Keras 레이어의 모양 이해

이 링크를 통해 텍스트 분류를위한 다중 채널 CNN 모델을 이해합니다.

코드는 이 튜토리얼을 기반으로 합니다.

나는 대부분의 것들을 이해했지만 Keras가 특정 레이어의 출력 모양을 어떻게 정의하는지 이해할 수 없습니다.

다음은 코드입니다.

4 그램, 6 그램, 8 그램의 영화 리뷰 텍스트를 처리하기위한 3 개의 입력 채널이있는 모델을 정의합니다.

#Skipped keras imports

# load a clean dataset
def load_dataset(filename):
    return load(open(filename, 'rb'))

# fit a tokenizer
def create_tokenizer(lines):
    tokenizer = Tokenizer()
    tokenizer.fit_on_texts(lines)
    return tokenizer

# calculate the maximum document length
def max_length(lines):
    return max([len(s.split()) for s in lines])

# encode a list of lines
def encode_text(tokenizer, lines, length):
    # integer encode
    encoded = tokenizer.texts_to_sequences(lines)
    # pad encoded sequences
    padded = pad_sequences(encoded, maxlen=length, padding='post')
    return padded

# define the model
def define_model(length, vocab_size):
    # channel 1
    inputs1 = Input(shape=(length,))
    embedding1 = Embedding(vocab_size, 100)(inputs1)
    conv1 = Conv1D(filters=32, kernel_size=4, activation='relu')(embedding1)
    drop1 = Dropout(0.5)(conv1)
    pool1 = MaxPooling1D(pool_size=2)(drop1)
    flat1 = Flatten()(pool1)
    # channel 2
    inputs2 = Input(shape=(length,))
    embedding2 = Embedding(vocab_size, 100)(inputs2)
    conv2 = Conv1D(filters=32, kernel_size=6, activation='relu')(embedding2)
    drop2 = Dropout(0.5)(conv2)
    pool2 = MaxPooling1D(pool_size=2)(drop2)
    flat2 = Flatten()(pool2)
    # channel 3
    inputs3 = Input(shape=(length,))
    embedding3 = Embedding(vocab_size, 100)(inputs3)
    conv3 = Conv1D(filters=32, kernel_size=8, activation='relu')(embedding3)
    drop3 = Dropout(0.5)(conv3)
    pool3 = MaxPooling1D(pool_size=2)(drop3)
    flat3 = Flatten()(pool3)
    # merge
    merged = concatenate([flat1, flat2, flat3])
    # interpretation
    dense1 = Dense(10, activation='relu')(merged)
    outputs = Dense(1, activation='sigmoid')(dense1)
    model = Model(inputs=[inputs1, inputs2, inputs3], outputs=outputs)
    # compile
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    # summarize
    print(model.summary())
    plot_model(model, show_shapes=True, to_file='multichannel.png')
    return model

# load training dataset
trainLines, trainLabels = load_dataset('train.pkl')
# create tokenizer
tokenizer = create_tokenizer(trainLines)
# calculate max document length
length = max_length(trainLines)
# calculate vocabulary size
vocab_size = len(tokenizer.word_index) + 1
print('Max document length: %d' % length)
print('Vocabulary size: %d' % vocab_size)
# encode data
trainX = encode_text(tokenizer, trainLines, length)
print(trainX.shape)

# define model
model = define_model(length, vocab_size)
# fit model
model.fit([trainX,trainX,trainX], array(trainLabels), epochs=10, batch_size=16)
# save the model
model.save('model.h5')

코드 실행 :

먼저 예제를 실행하면 준비된 훈련 데이터 세트의 요약이 인쇄됩니다. 최대 문서 길이 : 1380 어휘 크기 : 44277 (1800, 1380)

