method.releaseconnection();. }. }.}...exception:... dec 08, 2017 1:41:39 pm . org.apache.commons.httpclient.auth.authchallengeprocessor selectauthscheme. info: ntlm authentication scheme selected. dec 08, 2017 1:41:39 pm org.apache.commons.httpclient.httpmethoddirector executeconnect. severe: credentials cannot be used for ntlm authentication: . org.apache.commons.httpclient.usernamepasswordcredentials. org.apache.commons.httpclient.auth.invalidcredentialsexception: credentials . cannot be used for ntlm authentication: . enter code here . org.apache.commons.httpclient.usernamepasswordcredentials. at org.apache.commons.httpclient.auth.ntlmscheme.authenticate(ntlmscheme.blank:332). at org.apache.commons.httpclient.httpmethoddirector.authenticateproxy(httpmethoddirector.blank:320). at org.apache.commons.httpclient.httpmethoddirector.executeconnect(httpmethoddirector.blank:491). at org.apache.commons.httpclient.httpmethoddirector.executewithretry(httpmethoddirector.blank:391). at org.apache.commons.httpclient.httpmethoddirector.executemethod(httpmethoddirector.blank:171). at org.apache.commons.httpclient.httpclient.executemethod(httpclient.blank:397). at org.apache.commons.httpclient.httpclient.executemethod(httpclient.blank:323). at httpgetproxy.main(httpgetproxy.blank:31). dec 08, 2017 1:41:39 pm org.apache.commons.httpclient.httpmethoddirector processproxyauthchallenge. info: failure authenticating with ntlm @proxy.****.com:6050"\n'
Label: 1
Labelnya adalah 0 , 1 , 2 atau 3 . Untuk memeriksa mana yang sesuai dengan label string mana, Anda dapat memeriksa properti class_names pada kumpulan data:
for i, label in enumerate(raw_train_ds.class_names):
print("Label", i, "corresponds to", label)
Label 0 corresponds to csharp Label 1 corresponds to java Label 2 corresponds to javascript Label 3 corresponds to python
Selanjutnya, Anda akan membuat validasi dan set pengujian menggunakan tf.keras.utils.text_dataset_from_directory . Anda akan menggunakan sisa 1.600 ulasan dari set pelatihan untuk validasi.
# Create a validation set.
raw_val_ds = utils.text_dataset_from_directory(
train_dir,
batch_size=batch_size,
validation_split=0.2,
subset='validation',
seed=seed)
Found 8000 files belonging to 4 classes. Using 1600 files for validation.
test_dir = dataset_dir/'test'
# Create a test set.
raw_test_ds = utils.text_dataset_from_directory(
test_dir,
batch_size=batch_size)
Found 8000 files belonging to 4 classes.
Siapkan dataset untuk pelatihan
Selanjutnya, Anda akan melakukan standarisasi, tokenize, dan vektorisasi data menggunakan lapisan tf.keras.layers.TextVectorization .
- Standardisasi mengacu pada pra-pemrosesan teks, biasanya untuk menghapus tanda baca atau elemen HTML untuk menyederhanakan kumpulan data.
- Tokenisasi mengacu pada pemisahan string menjadi token (misalnya, membagi kalimat menjadi kata-kata individual dengan memisahkan spasi).
- Vektorisasi mengacu pada konversi token menjadi angka sehingga dapat dimasukkan ke dalam jaringan saraf.
Semua tugas ini dapat diselesaikan dengan lapisan ini. (Anda dapat mempelajari lebih lanjut tentang masing-masing ini di dokumen tf.keras.layers.TextVectorization API.)
Perhatikan bahwa:
- Standarisasi default mengonversi teks menjadi huruf kecil dan menghilangkan tanda baca (
standardize='lower_and_strip_punctuation'). - Tokenizer default terbagi pada spasi putih (
split='whitespace'). - Mode vektorisasi default adalah
'int'(output_mode='int'). Ini menampilkan indeks integer (satu per token). Mode ini dapat digunakan untuk membangun model yang memperhitungkan urutan kata. Anda juga dapat menggunakan mode lain—seperti'binary'untuk membuat model bag-of-words .
Anda akan membuat dua model untuk mempelajari lebih lanjut tentang standardisasi, tokenisasi, dan vektorisasi dengan TextVectorization :
- Pertama, Anda akan menggunakan mode vektorisasi
'binary'untuk membangun model bag-of-words. - Kemudian, Anda akan menggunakan mode
'int'dengan ConvNet 1D.
VOCAB_SIZE = 10000
binary_vectorize_layer = TextVectorization(
max_tokens=VOCAB_SIZE,
output_mode='binary')
Untuk mode 'int' , selain ukuran kosakata maksimum, Anda perlu menyetel panjang urutan maksimum eksplisit ( MAX_SEQUENCE_LENGTH ), yang akan menyebabkan lapisan melapisi atau memotong urutan ke nilai output_sequence_length yang tepat:
MAX_SEQUENCE_LENGTH = 250
int_vectorize_layer = TextVectorization(
max_tokens=VOCAB_SIZE,
output_mode='int',
output_sequence_length=MAX_SEQUENCE_LENGTH)
Selanjutnya, panggil TextVectorization.adapt agar sesuai dengan status lapisan prapemrosesan ke kumpulan data. Ini akan menyebabkan model membangun indeks string ke bilangan bulat.
