ValueError: Error when checking input: expected input_1 to have 3 dimensions,

Question

kerasでseq2seqのサンプルコードを動かしてみたのですが、何故か動かず困っています.
どこをどのように直せば良いかわからないので、ご教授願います

Using TensorFlow backend.
WARNING:tensorflow:From /Users/mac/.pyenv/versions/3.6.3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
(100000, 1, 6, 51) (100000, 1, 3, 51) (100000, 1, 3, 51)
Traceback (most recent call last):
  File "sample_seq2seq.py", line 91, in <module>
    train.fit([X1, X2], y, epochs=1)
  File "/Users/mac/.pyenv/versions/3.6.3/lib/python3.6/site-packages/keras/engine/training.py", line 1089, in fit
    batch_size=batch_size)
  File "/Users/mac/.pyenv/versions/3.6.3/lib/python3.6/site-packages/keras/engine/training.py", line 757, in _standardize_user_data
    exception_prefix='input')
  File "/Users/mac/.pyenv/versions/3.6.3/lib/python3.6/site-packages/keras/engine/training_utils.py", line 131, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (100000, 1, 6, 51)

from random import randint
from numpy import array
from numpy import argmax
from numpy import array_equal
from keras.utils import to_categorical
from keras.models import Model
from keras.layers import Input
from keras.layers import LSTM
from keras.layers import Dense
# generate a sequence of random integers
def generate_sequence(length, n_unique):
    return [randint(1, n_unique-1) for _ in range(length)]
# prepare data for the LSTM
def get_dataset(n_in, n_out, cardinality, n_samples):
    X1, X2, y = list(), list(), list()
    for _ in range(n_samples):
        # generate source sequence
        source = generate_sequence(n_in, cardinality)
        # define padded target sequence
        target = source[:n_out]
        target.reverse()
        # create padded input target sequence
        target_in = [0] + target[:-1]
        # encode
        src_encoded = to_categorical([source], num_classes=cardinality)
        tar_encoded = to_categorical([target], num_classes=cardinality)
        tar2_encoded = to_categorical([target_in], num_classes=cardinality)
        # store
        X1.append(src_encoded)
        X2.append(tar2_encoded)
        y.append(tar_encoded)
    return array(X1), array(X2), array(y)
# returns train, inference_encoder and inference_decoder models
def define_models(n_input, n_output, n_units):
    # define training encoder
    encoder_inputs = Input(shape=(None, n_input,))
    encoder = LSTM(n_units, return_state=True)
    encoder_outputs, state_h, state_c = encoder(encoder_inputs)
    encoder_states = [state_h, state_c]
    # define training decoder
    decoder_inputs = Input(shape=(None, n_output))
    decoder_lstm = LSTM(n_units, return_sequences=True, return_state=True)
    decoder_outputs, _, _ = decoder_lstm(decoder_inputs, initial_state=encoder_states)
    decoder_dense = Dense(n_output, activation='softmax')
    decoder_outputs = decoder_dense(decoder_outputs)
    model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
    # define inference encoder
    encoder_model = Model(encoder_inputs, encoder_states)
    # define inference decoder
    decoder_state_input_h = Input(shape=(n_units,))
    decoder_state_input_c = Input(shape=(n_units,))
    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)
    # return all models
    return model, encoder_model, decoder_model
# generate target given source sequence
def predict_sequence(infenc, infdec, source, n_steps, cardinality):
    # encode
    state = infenc.predict(source)
    # start of sequence input
    target_seq = array([0.0 for _ in range(cardinality)]).reshape(1, 1, cardinality)
    # collect predictions
    output = list()
    for t in range(n_steps):
        # predict next char
        yhat, h, c = infdec.predict([target_seq] + state)
        # store prediction
        output.append(yhat[0,0,:])
        # update state
        state = [h, c]
        # update target sequence
        target_seq = yhat
    return array(output)
# decode a one hot encoded string
def one_hot_decode(encoded_seq):
    return [argmax(vector) for vector in encoded_seq]
# configure problem
n_features = 50 + 1
n_steps_in = 6
n_steps_out = 3
# define model
train, infenc, infdec = define_models(n_features, n_features, 128)
train.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['acc'])
# generate training dataset
X1, X2, y = get_dataset(n_steps_in, n_steps_out, n_features, 100000)
print(X1.shape,X2.shape,y.shape)
# train model
train.fit([X1, X2], y, epochs=1)
# evaluate LSTM
total, correct = 100, 0
for _ in range(total):
    X1, X2, y = get_dataset(n_steps_in, n_steps_out, n_features, 1)
    target = predict_sequence(infenc, infdec, X1, n_steps_out, n_features)
    if array_equal(one_hot_decode(y[0]), one_hot_decode(target)):
        correct += 1
print('Accuracy: %.2f%%' % (float(correct)/float(total)*100.0))
# spot check some examples
for _ in range(10):
    X1, X2, y = get_dataset(n_steps_in, n_steps_out, n_features, 1)
    target = predict_sequence(infenc, infdec, X1, n_steps_out, n_features)
    print('X=%s y=%s, yhat=%s' % (one_hot_decode(X1[0]), one_hot_decode(y[0]), one_hot_decode(target)))

Answer 1

まずはErrorと記述されている内容に着目してみましょう
ValueError: Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (100000, 1, 6, 51)

英語で意味がわからないというのであればGoogle翻訳を使います。
基本的にエラーの内容を調べるのに翻訳ツールは日常的に使うようにしたほうが良いです。
一部の言語を除いて日本語でエラーの内容が出てくることは無いので。

翻訳結果↓
ValueError：入力のチェック中にエラーが発生しました：input_1は3次元であることが期待されていますが、形状（100000、1、6、51）の配列を取得しました

これだけを見ると求められる入力値は3次元に対し、4次元で指定しているのが原因のように見受けられます。
この情報を元に原因を調査してみてはいかがでしょうか。

Comments

[tome_neko]

回答ありがとうございます。次元数を調整したらちゃんと動くようになりました。ありがとうございます。これからもちゃんとエラー文を読めるように頑張ります（笑）