Google I/O adalah bungkusnya! Ikuti sesi TensorFlow

# Klasifikasi teks dengan RNN

Tutorial klasifikasi teks melatih jaringan saraf berulang pada IMDB film besar tinjauan dataset untuk analisis sentimen.

## Mempersiapkan

``````import numpy as np

import tensorflow_datasets as tfds
import tensorflow as tf

tfds.disable_progress_bar()
``````

Impor `matplotlib` dan membuat fungsi pembantu plot grafik:

``````import matplotlib.pyplot as plt

def plot_graphs(history, metric):
plt.plot(history.history[metric])
plt.plot(history.history['val_'+metric], '')
plt.xlabel("Epochs")
plt.ylabel(metric)
plt.legend([metric, 'val_'+metric])
``````

## Siapkan pipa input

The IMDB besar review film dataset adalah biner klasifikasi dataset-semua ulasan telah baik positif atau sentimen negatif.

Men-download dataset menggunakan TFDS . Lihat teks tutorial bongkar untuk rincian tentang bagaimana untuk memuat semacam ini data secara manual.

``````dataset, info = tfds.load('imdb_reviews', with_info=True,
as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']

train_dataset.element_spec
``````
```(TensorSpec(shape=(), dtype=tf.string, name=None),
TensorSpec(shape=(), dtype=tf.int64, name=None))
```

Awalnya ini mengembalikan set data (teks, pasangan label):

``````for example, label in train_dataset.take(1):
print('text: ', example.numpy())
print('label: ', label.numpy())
``````
```text:  b"This was an absolutely terrible movie. Don't be lured in by Christopher Walken or Michael Ironside. Both are great actors, but this must simply be their worst role in history. Even their great acting could not redeem this movie's ridiculous storyline. This movie is an early nineties US propaganda piece. The most pathetic scenes were those when the Columbian rebels were making their cases for revolutions. Maria Conchita Alonso appeared phony, and her pseudo-love affair with Walken was nothing but a pathetic emotional plug in a movie that was devoid of any real meaning. I am disappointed that there are movies like this, ruining actor's like Christopher Walken's good name. I could barely sit through it."
label:  0
```

Berikutnya mengocok data untuk pelatihan dan menciptakan batch ini `(text, label)` pasangan:

``````BUFFER_SIZE = 10000
BATCH_SIZE = 64
``````
``````train_dataset = train_dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)
test_dataset = test_dataset.batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)
``````
``````for example, label in train_dataset.take(1):
print('texts: ', example.numpy()[:3])
print()
print('labels: ', label.numpy()[:3])
``````
```texts:  [b'This is arguably the worst film I have ever seen, and I have quite an appetite for awful (and good) movies. It could (just) have managed a kind of adolescent humour if it had been consistently tongue-in-cheek --\xc3\xa0 la ROCKY HORROR PICTURE SHOW, which was really very funny. Other movies, like PLAN NINE FROM OUTER SPACE, manage to be funny while (apparently) trying to be serious. As to the acting, it looks like they rounded up brain-dead teenagers and asked them to ad-lib the whole production. Compared to them, Tom Cruise looks like Alec Guinness. There was one decent interpretation -- that of the older ghoul-busting broad on the motorcycle.'
b"I saw this film in the worst possible circumstance. I'd already missed 15 minutes when I woke up to it on an international flight between Sydney and Seoul. I didn't know what I was watching, I thought maybe it was a movie of the week, but quickly became riveted by the performance of the lead actress playing a young woman who's child had been kidnapped. The premise started taking twist and turns I didn't see coming and by the end credits I was scrambling through the the in-flight guide to figure out what I had just watched. Turns out I was belatedly discovering Do-yeon Jeon who'd won Best Actress at Cannes for the role. I don't know if Secret Sunshine is typical of Korean cinema but I'm off to the DVD store to discover more."

labels:  [0 1 0]
```

## Buat pembuat kode teks

Teks mentah dimuat oleh `tfds` perlu diolah sebelum dapat digunakan dalam model. Cara paling mudah untuk proses teks untuk pelatihan menggunakan `TextVectorization` lapisan. Lapisan ini memiliki banyak kemampuan, tetapi tutorial ini tetap pada perilaku default.