# Make a text-only dataset (without labels), then call `TextVectorization.adapt`.
train_text = raw_train_ds.map(lambda text, labels: text)
binary_vectorize_layer.adapt(train_text)
int_vectorize_layer.adapt(train_text)
Cetak hasil penggunaan layer ini untuk melakukan preprocessing data:
def binary_vectorize_text(text, label):
text = tf.expand_dims(text, -1)
return binary_vectorize_layer(text), label
def int_vectorize_text(text, label):
text = tf.expand_dims(text, -1)
return int_vectorize_layer(text), label
# Retrieve a batch (of 32 reviews and labels) from the dataset.
text_batch, label_batch = next(iter(raw_train_ds))
first_question, first_label = text_batch[0], label_batch[0]
print("Question", first_question)
print("Label", first_label)
Question tf.Tensor(b'"what is the difference between these two ways to create an element? var a = document.createelement(\'div\');..a.id = ""mydiv"";...and..var a = document.createelement(\'div\').id = ""mydiv"";...what is the difference between them such that the first one works and the second one doesn\'t?"\n', shape=(), dtype=string) Label tf.Tensor(2, shape=(), dtype=int32)
print("'binary' vectorized question:",
binary_vectorize_text(first_question, first_label)[0])
'binary' vectorized question: tf.Tensor([[1. 1. 0. ... 0. 0. 0.]], shape=(1, 10000), dtype=float32)
print("'int' vectorized question:",
int_vectorize_text(first_question, first_label)[0])
'int' vectorized question: tf.Tensor(
[[ 55 6 2 410 211 229 121 895 4 124 32 245 43 5 1 1 5 1
1 6 2 410 211 191 318 14 2 98 71 188 8 2 199 71 178 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]], shape=(1, 250), dtype=int64)
Seperti ditunjukkan di atas, mode 'binary' TextVectorization mengembalikan array yang menunjukkan token mana yang ada setidaknya sekali dalam input, sedangkan mode 'int' menggantikan setiap token dengan bilangan bulat, sehingga mempertahankan urutannya.
Anda dapat mencari token (string) yang terkait dengan setiap bilangan bulat dengan memanggil TextVectorization.get_vocabulary pada layer:
print("1289 ---> ", int_vectorize_layer.get_vocabulary()[1289])
print("313 ---> ", int_vectorize_layer.get_vocabulary()[313])
print("Vocabulary size: {}".format(len(int_vectorize_layer.get_vocabulary())))
1289 ---> roman 313 ---> source Vocabulary size: 10000
Anda hampir siap untuk melatih model Anda.
Sebagai langkah prapemrosesan terakhir, Anda akan menerapkan lapisan TextVectorization yang Anda buat sebelumnya ke set pelatihan, validasi, dan pengujian:
binary_train_ds = raw_train_ds.map(binary_vectorize_text)
binary_val_ds = raw_val_ds.map(binary_vectorize_text)
binary_test_ds = raw_test_ds.map(binary_vectorize_text)
int_train_ds = raw_train_ds.map(int_vectorize_text)
int_val_ds = raw_val_ds.map(int_vectorize_text)
int_test_ds = raw_test_ds.map(int_vectorize_text)
Konfigurasikan kumpulan data untuk kinerja
Ini adalah dua metode penting yang harus Anda gunakan saat memuat data untuk memastikan bahwa I/O tidak menjadi pemblokiran.
-
Dataset.cachemenyimpan data dalam memori setelah dimuat dari disk. Ini akan memastikan kumpulan data tidak menjadi hambatan saat melatih model Anda. Jika kumpulan data Anda terlalu besar untuk dimasukkan ke dalam memori, Anda juga dapat menggunakan metode ini untuk membuat cache di disk yang berkinerja baik, yang lebih efisien untuk dibaca daripada banyak file kecil. -
Dataset.prefetchtumpang tindih dengan prapemrosesan data dan eksekusi model saat pelatihan.
Anda dapat mempelajari lebih lanjut tentang kedua metode tersebut, serta cara menyimpan data ke dalam cache di bagian Prefetching pada Better performance with the tf.data API guide.
AUTOTUNE = tf.data.AUTOTUNE
def configure_dataset(dataset):
return dataset.cache().prefetch(buffer_size=AUTOTUNE)
binary_train_ds = configure_dataset(binary_train_ds)
binary_val_ds = configure_dataset(binary_val_ds)
binary_test_ds = configure_dataset(binary_test_ds)
int_train_ds = configure_dataset(int_train_ds)
int_val_ds = configure_dataset(int_val_ds)
int_test_ds = configure_dataset(int_test_ds)
Latih modelnya
Saatnya untuk membuat jaringan saraf Anda.
