带有 WTO 面板报告文本数据的解码器模型。代码如下
from __future__ import print_function
from keras.models import Model
from keras.layers import Input, LSTM, Dense
import numpy as np
batch_size = 64 # Batch size for training.
epochs = 100 # Number of epochs to train for.
latent_dim = 256 # Latent dimensionality of the encoding space.
input_characters = set()
target_characters = set()
input_text = open("/Users/zachary/Downloads//DS2_input_art_III.txt").read()
target_text = open("/Users/zachary/Downloads/DS_2_output_art_III.txt").read()
for char in input_text:
if char not in input_characters:
input_characters.add(char)
for char in target_text:
if char not in target_characters:
target_characters.add(char)
input_characters = sorted(list(input_characters))
target_characters = sorted(list(target_characters))
num_encoder_tokens = len(input_characters)
num_decoder_tokens = len(target_characters)
max_encoder_seq_length = len(input_text) #the max number of input text
max_decoder_seq_length = len(target_text) #the max number of output text
print('Number of samples:', len(input_text))
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Sequence length for input:', max_encoder_seq_length)
print('Sequence length for output:', max_decoder_seq_length)
input_token_index = dict(
[(char, i) for i, char in enumerate(input_characters)])
target_token_index = dict(
[(char, i) for i, char in enumerate(target_characters)])
encoder_input_data = np.zeros(
(len(input_text), max_encoder_seq_length, num_encoder_tokens),
dtype='float32')
decoder_input_data = np.zeros(
(len(input_text), max_decoder_seq_length, num_decoder_tokens),
dtype='float32')
decoder_target_data = np.zeros(
(len(input_text), max_decoder_seq_length, num_decoder_tokens),
dtype='float32')
for i, (input_text, target_text) in enumerate(zip(input_text, target_text)):
for t, char in enumerate(input_text):
encoder_input_data[i, t, input_token_index[char]] = 1.
print(encoder_input_data[i,t])
for t, char in enumerate(target_text):
decoder_input_data[i, t, target_token_index[char]] = 1.
if t > 0:
# decoder_target_data will be ahead by one timestep
# and will not include the start character.
decoder_target_data[i, t - 1, target_token_index[char]] = 1.
# Define an input sequence and process it.
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs) #encoder is the Keras function
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
# Run training
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
batch_size=batch_size,
epochs=epochs,
validation_split=0.2)
# Save model
model.save('s2s.h5')
# Define sampling models
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(
decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs] + decoder_states)
# Reverse-lookup token index to decode sequences back to
# something readable.
reverse_input_char_index = dict(
(i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict(
(i, char) for char, i in target_token_index.items())
# In[ ]:
def decode_sequence(input_seq):
# Encode the input as state vectors.
states_value = encoder_model.predict(input_seq)
# Generate empty target sequence of length 1.
target_seq = np.zeros((1, 1, num_decoder_tokens))
# Populate the first character of target sequence with the start character.
target_seq[0, 0, target_token_index['\t']] = 1.
# Sampling loop for a batch of sequences
# (to simplify, here we assume a batch of size 1).
stop_condition = False
decoded_sentence = ''
while not stop_condition:
output_tokens, h, c = decoder_model.predict(
[target_seq] + states_value)
# Sample a token
sampled_token_index = np.argmax(output_tokens[0, -1, :])
sampled_char = reverse_target_char_index[sampled_token_index]
decoded_sentence += sampled_char
# Exit condition: either hit max length
# or find stop character.
if (sampled_char == '\n' or
len(decoded_sentence) > max_decoder_seq_length):
stop_condition = True
# Update the target sequence (of length 1).
target_seq = np.zeros((1, 1, num_decoder_tokens))
target_seq[0, 0, sampled_token_index] = 1.
# Update states
states_value = [h, c]
return decoded_sentence
input_seq = open("/Users/zachary/Downloads/DS10_argued_GATTIII.txt").read()
decoded_sentence = decode_sequence(input_seq)
print('Decoded sentence:', decoded_sentence)
f = open('decoded_sentence','w')
f.write(decoded_sentence)
f.close()
我正在尝试在我的远程控制计算机中运行此代码，该计算机具有 64GB 内存和两个 Titan X，但它一直返回以下错误：
Using TensorFlow backend.
Number of samples: 34196
Number of unique input tokens: 70
Number of unique output tokens: 74
Max sequence length for inputs: 34196
Max sequence length for outputs: 17037
Traceback (most recent call last):
File "encoder-decoder WTO-18-1-15 (1).py", line 135, in <module>
(len(input_text), max_encoder_seq_length, num_encoder_tokens))
MemoryError
有一件事很奇怪，在我没有 gpu 的普通计算机上，有 16GB 内存，它不会返回相同代码的错误。
会有什么可疑的问题？