Buat layer, dan lulus teks dataset untuk layer `.adapt` metode:

``````VOCAB_SIZE = 1000
encoder = tf.keras.layers.TextVectorization(
max_tokens=VOCAB_SIZE)
encoder.adapt(train_dataset.map(lambda text, label: text))
``````

The `.adapt` metode menetapkan kosakata layer. Berikut adalah 20 token pertama. Setelah padding dan token yang tidak diketahui, mereka diurutkan berdasarkan frekuensi:

``````vocab = np.array(encoder.get_vocabulary())
vocab[:20]
``````
```array(['', '[UNK]', 'the', 'and', 'a', 'of', 'to', 'is', 'in', 'it', 'i',
'this', 'that', 'br', 'was', 'as', 'for', 'with', 'movie', 'but'],
dtype='<U14')
```

Setelah kosakata diatur, lapisan dapat mengkodekan teks ke dalam indeks. The tensor indeks adalah 0-empuk dengan urutan terpanjang di batch (kecuali Anda menetapkan tetap `output_sequence_length` ):

``````encoded_example = encoder(example)[:3].numpy()
encoded_example
``````
```array([[ 11,   7,   1, ...,   0,   0,   0],
[ 10, 208,  11, ...,   0,   0,   0],
[  1,  10, 237, ...,   0,   0,   0]])
```

Dengan pengaturan default, prosesnya tidak sepenuhnya dapat dibalik. Ada tiga alasan utama untuk itu:

1. Nilai default untuk `preprocessing.TextVectorization` 's `standardize` argumen adalah `"lower_and_strip_punctuation"` .
2. Ukuran kosakata yang terbatas dan kurangnya fallback berbasis karakter menghasilkan beberapa token yang tidak diketahui.
``````for n in range(3):
print("Original: ", example[n].numpy())
print("Round-trip: ", " ".join(vocab[encoded_example[n]]))
print()
``````
```Original:  b'This is arguably the worst film I have ever seen, and I have quite an appetite for awful (and good) movies. It could (just) have managed a kind of adolescent humour if it had been consistently tongue-in-cheek --\xc3\xa0 la ROCKY HORROR PICTURE SHOW, which was really very funny. Other movies, like PLAN NINE FROM OUTER SPACE, manage to be funny while (apparently) trying to be serious. As to the acting, it looks like they rounded up brain-dead teenagers and asked them to ad-lib the whole production. Compared to them, Tom Cruise looks like Alec Guinness. There was one decent interpretation -- that of the older ghoul-busting broad on the motorcycle.'
Round-trip:  this is [UNK] the worst film i have ever seen and i have quite an [UNK] for awful and good movies it could just have [UNK] a kind of [UNK] [UNK] if it had been [UNK] [UNK] [UNK] la [UNK] horror picture show which was really very funny other movies like [UNK] [UNK] from [UNK] space [UNK] to be funny while apparently trying to be serious as to the acting it looks like they [UNK] up [UNK] [UNK] and [UNK] them to [UNK] the whole production [UNK] to them tom [UNK] looks like [UNK] [UNK] there was one decent [UNK] that of the older [UNK] [UNK] on the [UNK]

Original:  b"I saw this film in the worst possible circumstance. I'd already missed 15 minutes when I woke up to it on an international flight between Sydney and Seoul. I didn't know what I was watching, I thought maybe it was a movie of the week, but quickly became riveted by the performance of the lead actress playing a young woman who's child had been kidnapped. The premise started taking twist and turns I didn't see coming and by the end credits I was scrambling through the the in-flight guide to figure out what I had just watched. Turns out I was belatedly discovering Do-yeon Jeon who'd won Best Actress at Cannes for the role. I don't know if Secret Sunshine is typical of Korean cinema but I'm off to the DVD store to discover more."
Round-trip:  i saw this film in the worst possible [UNK] id already [UNK] [UNK] minutes when i [UNK] up to it on an [UNK] [UNK] between [UNK] and [UNK] i didnt know what i was watching i thought maybe it was a movie of the [UNK] but quickly became [UNK] by the performance of the lead actress playing a young woman whos child had been [UNK] the premise started taking twist and turns i didnt see coming and by the end credits i was [UNK] through the the [UNK] [UNK] to figure out what i had just watched turns out i was [UNK] [UNK] [UNK] [UNK] [UNK] [UNK] best actress at [UNK] for the role i dont know if secret [UNK] is typical of [UNK] cinema but im off to the dvd [UNK] to [UNK] more

Round-trip:  [UNK] i am paul [UNK] [UNK] [UNK] [UNK] of [UNK] [UNK] [UNK] in [UNK] let me tell you about this god awful movie that [UNK] on [UNK] [UNK] film career but was [UNK] after a short [UNK] br going [UNK] is about an [UNK] [UNK] played by [UNK] who gets a job on a [UNK] [UNK] and [UNK] so i thought [UNK] [UNK] [UNK] that like history of the world part 1 and [UNK] the [UNK] were supposed to be [UNK] but actually they get [UNK] by [UNK] the [UNK] [UNK] the world has ever known [UNK] [UNK] [UNK] bad in going [UNK] but [UNK] better in big [UNK] [UNK] [UNK] and [UNK] [UNK] favorite [UNK] first [UNK] man [UNK] [UNK] was one hot [UNK] [UNK] is red hot going [UNK] [UNK] [UNK] [UNK] end of [UNK]
```