Untuk data vektor 'binary' , tentukan model linier bag-of-words sederhana, lalu konfigurasikan dan latih:
binary_model = tf.keras.Sequential([layers.Dense(4)])
binary_model.compile(
loss=losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer='adam',
metrics=['accuracy'])
history = binary_model.fit(
binary_train_ds, validation_data=binary_val_ds, epochs=10)
Epoch 1/10 200/200 [==============================] - 2s 4ms/step - loss: 1.1170 - accuracy: 0.6509 - val_loss: 0.9165 - val_accuracy: 0.7844 Epoch 2/10 200/200 [==============================] - 1s 3ms/step - loss: 0.7781 - accuracy: 0.8169 - val_loss: 0.7522 - val_accuracy: 0.8050 Epoch 3/10 200/200 [==============================] - 1s 3ms/step - loss: 0.6274 - accuracy: 0.8591 - val_loss: 0.6664 - val_accuracy: 0.8163 Epoch 4/10 200/200 [==============================] - 1s 3ms/step - loss: 0.5342 - accuracy: 0.8866 - val_loss: 0.6129 - val_accuracy: 0.8188 Epoch 5/10 200/200 [==============================] - 1s 3ms/step - loss: 0.4683 - accuracy: 0.9038 - val_loss: 0.5761 - val_accuracy: 0.8281 Epoch 6/10 200/200 [==============================] - 1s 3ms/step - loss: 0.4181 - accuracy: 0.9181 - val_loss: 0.5494 - val_accuracy: 0.8331 Epoch 7/10 200/200 [==============================] - 1s 3ms/step - loss: 0.3779 - accuracy: 0.9287 - val_loss: 0.5293 - val_accuracy: 0.8388 Epoch 8/10 200/200 [==============================] - 1s 3ms/step - loss: 0.3446 - accuracy: 0.9361 - val_loss: 0.5137 - val_accuracy: 0.8400 Epoch 9/10 200/200 [==============================] - 1s 3ms/step - loss: 0.3164 - accuracy: 0.9430 - val_loss: 0.5014 - val_accuracy: 0.8381 Epoch 10/10 200/200 [==============================] - 1s 3ms/step - loss: 0.2920 - accuracy: 0.9495 - val_loss: 0.4916 - val_accuracy: 0.8388
Selanjutnya, Anda akan menggunakan lapisan vektor 'int' untuk membangun ConvNet 1D:
def create_model(vocab_size, num_labels):
model = tf.keras.Sequential([
layers.Embedding(vocab_size, 64, mask_zero=True),
layers.Conv1D(64, 5, padding="valid", activation="relu", strides=2),
layers.GlobalMaxPooling1D(),
layers.Dense(num_labels)
])
return model
# `vocab_size` is `VOCAB_SIZE + 1` since `0` is used additionally for padding.
int_model = create_model(vocab_size=VOCAB_SIZE + 1, num_labels=4)
int_model.compile(
loss=losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer='adam',
metrics=['accuracy'])
history = int_model.fit(int_train_ds, validation_data=int_val_ds, epochs=5)
Epoch 1/5 200/200 [==============================] - 9s 5ms/step - loss: 1.1471 - accuracy: 0.5016 - val_loss: 0.7856 - val_accuracy: 0.6913 Epoch 2/5 200/200 [==============================] - 1s 3ms/step - loss: 0.6378 - accuracy: 0.7550 - val_loss: 0.5494 - val_accuracy: 0.8056 Epoch 3/5 200/200 [==============================] - 1s 3ms/step - loss: 0.3900 - accuracy: 0.8764 - val_loss: 0.4845 - val_accuracy: 0.8206 Epoch 4/5 200/200 [==============================] - 1s 3ms/step - loss: 0.2234 - accuracy: 0.9447 - val_loss: 0.4819 - val_accuracy: 0.8188 Epoch 5/5 200/200 [==============================] - 1s 3ms/step - loss: 0.1146 - accuracy: 0.9809 - val_loss: 0.5038 - val_accuracy: 0.8150
Bandingkan dua model:
print("Linear model on binary vectorized data:")
print(binary_model.summary())
Linear model on binary vectorized data:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 4) 40004
=================================================================
Total params: 40,004
Trainable params: 40,004
Non-trainable params: 0
_________________________________________________________________
None
print("ConvNet model on int vectorized data:")
print(int_model.summary())
ConvNet model on int vectorized data:
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, None, 64) 640064
conv1d (Conv1D) (None, None, 64) 20544
global_max_pooling1d (Globa (None, 64) 0
lMaxPooling1D)
dense_1 (Dense) (None, 4) 260
=================================================================
Total params: 660,868
Trainable params: 660,868
Non-trainable params: 0
_________________________________________________________________
None
Evaluasi kedua model pada data uji:
binary_loss, binary_accuracy = binary_model.evaluate(binary_test_ds)
int_loss, int_accuracy = int_model.evaluate(int_test_ds)
print("Binary model accuracy: {:2.2%}".format(binary_accuracy))
print("Int model accuracy: {:2.2%}".format(int_accuracy))
250/250 [==============================] - 1s 3ms/step - loss: 0.5178 - accuracy: 0.8151 250/250 [==============================] - 1s 2ms/step - loss: 0.5262 - accuracy: 0.8073 Binary model accuracy: 81.51% Int model accuracy: 80.73%
Ekspor modelnya
Dalam kode di atas, Anda menerapkan tf.keras.layers.TextVectorization ke dataset sebelum memasukkan teks ke model. Jika Anda ingin membuat model Anda mampu memproses string mentah (misalnya, untuk menyederhanakan penerapannya), Anda dapat menyertakan lapisan TextVectorization di dalam model Anda.
