ЕТ
x_train это лист из листов вида [0.03505, 0.01628, 0.01102,...]
x_train это нумпай массив из листов вида [1 0 0]
model = Sequential()
model.add(Embedding(10000, 8, input_length=200))
model.add(LSTM(32, recurrent_dropout = 0.2))
model.add(Dense(1, activation='sigmoid'))
history = model.fit(x_train, y_train, epochs=15, batch_size=128, validation_split=0.1)
Model was constructed with shape (None, 200) for input Tensor("embedding_3_input:0", shape=(None, 200), dtype=float32), but it was called on an input with incompatible shape (None, 1)