## Buat modelnya

Di atas adalah diagram model.

1. Model ini dapat membangun sebagai `tf.keras.Sequential` .

2. Lapisan pertama adalah `encoder` , yang mengubah teks ke urutan indeks tanda.

3. Setelah encoder adalah lapisan embedding. Lapisan embedding menyimpan satu vektor per kata. Ketika dipanggil, itu mengubah urutan indeks kata menjadi urutan vektor. Vektor ini dapat dilatih. Setelah pelatihan (pada data yang cukup), kata-kata dengan arti yang sama sering kali memiliki vektor yang serupa.

Ini indeks-lookup jauh lebih efisien daripada operasi setara melewati vektor encoded satu-panas melalui `tf.keras.layers.Dense` lapisan.

4. Sebuah jaringan saraf berulang (RNN) memproses input urutan dengan iterasi melalui elemen. RNN melewatkan output dari satu timestep ke input mereka di timestep berikutnya.

The `tf.keras.layers.Bidirectional` wrapper juga dapat digunakan dengan lapisan RNN. Ini menyebarkan input maju dan mundur melalui lapisan RNN dan kemudian menggabungkan output akhir.

• Keuntungan utama dari RNN dua arah adalah bahwa sinyal dari awal input tidak perlu diproses sepanjang setiap langkah waktu untuk mempengaruhi output.

• Kerugian utama dari RNN dua arah adalah Anda tidak dapat mengalirkan prediksi secara efisien karena kata-kata ditambahkan di akhir.

5. Setelah RNN telah dikonversi urutan ke vektor tunggal dua `layers.Dense` melakukan beberapa pemrosesan akhir, dan mengkonversi dari representasi vektor ini ke logit tunggal sebagai output klasifikasi.

Kode untuk mengimplementasikan ini di bawah ini:

``````model = tf.keras.Sequential([
encoder,
tf.keras.layers.Embedding(
input_dim=len(encoder.get_vocabulary()),
output_dim=64,
# Use masking to handle the variable sequence lengths
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(1)
])
``````

Harap dicatat bahwa model sekuensial Keras digunakan di sini karena semua lapisan dalam model hanya memiliki input tunggal dan menghasilkan output tunggal. Jika Anda ingin menggunakan lapisan RNN stateful, Anda mungkin ingin membangun model Anda dengan API fungsional Keras atau subkelas model sehingga Anda dapat mengambil dan menggunakan kembali status lapisan RNN. Silakan periksa Keras RNN panduan untuk rincian lebih lanjut.