Untuk melakukannya, Anda dapat membuat model baru menggunakan bobot yang baru saja Anda latih:
export_model = tf.keras.Sequential(
[binary_vectorize_layer, binary_model,
layers.Activation('sigmoid')])
export_model.compile(
loss=losses.SparseCategoricalCrossentropy(from_logits=False),
optimizer='adam',
metrics=['accuracy'])
# Test it with `raw_test_ds`, which yields raw strings
loss, accuracy = export_model.evaluate(raw_test_ds)
print("Accuracy: {:2.2%}".format(binary_accuracy))
250/250 [==============================] - 1s 4ms/step - loss: 0.5178 - accuracy: 0.8151 Accuracy: 81.51%
Sekarang, model Anda dapat mengambil string mentah sebagai input dan memprediksi skor untuk setiap label menggunakan Model.predict . Tentukan fungsi untuk menemukan label dengan skor maksimum:
def get_string_labels(predicted_scores_batch):
predicted_int_labels = tf.argmax(predicted_scores_batch, axis=1)
predicted_labels = tf.gather(raw_train_ds.class_names, predicted_int_labels)
return predicted_labels
Jalankan inferensi pada data baru
inputs = [
"how do I extract keys from a dict into a list?", # 'python'
"debug public static void main(string[] args) {...}", # 'java'
]
predicted_scores = export_model.predict(inputs)
predicted_labels = get_string_labels(predicted_scores)
for input, label in zip(inputs, predicted_labels):
print("Question: ", input)
print("Predicted label: ", label.numpy())
Question: how do I extract keys from a dict into a list?
Predicted label: b'python'
Question: debug public static void main(string[] args) {...}
Predicted label: b'java'
Menyertakan logika prapemrosesan teks di dalam model Anda memungkinkan Anda mengekspor model untuk produksi yang menyederhanakan penerapan, dan mengurangi potensi kemiringan train/test .
Ada perbedaan kinerja yang perlu diingat saat memilih tempat untuk menerapkan tf.keras.layers.TextVectorization . Menggunakannya di luar model Anda memungkinkan Anda melakukan pemrosesan CPU asinkron dan buffering data Anda saat berlatih di GPU. Jadi, jika Anda melatih model Anda di GPU, Anda mungkin ingin menggunakan opsi ini untuk mendapatkan kinerja terbaik saat mengembangkan model Anda, lalu beralih ke menyertakan lapisan TextVectorization di dalam model Anda saat Anda siap untuk mempersiapkan penerapan .
Kunjungi tutorial Simpan dan muat model untuk mempelajari lebih lanjut tentang menyimpan model.
Contoh 2: Prediksi penulis terjemahan Iliad
Berikut ini adalah contoh penggunaan tf.data.TextLineDataset untuk memuat contoh dari file teks, dan Teks TensorFlow untuk memproses data sebelumnya. Anda akan menggunakan tiga terjemahan bahasa Inggris yang berbeda dari karya yang sama, Homer's Iliad, dan melatih model untuk mengidentifikasi penerjemah yang diberikan satu baris teks.
Unduh dan jelajahi kumpulan data
Teks dari ketiga terjemahan tersebut adalah dengan:
File teks yang digunakan dalam tutorial ini telah mengalami beberapa tugas pemrosesan awal seperti menghapus header dan footer dokumen, nomor baris, dan judul bab.
Unduh file-file munged ringan ini secara lokal:
DIRECTORY_URL = 'https://storage.googleapis.com/download.tensorflow.org/data/illiad/'
FILE_NAMES = ['cowper.txt', 'derby.txt', 'butler.txt']
for name in FILE_NAMES:
text_dir = utils.get_file(name, origin=DIRECTORY_URL + name)
parent_dir = pathlib.Path(text_dir).parent
list(parent_dir.iterdir())
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/cowper.txt
819200/815980 [==============================] - 0s 0us/step
827392/815980 [==============================] - 0s 0us/step
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/derby.txt
811008/809730 [==============================] - 0s 0us/step
819200/809730 [==============================] - 0s 0us/step
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/butler.txt
811008/807992 [==============================] - 0s 0us/step
819200/807992 [==============================] - 0s 0us/step
[PosixPath('/home/kbuilder/.keras/datasets/derby.txt'),
PosixPath('/home/kbuilder/.keras/datasets/butler.txt'),
PosixPath('/home/kbuilder/.keras/datasets/cowper.txt'),
PosixPath('/home/kbuilder/.keras/datasets/fashion-mnist'),
PosixPath('/home/kbuilder/.keras/datasets/mnist.npz')]
Muat kumpulan data
Sebelumnya, dengan tf.keras.utils.text_dataset_from_directory semua konten file diperlakukan sebagai satu contoh. Di sini, Anda akan menggunakan tf.data.TextLineDataset , yang dirancang untuk membuat tf.data.Dataset dari file teks di mana setiap contoh adalah baris teks dari file asli. TextLineDataset berguna untuk data teks yang terutama berbasis baris (misalnya, puisi atau log kesalahan).
