Keras TensorFlow Hub：简单ELMO网络入门

import tensorflow as tf import tensorflow_hub as hub import re from tensorflow import keras import tensorflow.keras from tensorflow.keras.layers import Input, Dense,Flatten import numpy as np import keras.callbacks import io from sklearn.model_selection import train_test_split i = 0 max_cells = 51 #countLines() x_data = np.zeros((max_cells, 10, 1), dtype='object') y_data = np.zeros((max_cells, 3), dtype='float32') seqs = np.zeros((max_cells), dtype='int32') with io.open('./data/names-sample.txt', encoding='utf-8') as f: content = f.readlines() for line in content: line = re.sub("[\n]", " ", line) tokens = line.split() for t in range(0, min(10,len(tokens))): tkn = tokens[t] x_data[i,t] = tkn seqs[i] = len(tokens) y_data[i,0] = 1 i = i+1 def build_model(): tokens = Input(shape=[10,], dtype=tf.string) seq_lens = Input(shape=[], dtype=tf.int32) elmo = hub.KerasLayer( "https://tfhub.dev/google/elmo/3", trainable=False, output_key="elmo", signature="tokens", ) out = elmo({"tokens": tokens, "sequence_len": seqs}) model = keras.Model(inputs=[tokens, seq_lens], outputs=out) model.compile("adam", loss="sparse_categorical_crossentropy") model.summary() return model x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.70, shuffle=True) model = build_model() model.fit(x_train, y_train,validation_data=(x_test, y_test),epochs=1,batch_size=32)

def build_model(): tokens = Input(shape=[10,], dtype=tf.string) seq_lens = Input(shape=[], dtype=tf.int32) elmo = hub.KerasLayer( "https://tfhub.dev/google/elmo/3", trainable=False, output_key="elmo", signature="tokens", ) out = elmo({"tokens": tokens, "sequence_len": seq_lens}) model = keras.Model(inputs=[tokens, seqs], outputs=out) model.compile("adam", loss="sparse_categorical_crossentropy") model.summary() return model

2条回答

网友

1楼 · 编辑于 2024-06-02 05:57:47

好的，终于开始工作了。我做的第一件事是升级：

Keras: 2.2.4
TF: 1.15.0
TF: 0.12.0

接下来更改了我的代码以使用正确版本的ELMO模型：

import tensorflow_hub as hub
import tensorflow as tf

elmo = hub.Module("https://tfhub.dev/google/elmo/3", trainable=False)

from tensorflow.keras.layers import Input, Lambda, Bidirectional, Dense, Dropout, Flatten, LSTM
from tensorflow.keras.models import Model

def ELMoEmbedding(input_text):
    return elmo(tf.reshape(tf.cast(input_text, tf.string), [-1]), signature="default", as_dict=True)["elmo"]

def build_model():
    input_layer = Input(shape=(1,), dtype="string", name="Input_layer")    
    embedding_layer = Lambda(ELMoEmbedding, output_shape=(1024, ), name="Elmo_Embedding")(input_layer)
    BiLSTM = Bidirectional(LSTM(128, return_sequences= False, recurrent_dropout=0.2, dropout=0.2), name="BiLSTM")(embedding_layer)
    Dense_layer_1 = Dense(64, activation='relu')(BiLSTM)
    Dropout_layer_1 = Dropout(0.5)(Dense_layer_1)
    Dense_layer_2 = Dense(32, activation='relu')(Dropout_layer_1)
    Dropout_layer_2 = Dropout(0.5)(Dense_layer_2)
    output_layer = Dense(3, activation='sigmoid')(Dropout_layer_2)
    model = Model(inputs=[input_layer], outputs=output_layer, name="BiLSTM with ELMo Embeddings")
    model.summary()
    model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
    return model
elmo_BiDirectional_model = build_model()

import numpy as np
import io
import re
from tensorflow import keras 

i = 0
max_cells = 300
x_data = np.zeros((max_cells, 1), dtype='object')
y_data = np.zeros((max_cells, 3), dtype='float32')

with tf.Session() as session:
    session.run(tf.global_variables_initializer()) 
    session.run(tf.tables_initializer())
    model_elmo = elmo_BiDirectional_model.fit(x_data, y_data, epochs=100, batch_size=5)
    train_prediction = elmo_BiDirectional_model.predict(x_data)

网友

2楼 · 编辑于 2024-06-02 05:57:47

我不认为这是一个错误，而是TF给了我们选择每种方法的自由。虽然我们可以将层子类与keras函数api混合匹配，但我想我们无法使模型子类与keras的模型api一起工作。在我看来，这就是急切执行和keras图形模式之间的区别产生冲突的地方，导致了这种“符号例外”

让TF事先知道它应该执行什么模式可以解决这个问题

相关问题更多 >

编程相关推荐

热门问题

热门文章