The embedding lapisan menggunakan masking untuk menangani berbagai urut-panjang. Semua lapisan setelah `Embedding` dukungan masking:

``````print([layer.supports_masking for layer in model.layers])
``````
```[False, True, True, True, True]
```

Untuk memastikan bahwa ini berfungsi seperti yang diharapkan, evaluasi sebuah kalimat dua kali. Pertama, sendiri sehingga tidak ada padding untuk menutupi:

``````# predict on a sample text without padding.

sample_text = ('The movie was cool. The animation and the graphics '
'were out of this world. I would recommend this movie.')
predictions = model.predict(np.array([sample_text]))
print(predictions[0])
``````
```[-0.00012211]
```

Sekarang, evaluasi lagi dalam batch dengan kalimat yang lebih panjang. Hasilnya harus identik:

``````# predict on a sample text with padding

padding = "the " * 2000
predictions = model.predict(np.array([sample_text, padding]))
print(predictions[0])
``````
```[-0.00012211]
```

Kompilasi model Keras untuk mengonfigurasi proses pelatihan:

``````model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=['accuracy'])
``````

## Latih modelnya

``````history = model.fit(train_dataset, epochs=10,
validation_data=test_dataset,
validation_steps=30)
``````
```Epoch 1/10
391/391 [==============================] - 39s 84ms/step - loss: 0.6454 - accuracy: 0.5630 - val_loss: 0.4888 - val_accuracy: 0.7568
Epoch 2/10
391/391 [==============================] - 30s 75ms/step - loss: 0.3925 - accuracy: 0.8200 - val_loss: 0.3663 - val_accuracy: 0.8464
Epoch 3/10
391/391 [==============================] - 30s 75ms/step - loss: 0.3319 - accuracy: 0.8525 - val_loss: 0.3402 - val_accuracy: 0.8385
Epoch 4/10
391/391 [==============================] - 30s 75ms/step - loss: 0.3183 - accuracy: 0.8616 - val_loss: 0.3289 - val_accuracy: 0.8438
Epoch 5/10
391/391 [==============================] - 30s 75ms/step - loss: 0.3088 - accuracy: 0.8656 - val_loss: 0.3254 - val_accuracy: 0.8646
Epoch 6/10
391/391 [==============================] - 32s 81ms/step - loss: 0.3043 - accuracy: 0.8686 - val_loss: 0.3242 - val_accuracy: 0.8521
Epoch 7/10
391/391 [==============================] - 30s 76ms/step - loss: 0.3019 - accuracy: 0.8696 - val_loss: 0.3315 - val_accuracy: 0.8609
Epoch 8/10
391/391 [==============================] - 32s 76ms/step - loss: 0.3007 - accuracy: 0.8688 - val_loss: 0.3245 - val_accuracy: 0.8609
Epoch 9/10
391/391 [==============================] - 31s 77ms/step - loss: 0.2981 - accuracy: 0.8707 - val_loss: 0.3294 - val_accuracy: 0.8599
Epoch 10/10
391/391 [==============================] - 31s 78ms/step - loss: 0.2969 - accuracy: 0.8742 - val_loss: 0.3218 - val_accuracy: 0.8547
```
``````test_loss, test_acc = model.evaluate(test_dataset)

print('Test Loss:', test_loss)
print('Test Accuracy:', test_acc)
``````
```391/391 [==============================] - 15s 38ms/step - loss: 0.3185 - accuracy: 0.8582
Test Loss: 0.3184521794319153
Test Accuracy: 0.8581600189208984
```
``````plt.figure(figsize=(16, 8))
plt.subplot(1, 2, 1)
plot_graphs(history, 'accuracy')
plt.ylim(None, 1)
plt.subplot(1, 2, 2)
plot_graphs(history, 'loss')
plt.ylim(0, None)
``````
```(0.0, 0.6627909764647484)
```

Jalankan prediksi pada kalimat baru:

Jika prediksinya >= 0,0, maka positif jika tidak maka negatif.

``````sample_text = ('The movie was cool. The animation and the graphics '
'were out of this world. I would recommend this movie.')
predictions = model.predict(np.array([sample_text]))
``````

## Tumpuk dua atau lebih lapisan LSTM

Keras lapisan berulang memiliki dua mode yang tersedia yang dikendalikan oleh `return_sequences` argumen konstruktor:

• Jika `False` itu kembali hanya output terakhir untuk setiap urutan input (tensor 2D bentuk (batch_size, output_features)). Ini adalah default, yang digunakan pada model sebelumnya.