Ulangi melalui file-file ini, memuat masing-masing ke dalam kumpulan datanya sendiri. Setiap contoh perlu diberi label satu per satu, jadi gunakan Dataset.map untuk menerapkan fungsi pemberi label ke masing-masing contoh. Ini akan mengulangi setiap contoh dalam kumpulan data, mengembalikan pasangan ( example, label ).
def labeler(example, index):
return example, tf.cast(index, tf.int64)
labeled_data_sets = []
for i, file_name in enumerate(FILE_NAMES):
lines_dataset = tf.data.TextLineDataset(str(parent_dir/file_name))
labeled_dataset = lines_dataset.map(lambda ex: labeler(ex, i))
labeled_data_sets.append(labeled_dataset)
Selanjutnya, Anda akan menggabungkan kumpulan data berlabel ini menjadi satu kumpulan data menggunakan Dataset.concatenate , dan mengacaknya dengan Dataset.shuffle :
BUFFER_SIZE = 50000
BATCH_SIZE = 64
VALIDATION_SIZE = 5000
all_labeled_data = labeled_data_sets[0]
for labeled_dataset in labeled_data_sets[1:]:
all_labeled_data = all_labeled_data.concatenate(labeled_dataset)
all_labeled_data = all_labeled_data.shuffle(
BUFFER_SIZE, reshuffle_each_iteration=False)
Cetak beberapa contoh seperti sebelumnya. Kumpulan data belum di-batch, oleh karena itu setiap entri di all_labeled_data sesuai dengan satu titik data:
for text, label in all_labeled_data.take(10):
print("Sentence: ", text.numpy())
print("Label:", label.numpy())
Sentence: b'Beneath the yoke the flying coursers led.' Label: 1 Sentence: b'Too free a range, and watchest all I do;' Label: 1 Sentence: b'defence of their ships. Thus would any seer who was expert in these' Label: 2 Sentence: b'"From morn to eve I fell, a summer\'s day,"' Label: 0 Sentence: b'went to the city bearing a message of peace to the Cadmeians; on his' Label: 2 Sentence: b'darkness of the flying night, and tell it to Agamemnon. This might' Label: 2 Sentence: b"To that distinction, Nestor's son, whom yet" Label: 0 Sentence: b'A sounder judge of honour and disgrace:' Label: 1 Sentence: b'He wept as he spoke, and the elders sighed in concert as each thought' Label: 2 Sentence: b'to gather his bones for the silt in which I shall have hidden him, and' Label: 2
Siapkan dataset untuk pelatihan
Alih-alih menggunakan tf.keras.layers.TextVectorization untuk melakukan praproses kumpulan data teks, Anda sekarang akan menggunakan API Teks TensorFlow untuk menstandarisasi dan membuat tokenisasi data, membangun kosakata, dan menggunakan tf.lookup.StaticVocabularyTable untuk memetakan token ke bilangan bulat untuk diumpankan ke model. (Pelajari lebih lanjut tentang Teks TensorFlow ).
Tentukan fungsi untuk mengonversi teks menjadi huruf kecil dan menandainya:
- TensorFlow Text menyediakan berbagai tokenizer. Dalam contoh ini, Anda akan menggunakan
text.UnicodeScriptTokenizeruntuk tokenize dataset. - Anda akan menggunakan
Dataset.mapuntuk menerapkan tokenisasi ke dataset.
tokenizer = tf_text.UnicodeScriptTokenizer()
def tokenize(text, unused_label):
lower_case = tf_text.case_fold_utf8(text)
return tokenizer.tokenize(lower_case)
tokenized_ds = all_labeled_data.map(tokenize)
Anda dapat mengulangi set data dan mencetak beberapa contoh tokenized:
for text_batch in tokenized_ds.take(5):
print("Tokens: ", text_batch.numpy())
Tokens: [b'beneath' b'the' b'yoke' b'the' b'flying' b'coursers' b'led' b'.'] Tokens: [b'too' b'free' b'a' b'range' b',' b'and' b'watchest' b'all' b'i' b'do' b';'] Tokens: [b'defence' b'of' b'their' b'ships' b'.' b'thus' b'would' b'any' b'seer' b'who' b'was' b'expert' b'in' b'these'] Tokens: [b'"' b'from' b'morn' b'to' b'eve' b'i' b'fell' b',' b'a' b'summer' b"'" b's' b'day' b',"'] Tokens: [b'went' b'to' b'the' b'city' b'bearing' b'a' b'message' b'of' b'peace' b'to' b'the' b'cadmeians' b';' b'on' b'his']
Selanjutnya, Anda akan membangun kosakata dengan menyortir token berdasarkan frekuensi dan menyimpan token VOCAB_SIZE teratas:
tokenized_ds = configure_dataset(tokenized_ds)
vocab_dict = collections.defaultdict(lambda: 0)
for toks in tokenized_ds.as_numpy_iterator():
for tok in toks:
vocab_dict[tok] += 1
vocab = sorted(vocab_dict.items(), key=lambda x: x[1], reverse=True)
vocab = [token for token, count in vocab]
vocab = vocab[:VOCAB_SIZE]
vocab_size = len(vocab)
print("Vocab size: ", vocab_size)
print("First five vocab entries:", vocab[:5])
Vocab size: 10000 First five vocab entries: [b',', b'the', b'and', b"'", b'of']
Untuk mengonversi token menjadi bilangan bulat, gunakan set vocab untuk membuat tf.lookup.StaticVocabularyTable . Anda akan memetakan token ke bilangan bulat dalam rentang [ 2 , vocab_size + 2 ]. Seperti pada layer TextVectorization , 0 dicadangkan untuk menunjukkan padding dan 1 dicadangkan untuk menunjukkan token out-of-vocabulary (OOV).