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to
====================================================================================================
input_1 (InputLayer)             (None, 1380)          0
____________________________________________________________________________________________________
input_2 (InputLayer)             (None, 1380)          0
____________________________________________________________________________________________________
input_3 (InputLayer)             (None, 1380)          0
____________________________________________________________________________________________________
embedding_1 (Embedding)          (None, 1380, 100)     4427700     input_1[0][0]
____________________________________________________________________________________________________
embedding_2 (Embedding)          (None, 1380, 100)     4427700     input_2[0][0]
____________________________________________________________________________________________________
embedding_3 (Embedding)          (None, 1380, 100)     4427700     input_3[0][0]
____________________________________________________________________________________________________
conv1d_1 (Conv1D)                (None, 1377, 32)      12832       embedding_1[0][0]
____________________________________________________________________________________________________
conv1d_2 (Conv1D)                (None, 1375, 32)      19232       embedding_2[0][0]
____________________________________________________________________________________________________
conv1d_3 (Conv1D)                (None, 1373, 32)      25632       embedding_3[0][0]
____________________________________________________________________________________________________
dropout_1 (Dropout)              (None, 1377, 32)      0           conv1d_1[0][0]
____________________________________________________________________________________________________
dropout_2 (Dropout)              (None, 1375, 32)      0           conv1d_2[0][0]
____________________________________________________________________________________________________
dropout_3 (Dropout)              (None, 1373, 32)      0           conv1d_3[0][0]
____________________________________________________________________________________________________
max_pooling1d_1 (MaxPooling1D)   (None, 688, 32)       0           dropout_1[0][0]
____________________________________________________________________________________________________
max_pooling1d_2 (MaxPooling1D)   (None, 687, 32)       0           dropout_2[0][0]
____________________________________________________________________________________________________
max_pooling1d_3 (MaxPooling1D)   (None, 686, 32)       0           dropout_3[0][0]
____________________________________________________________________________________________________
flatten_1 (Flatten)              (None, 22016)         0           max_pooling1d_1[0][0]
____________________________________________________________________________________________________
flatten_2 (Flatten)              (None, 21984)         0           max_pooling1d_2[0][0]
____________________________________________________________________________________________________
flatten_3 (Flatten)              (None, 21952)         0           max_pooling1d_3[0][0]
____________________________________________________________________________________________________
concatenate_1 (Concatenate)      (None, 65952)         0           flatten_1[0][0]
                                                                   flatten_2[0][0]
                                                                   flatten_3[0][0]
____________________________________________________________________________________________________
dense_1 (Dense)                  (None, 10)            659530      concatenate_1[0][0]
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 1)             11          dense_1[0][0]
====================================================================================================
Total params: 14,000,337
Trainable params: 14,000,337
Non-trainable params: 0
____________________________________________________________________________________________________

과

Epoch 6/10
1800/1800 [==============================] - 30s - loss: 9.9093e-04 - acc: 1.0000
Epoch 7/10
1800/1800 [==============================] - 29s - loss: 5.1899e-04 - acc: 1.0000
Epoch 8/10
1800/1800 [==============================] - 28s - loss: 3.7958e-04 - acc: 1.0000
Epoch 9/10
1800/1800 [==============================] - 29s - loss: 3.0534e-04 - acc: 1.0000
Epoch 10/10
1800/1800 [==============================] - 29s - loss: 2.6234e-04 - acc: 1.0000

레이어 및 출력 모양에 대한 나의 해석은 다음과 같습니다. 다차원에서 길을 잃었으므로 올바른지 이해하도록 도와주세요.

input_1 (InputLayer) (None, 1380) : ---> 1380는 데이터 포인트 당 총 특성 수 (즉, 1380 개의 입력 뉴런)입니다. 1800문서 또는 데이터 포인트의 총 수입니다.

embedding_1 (Embedding) (None, 1380, 100) 4427700 ----> Embedding layer is : 1380 as features (words) and each feature is a vector of dimension 100.

여기서 매개 변수의 수는 4427700?

conv1d_1 (Conv1D) (없음, 1377, 32) 12832 ------> Conv1d가 kernel size=4. 시간을 1*4사용 하는 필터입니다 32. 그런 차원이 된 방법 (None, 1377, 32)으로 12832매개 변수?

max_pooling1d_1 (MaxPooling1D) (None, 688, 32) MaxPooling1D (pool_size = 2)와 함께 치수가 (None, 688, 32)어떻게 되었습니까? flatten_1 (Flatten) (없음, 22016) 이것은 단지 688, 32의 곱셈입니까?

** 모든 Epoch가 한 번에 1800 개의 데이터 포인트를 훈련합니까? **

출력 치수 계산 방법을 알려주십시오. 모든 참조 또는 도움을 주시면 감사하겠습니다.