• Jika `True` urutan penuh output berturut-turut untuk setiap timestep dikembalikan (tensor 3D bentuk `(batch_size, timesteps, output_features)` ).

Berikut adalah apa arus informasi terlihat seperti dengan `return_sequences=True` :

Hal yang menarik tentang menggunakan `RNN` dengan `return_sequences=True` adalah bahwa output masih memiliki 3-sumbu, seperti input, sehingga dapat dikirimkan ke lapisan RNN lain, seperti ini:

``````model = tf.keras.Sequential([
encoder,
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64,  return_sequences=True)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(1)
])
``````
``````model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=['accuracy'])
``````
``````history = model.fit(train_dataset, epochs=10,
validation_data=test_dataset,
validation_steps=30)
``````
```Epoch 1/10
391/391 [==============================] - 71s 149ms/step - loss: 0.6502 - accuracy: 0.5625 - val_loss: 0.4923 - val_accuracy: 0.7573
Epoch 2/10
391/391 [==============================] - 55s 138ms/step - loss: 0.4067 - accuracy: 0.8198 - val_loss: 0.3727 - val_accuracy: 0.8271
Epoch 3/10
391/391 [==============================] - 54s 136ms/step - loss: 0.3417 - accuracy: 0.8543 - val_loss: 0.3343 - val_accuracy: 0.8510
Epoch 4/10
391/391 [==============================] - 53s 134ms/step - loss: 0.3242 - accuracy: 0.8607 - val_loss: 0.3268 - val_accuracy: 0.8568
Epoch 5/10
391/391 [==============================] - 53s 135ms/step - loss: 0.3174 - accuracy: 0.8652 - val_loss: 0.3213 - val_accuracy: 0.8516
Epoch 6/10
391/391 [==============================] - 52s 132ms/step - loss: 0.3098 - accuracy: 0.8671 - val_loss: 0.3294 - val_accuracy: 0.8547
Epoch 7/10
391/391 [==============================] - 53s 134ms/step - loss: 0.3063 - accuracy: 0.8697 - val_loss: 0.3158 - val_accuracy: 0.8594
Epoch 8/10
391/391 [==============================] - 52s 132ms/step - loss: 0.3043 - accuracy: 0.8692 - val_loss: 0.3184 - val_accuracy: 0.8521
Epoch 9/10
391/391 [==============================] - 53s 133ms/step - loss: 0.3016 - accuracy: 0.8704 - val_loss: 0.3208 - val_accuracy: 0.8609
Epoch 10/10
391/391 [==============================] - 54s 136ms/step - loss: 0.2975 - accuracy: 0.8740 - val_loss: 0.3301 - val_accuracy: 0.8651
```
``````test_loss, test_acc = model.evaluate(test_dataset)

print('Test Loss:', test_loss)
print('Test Accuracy:', test_acc)
``````
```391/391 [==============================] - 26s 65ms/step - loss: 0.3293 - accuracy: 0.8646
Test Loss: 0.329334557056427
Test Accuracy: 0.8646399974822998
```
``````# predict on a sample text without padding.

sample_text = ('The movie was not good. The animation and the graphics '
'were terrible. I would not recommend this movie.')
predictions = model.predict(np.array([sample_text]))
print(predictions)
``````
```[[-1.6796288]]
```
``````plt.figure(figsize=(16, 6))
plt.subplot(1, 2, 1)
plot_graphs(history, 'accuracy')
plt.subplot(1, 2, 2)
plot_graphs(history, 'loss')
``````

Periksa lapisan berulang lainnya yang ada seperti lapisan GRU .

Jika Anda sedang interestied dalam membangun RNNs kustom, lihat Keras RNN Panduan .

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Missing the information I need" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Too complicated / too many steps" },{ "type": "thumb-down", "id": "outOfDate", "label":"Out of date" },{ "type": "thumb-down", "id": "translationIssue", "label":"Translation issue" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Masalah kode / contoh" },{ "type": "thumb-down", "id": "otherDown", "label":"Other" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Easy to understand" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Solved my problem" },{ "type": "thumb-up", "id": "otherUp", "label":"Other" }]