keys = vocab
values = range(2, len(vocab) + 2) # Reserve `0` for padding, `1` for OOV tokens.
init = tf.lookup.KeyValueTensorInitializer(
keys, values, key_dtype=tf.string, value_dtype=tf.int64)
num_oov_buckets = 1
vocab_table = tf.lookup.StaticVocabularyTable(init, num_oov_buckets)
Terakhir, tentukan fungsi untuk menstandardisasi, membuat token, dan membuat vektor dataset menggunakan tokenizer dan tabel pencarian:
def preprocess_text(text, label):
standardized = tf_text.case_fold_utf8(text)
tokenized = tokenizer.tokenize(standardized)
vectorized = vocab_table.lookup(tokenized)
return vectorized, label
Anda dapat mencoba ini pada satu contoh untuk mencetak output:
example_text, example_label = next(iter(all_labeled_data))
print("Sentence: ", example_text.numpy())
vectorized_text, example_label = preprocess_text(example_text, example_label)
print("Vectorized sentence: ", vectorized_text.numpy())
Sentence: b'Beneath the yoke the flying coursers led.' Vectorized sentence: [234 3 811 3 446 749 248 7]
Sekarang jalankan fungsi preprocess pada dataset menggunakan Dataset.map :
all_encoded_data = all_labeled_data.map(preprocess_text)
Pisahkan set data menjadi set pelatihan dan pengujian
Lapisan Keras TextVectorization juga mengelompokkan dan melapisi data yang divektorkan. Padding diperlukan karena contoh di dalam kumpulan harus memiliki ukuran dan bentuk yang sama, tetapi contoh dalam kumpulan data ini tidak semuanya berukuran sama—setiap baris teks memiliki jumlah kata yang berbeda.
tf.data.Dataset mendukung set data splitting dan padded-batching:
train_data = all_encoded_data.skip(VALIDATION_SIZE).shuffle(BUFFER_SIZE)
validation_data = all_encoded_data.take(VALIDATION_SIZE)
train_data = train_data.padded_batch(BATCH_SIZE)
validation_data = validation_data.padded_batch(BATCH_SIZE)
Sekarang, validation_data dan train_data bukan kumpulan pasangan ( example, label ), tetapi kumpulan kumpulan. Setiap batch adalah sepasang ( banyak contoh , banyak label ) direpresentasikan sebagai array.
Untuk mengilustrasikan ini:
sample_text, sample_labels = next(iter(validation_data))
print("Text batch shape: ", sample_text.shape)
print("Label batch shape: ", sample_labels.shape)
print("First text example: ", sample_text[0])
print("First label example: ", sample_labels[0])
Text batch shape: (64, 18) Label batch shape: (64,) First text example: tf.Tensor([234 3 811 3 446 749 248 7 0 0 0 0 0 0 0 0 0 0], shape=(18,), dtype=int64) First label example: tf.Tensor(1, shape=(), dtype=int64)
Karena Anda menggunakan 0 untuk padding dan 1 untuk token out-of-vocabulary (OOV), ukuran kosakata meningkat dua:
vocab_size += 2
Konfigurasikan kumpulan data untuk kinerja yang lebih baik seperti sebelumnya:
train_data = configure_dataset(train_data)
validation_data = configure_dataset(validation_data)
Latih modelnya
Anda dapat melatih model pada dataset ini seperti sebelumnya:
model = create_model(vocab_size=vocab_size, num_labels=3)
model.compile(
optimizer='adam',
loss=losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model.fit(train_data, validation_data=validation_data, epochs=3)
Epoch 1/3 697/697 [==============================] - 27s 9ms/step - loss: 0.5238 - accuracy: 0.7658 - val_loss: 0.3814 - val_accuracy: 0.8306 Epoch 2/3 697/697 [==============================] - 3s 4ms/step - loss: 0.2852 - accuracy: 0.8847 - val_loss: 0.3697 - val_accuracy: 0.8428 Epoch 3/3 697/697 [==============================] - 3s 4ms/step - loss: 0.1924 - accuracy: 0.9279 - val_loss: 0.3917 - val_accuracy: 0.8424
loss, accuracy = model.evaluate(validation_data)
print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))
79/79 [==============================] - 1s 2ms/step - loss: 0.3917 - accuracy: 0.8424 Loss: 0.391705721616745 Accuracy: 84.24%
Ekspor modelnya
Untuk membuat model mampu mengambil string mentah sebagai input, Anda akan membuat layer Keras TextVectorization yang melakukan langkah-langkah yang sama seperti fungsi preprocessing kustom Anda. Karena Anda telah melatih kosa kata, Anda dapat menggunakan TextVectorization.set_vocabulary (bukan TextVectorization.adapt ), yang melatih kosa kata baru.
