model=tf.keras.Sequential([
tf.keras.layers.Embedding(len(tokenizer.word_index)+1, 16, input_shape=(trainX.shape[0], trainX.shape[1])),
tf.keras.layers.LSTM(100),
tf.keras.layers.Dense(32, activation='tanh'),
tf.keras.layers.Dense(1, activation='sigmoid'),
])
Input 0 of layer "lstm_6" is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: (None, 160000, 100, 16)
Embedding를 어떻게 3차원으로 만들어서 LSTM에 집어넣을 수 있을까요??
