Spaces:
Running
Running
File size: 3,625 Bytes
9ce984a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
"""
Title: Text classification with Transformer
Author: [Apoorv Nandan](https://twitter.com/NandanApoorv)
Date created: 2020/05/10
Last modified: 2024/01/18
Description: Implement a Transformer block as a Keras layer and use it for text classification.
Accelerator: GPU
Converted to Keras 3 by: [Sitam Meur](https://github.com/sitamgithub-MSIT)
"""
"""
## Setup
"""
import keras
from keras import ops
from keras import layers
"""
## Implement a Transformer block as a layer
"""
class TransformerBlock(layers.Layer):
def __init__(self, embed_dim, num_heads, ff_dim, rate=0.1):
super().__init__()
self.att = layers.MultiHeadAttention(num_heads=num_heads, key_dim=embed_dim)
self.ffn = keras.Sequential(
[
layers.Dense(ff_dim, activation="relu"),
layers.Dense(embed_dim),
]
)
self.layernorm1 = layers.LayerNormalization(epsilon=1e-6)
self.layernorm2 = layers.LayerNormalization(epsilon=1e-6)
self.dropout1 = layers.Dropout(rate)
self.dropout2 = layers.Dropout(rate)
def call(self, inputs):
attn_output = self.att(inputs, inputs)
attn_output = self.dropout1(attn_output)
out1 = self.layernorm1(inputs + attn_output)
ffn_output = self.ffn(out1)
ffn_output = self.dropout2(ffn_output)
return self.layernorm2(out1 + ffn_output)
"""
## Implement embedding layer
Two separate embedding layers, one for tokens, one for token index (positions).
"""
class TokenAndPositionEmbedding(layers.Layer):
def __init__(self, maxlen, vocab_size, embed_dim):
super().__init__()
self.token_emb = layers.Embedding(input_dim=vocab_size, output_dim=embed_dim)
self.pos_emb = layers.Embedding(input_dim=maxlen, output_dim=embed_dim)
def call(self, x):
maxlen = ops.shape(x)[-1]
positions = ops.arange(start=0, stop=maxlen, step=1)
positions = self.pos_emb(positions)
x = self.token_emb(x)
return x + positions
"""
## Download and prepare dataset
"""
vocab_size = 20000 # Only consider the top 20k words
maxlen = 200 # Only consider the first 200 words of each movie review
(x_train, y_train), (x_val, y_val) = keras.datasets.imdb.load_data(num_words=vocab_size)
print(len(x_train), "Training sequences")
print(len(x_val), "Validation sequences")
x_train = keras.utils.pad_sequences(x_train, maxlen=maxlen)
x_val = keras.utils.pad_sequences(x_val, maxlen=maxlen)
"""
## Create classifier model using transformer layer
Transformer layer outputs one vector for each time step of our input sequence.
Here, we take the mean across all time steps and
use a feed forward network on top of it to classify text.
"""
embed_dim = 32 # Embedding size for each token
num_heads = 2 # Number of attention heads
ff_dim = 32 # Hidden layer size in feed forward network inside transformer
inputs = layers.Input(shape=(maxlen,))
embedding_layer = TokenAndPositionEmbedding(maxlen, vocab_size, embed_dim)
x = embedding_layer(inputs)
transformer_block = TransformerBlock(embed_dim, num_heads, ff_dim)
x = transformer_block(x)
x = layers.GlobalAveragePooling1D()(x)
x = layers.Dropout(0.1)(x)
x = layers.Dense(20, activation="relu")(x)
x = layers.Dropout(0.1)(x)
outputs = layers.Dense(2, activation="softmax")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
"""
## Train and Evaluate
"""
model.compile(
optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
)
history = model.fit(
x_train, y_train, batch_size=32, epochs=2, validation_data=(x_val, y_val)
)
|