preprocess_layer = TextVectorization(
max_tokens=vocab_size,
standardize=tf_text.case_fold_utf8,
split=tokenizer.tokenize,
output_mode='int',
output_sequence_length=MAX_SEQUENCE_LENGTH)
preprocess_layer.set_vocabulary(vocab)
export_model = tf.keras.Sequential(
[preprocess_layer, model,
layers.Activation('sigmoid')])
export_model.compile(
loss=losses.SparseCategoricalCrossentropy(from_logits=False),
optimizer='adam',
metrics=['accuracy'])
# Create a test dataset of raw strings.
test_ds = all_labeled_data.take(VALIDATION_SIZE).batch(BATCH_SIZE)
test_ds = configure_dataset(test_ds)
loss, accuracy = export_model.evaluate(test_ds)
print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))
2022-02-05 02:26:40.203675: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:907] Skipping loop optimization for Merge node with control input: sequential_4/text_vectorization_2/UnicodeScriptTokenize/Assert_1/AssertGuard/branch_executed/_185 79/79 [==============================] - 6s 8ms/step - loss: 0.4955 - accuracy: 0.7964 Loss: 0.4955357015132904 Accuracy: 79.64%
Kehilangan dan akurasi untuk model pada set validasi yang disandikan dan model yang diekspor pada set validasi mentah adalah sama, seperti yang diharapkan.
Jalankan inferensi pada data baru
inputs = [
"Join'd to th' Ionians with their flowing robes,", # Label: 1
"the allies, and his armour flashed about him so that he seemed to all", # Label: 2
"And with loud clangor of his arms he fell.", # Label: 0
]
predicted_scores = export_model.predict(inputs)
predicted_labels = tf.argmax(predicted_scores, axis=1)
for input, label in zip(inputs, predicted_labels):
print("Question: ", input)
print("Predicted label: ", label.numpy())
2022-02-05 02:26:43.328949: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:907] Skipping loop optimization for Merge node with control input: sequential_4/text_vectorization_2/UnicodeScriptTokenize/Assert_1/AssertGuard/branch_executed/_185 Question: Join'd to th' Ionians with their flowing robes, Predicted label: 1 Question: the allies, and his armour flashed about him so that he seemed to all Predicted label: 2 Question: And with loud clangor of his arms he fell. Predicted label: 0
Unduh lebih banyak set data menggunakan TensorFlow Datasets (TFDS)
Anda dapat mendownload lebih banyak set data dari TensorFlow Datasets .
Dalam contoh ini, Anda akan menggunakan kumpulan data IMDB Large Movie Review untuk melatih model klasifikasi sentimen:
# Training set.
train_ds = tfds.load(
'imdb_reviews',
split='train[:80%]',
batch_size=BATCH_SIZE,
shuffle_files=True,
as_supervised=True)
# Validation set.
val_ds = tfds.load(
'imdb_reviews',
split='train[80%:]',
batch_size=BATCH_SIZE,
shuffle_files=True,
as_supervised=True)
Cetak beberapa contoh:
for review_batch, label_batch in val_ds.take(1):
for i in range(5):
print("Review: ", review_batch[i].numpy())
print("Label: ", label_batch[i].numpy())
Review: b"Instead, go to the zoo, buy some peanuts and feed 'em to the monkeys. Monkeys are funny. People with amnesia who don't say much, just sit there with vacant eyes are not all that funny.<br /><br />Black comedy? There isn't a black person in it, and there isn't one funny thing in it either.<br /><br />Walmart buys these things up somehow and puts them on their dollar rack. It's labeled Unrated. I think they took out the topless scene. They may have taken out other stuff too, who knows? All we know is that whatever they took out, isn't there any more.<br /><br />The acting seemed OK to me. There's a lot of unfathomables tho. It's supposed to be a city? It's supposed to be a big lake? If it's so hot in the church people are fanning themselves, why are they all wearing coats?" Label: 0 Review: b'Well, was Morgan Freeman any more unusual as God than George Burns? This film sure was better than that bore, "Oh, God". I was totally engrossed and LMAO all the way through. Carrey was perfect as the out of sorts anchorman wannabe, and Aniston carried off her part as the frustrated girlfriend in her usual well played performance. I, for one, don\'t consider her to be either ugly or untalented. I think my favorite scene was when Carrey opened up the file cabinet thinking it could never hold his life history. See if you can spot the file in the cabinet that holds the events of his bathroom humor: I was rolling over this one. Well written and even better played out, this comedy will go down as one of this funnyman\'s best.' Label: 1 Review: b'I remember stumbling upon this special while channel-surfing in 1965. I had never heard of Barbra before. When the show was over, I thought "This is probably the best thing on TV I will ever see in my life." 42 years later, that has held true. There is still nothing so amazing, so honestly astonishing as the talent that was displayed here. You can talk about all the super-stars you want to, this is the most superlative of them all!<br /><br />You name it, she can do it. Comedy, pathos, sultry seduction, ballads, Barbra is truly a story-teller. Her ability to pull off anything she attempts is legendary. But this special was made in the beginning, and helped to create the legend that she quickly became. In spite of rising so far in such a short time, she has fulfilled the promise, revealing more of her talents as she went along. But they are all here from the very beginning. You will not be disappointed in viewing this.' Label: 1 Review: b"Firstly, I would like to point out that people who have criticised this film have made some glaring errors. Anything that has a rating below 6/10 is clearly utter nonsense.<br /><br />Creep is an absolutely fantastic film with amazing film effects. The actors are highly believable, the narrative thought provoking and the horror and graphical content extremely disturbing. <br /><br />There is much mystique in this film. Many questions arise as the audience are revealed to the strange and freakish creature that makes habitat in the dark rat ridden tunnels. How was 'Craig' created and what happened to him?<br /><br />A fantastic film with a large chill factor. A film with so many unanswered questions and a film that needs to be appreciated along with others like 28 Days Later, The Bunker, Dog Soldiers and Deathwatch.<br /><br />Look forward to more of these fantastic films!!" Label: 1 Review: b"I'm sorry but I didn't like this doc very much. I can think of a million ways it could have been better. The people who made it obviously don't have much imagination. The interviews aren't very interesting and no real insight is offered. The footage isn't assembled in a very informative way, either. It's too bad because this is a movie that really deserves spellbinding special features. One thing I'll say is that Isabella Rosselini gets more beautiful the older she gets. All considered, this only gets a '4.'" Label: 0
Anda sekarang dapat melakukan praproses data dan melatih model seperti sebelumnya.
