Seq2Seqの推論について

KerasでSeq2seqを使ってランダムな文字列からcrcを推定するというものを作っています.

元々あるサンプルプログラムを動かしてみると, テストデータの学習精度が53%で,損失値が0.66と結果が出ました.

しかし, いざ推論モデルを使って確認してみると, 何一つあっていませんでした.

この場合, 学習モデルの構築を変更すればいいのか, 推論モデルの構築を変更すればいいのかわかりません.

どうすれば良いのか, どなたかご教授お願いいたします.

実行したコード

from __future__ import print_function
import keras
from keras.models import Model
from keras.layers import Input, LSTM, Dense, Embedding, Add, BatchNormalization, Dropout, RNN
from keras.utils import plot_model
import pandas as pd
import numpy as np
import string
from string import digits
import matplotlib.pyplot as plt
import re
from sklearn.model_selection import train_test_split
#from keras.utils.visualize_util import plot

batch_size = 100  # Batch size for training.
epochs = 50  # Number of epochs to train for.
latent_dim = 64  # Latent dimensionality of the encoding space.
num_samples = 1000000  # Number of samples to train on.
# Path to the data txt file on disk.
data_path = 'datalist.txt'

# Vectorize the data.
input_texts = []
target_texts = []
input_characters = set()
target_characters = set()
with open(data_path, 'r', encoding='utf-8') as f:
    lines = f.read().split('\n')
for line in lines[: min(num_samples, len(lines) - 1)]:
    input_text, target_text = line.split()
    # We use "tab" as the "start sequence" character
    # for the targets, and "\n" as "end sequence" character.
    target_text =  target_text + '\n'
    input_texts.append(input_text)
    target_texts.append(target_text)
    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 = max([len(txt) for txt in input_texts])
max_decoder_seq_length = max([len(txt) for txt in target_texts])

print('Number of samples:', target_text)
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Max sequence length for inputs:', max_encoder_seq_length)
print('Max sequence length for outputs:', 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_texts), max_encoder_seq_length),
    dtype='float32')
decoder_input_data = np.zeros(
    (len(input_texts), max_decoder_seq_length),
    dtype='float32')
decoder_target_data = np.zeros(
    (len(input_texts), max_decoder_seq_length, num_decoder_tokens),
    dtype='float32')

for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):
    for t, char in enumerate(input_text):
        encoder_input_data[i, t] = input_token_index[char]
    for t, char in enumerate(target_text):
        # decoder_target_data is ahead of decoder_input_data by one timestep
        decoder_input_data[i, t] = target_token_index[char]
        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.

embedding_size = 512
encoder_inputs = Input(shape=(None,))
en_x=  Embedding(num_encoder_tokens, embedding_size)(encoder_inputs)
encoder = LSTM(64, dropout=0.5, return_state=True)
encoder_outputs, state_h, state_c = encoder(en_x)
# 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,))
dex=  Embedding(num_decoder_tokens, embedding_size)
final_dex= dex(decoder_inputs)
decoder_lstm = LSTM(64, dropout=0.5, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(final_dex,
                                     initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['acc'])
# Note that `decoder_target_data` needs to be one-hot encoded,
# rather than sequences of integers like `decoder_input_data`!
model.summary()
plot_model(model, to_file='model_gakusyu.png')
history  = model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
          batch_size=batch_size,
          epochs=epochs,
          validation_split=0.2)

acc = history.history["acc"]
val_acc = history.history["val_acc"]
epochs = range(1, len(acc) + 1)

#plt.plot(epochs, acc, "bo", label = "Training acc" )
#plt.plot(epochs, val_acc, "r", label = "Validation acc")
#plt.title("Training and Validation accuracy")
#plt.legend()
#plt.show()
# Save model
model.save('s2s.h5')


# Define sampling models
# define the encoder model
encoder_model = Model(encoder_inputs, encoder_states)
encoder_model.summary()
# Define sampling models

decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
final_dex2= dex(decoder_inputs)
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]


decoder_outputs2, state_h2, state_c2 = decoder_lstm(final_dex2, initial_state=decoder_states_inputs)
decoder_states2 = [state_h2, state_c2]
decoder_outputs2 = decoder_dense(decoder_outputs2)
decoder_model = Model(
    [decoder_inputs] + decoder_states_inputs,
    [decoder_outputs2] + decoder_states2)

# 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())

#plot_model(model, to_file='model_suiron.png')
# Reverse-lookup token index to decode sequences back to
# something readable.


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))
    # 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))
        target_seq[0, 0]= sampled_token_index

        # Update states
        states_value = [h, c]

    return decoded_sentence

for seq_index in range(100):
    # Take one sequence (part of the training set)
    # for trying out decoding.
   input_seq = encoder_input_data[seq_index: seq_index + 1]
   decoded_sentence = decode_sequence(input_seq)
   print('-')
   print('Input sentence:', input_texts[seq_index])
   print('Decoded sentence:', decoded_sentence)

データセット

HW7oN8bEDbXpuNqB 1001001111000111
SxiYZ,Q5KSd9dLfN 101011000000010
:yt2qI";uaslhKqR 10101110111100
UXNxU.cs~#gu):,o 111111111101
weP}f,)R(B7CUwk| 1101101110111001
Yq^L,TInUXc.GFVt 110111001111111
7Z5(;h3]]Dbq!*qH 1110001101000111
ZQ`PM^`>nQ-W,t^X 1000110110001100
7!JVJ3(m#og54&YE 1001111100001
8)CG)cZ|~t<1W&b. 1100110100000
BEk]eYJesVq!V~iK 1000011001000010
q;Zzrtj*OHIxuwnt 1100011100000101
!%Py#C=]?E}@vVKO 111110011110100
v=t>un)p|_.ujR%m 1100010100001111
:aQL&ver:}($2}aL 111001000110000
/RFk1_|w<OX)gv,* 10011011010001
8ju||f-}8RrNHR+e 1001000101000100
ICmq|%zT9pXqu)>q 101011111010
l;A"=|?,2<D_`t~T 1001001100110000
#DE0QjwY8{ZJXX[+ 101001101010
l#3-tE/nXR`Ts5G# 11111100000111
P:aM+&@3(g>5H_so 11001000111
(B2Y(2(/rF`2+.w- 111000011100001
dzHNO.j2LKn(&(aE 1111100001100000