Siapkan dataset untuk pelatihan
vectorize_layer = TextVectorization(
max_tokens=VOCAB_SIZE,
output_mode='int',
output_sequence_length=MAX_SEQUENCE_LENGTH)
# Make a text-only dataset (without labels), then call `TextVectorization.adapt`.
train_text = train_ds.map(lambda text, labels: text)
vectorize_layer.adapt(train_text)
def vectorize_text(text, label):
text = tf.expand_dims(text, -1)
return vectorize_layer(text), label
train_ds = train_ds.map(vectorize_text)
val_ds = val_ds.map(vectorize_text)
# Configure datasets for performance as before.
train_ds = configure_dataset(train_ds)
val_ds = configure_dataset(val_ds)
Buat, konfigurasikan, dan latih modelnya
model = create_model(vocab_size=VOCAB_SIZE + 1, num_labels=1)
model.summary()
Model: "sequential_5"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_2 (Embedding) (None, None, 64) 640064
conv1d_2 (Conv1D) (None, None, 64) 20544
global_max_pooling1d_2 (Glo (None, 64) 0
balMaxPooling1D)
dense_3 (Dense) (None, 1) 65
=================================================================
Total params: 660,673
Trainable params: 660,673
Non-trainable params: 0
_________________________________________________________________
model.compile(
loss=losses.BinaryCrossentropy(from_logits=True),
optimizer='adam',
metrics=['accuracy'])
history = model.fit(train_ds, validation_data=val_ds, epochs=3)
Epoch 1/3 313/313 [==============================] - 3s 7ms/step - loss: 0.5417 - accuracy: 0.6618 - val_loss: 0.3752 - val_accuracy: 0.8244 Epoch 2/3 313/313 [==============================] - 1s 4ms/step - loss: 0.2996 - accuracy: 0.8680 - val_loss: 0.3165 - val_accuracy: 0.8632 Epoch 3/3 313/313 [==============================] - 1s 4ms/step - loss: 0.1845 - accuracy: 0.9276 - val_loss: 0.3217 - val_accuracy: 0.8674
loss, accuracy = model.evaluate(val_ds)
print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))
79/79 [==============================] - 0s 2ms/step - loss: 0.3217 - accuracy: 0.8674 Loss: 0.32172858715057373 Accuracy: 86.74%
Ekspor modelnya
export_model = tf.keras.Sequential(
[vectorize_layer, model,
layers.Activation('sigmoid')])
export_model.compile(
loss=losses.SparseCategoricalCrossentropy(from_logits=False),
optimizer='adam',
metrics=['accuracy'])
# 0 --> negative review
# 1 --> positive review
inputs = [
"This is a fantastic movie.",
"This is a bad movie.",
"This movie was so bad that it was good.",
"I will never say yes to watching this movie.",
]
predicted_scores = export_model.predict(inputs)
predicted_labels = [int(round(x[0])) for x in predicted_scores]
for input, label in zip(inputs, predicted_labels):
print("Question: ", input)
print("Predicted label: ", label)
Question: This is a fantastic movie. Predicted label: 1 Question: This is a bad movie. Predicted label: 0 Question: This movie was so bad that it was good. Predicted label: 0 Question: I will never say yes to watching this movie. Predicted label: 0
Kesimpulan
Tutorial ini menunjukkan beberapa cara untuk memuat dan memproses teks sebelumnya. Sebagai langkah selanjutnya, Anda dapat menjelajahi tutorial Teks TensorFlow prapemrosesan teks tambahan, seperti:
Anda juga dapat menemukan set data baru di TensorFlow Datasets . Dan, untuk mempelajari lebih lanjut tentang tf.data , lihat panduan membangun saluran pipa input .