Я подготовил простой набор данных и набор этикеток. Я хочу узнать, как реализовать простой RNN в Keras. Я подготовил свои данные. Когда я не использую нормализацию (MinMaxScaler), все компилируется без ошибок.
Однако, когда я пытаюсь использовать скейлер, я получал ValueError: Found array with dim 3. Estimator expected <= 2.. Это код:
# -*- coding: utf-8 -*-
#!/usr/bin/env python3
import tensorflow as tf
from tensorflow import keras
from keras.models import Sequential
from keras.layers import Dense, SimpleRNN
from keras.callbacks import ModelCheckpoint
from keras import backend as K
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
import numpy
import matplotlib.pyplot as plt
def stagger(a, delay):
num_of_rows = a.shape[0]
num_of_cols = a.shape[1]
data_in = numpy.zeros((num_of_rows + delay, num_of_cols * (1 + delay)))
data_in[0:num_of_rows, 0:4] = a
data_in[1:(num_of_rows + 1), 4:8] = a
a = data_in[0:num_of_rows, :]
return a
dataset = numpy.array([[0, 2, 0, 324], [1, 2, 0,324], [2, 2, 0, 324], [3, 2, 0, 324], [4, 2, 0, 324], [5, 2, 0, 324], [6, 2, 0, 324],
[7, 2, 0, 324], [8, 2, 0, 324], [9, 2, 0, 324], [ 10, 2, 0, 324], [ 11, 2, 0, 324], [ 12, 2, 0, 324], [ 13, 2, 0, 324],
[ 14, 2, 0, 324], [ 15, 2, 0, 324], [ 16, 2, 0, 324], [ 17, 2, 0, 324],[ 18, 2, 0, 324], [ 19, 2, 0, 324], [ 20, 2, 0, 324],
[ 21, 2, 0, 324],[ 22, 2, 0, 324], [ 23, 2, 0, 324]])
labels = numpy.array([[0.82174763], [0.62098727], [0.45012733], [1.5912102 ],
[0.37570953], [0.2930966 ], [0.34982923], [0.72239097],
[1.37881947], [1.79550653], [1.88867237], [1.93567087],
[1.9771925 ], [2.10873853], [2.158302 ], [2.11018633],
[1.9714166 ], [2.2553416 ], [2.41161887], [2.41161887],
[2.30333453], [2.38390613], [2.21882553], [2.0707972 ]])
delay = 2
input_shape = (1, 4*(1+delay))
min_max_scaler = MinMaxScaler(feature_range=(0, 1))
# prepare dataset
dataset = stagger(dataset, delay)
# split dataset
x_train, x_test, y_train, y_test = train_test_split(dataset, labels, test_size=0.2, shuffle=False)
x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size=0.25, shuffle=False)
# normalize dataset
x_train = min_max_scaler.fit_transform(x_train)
x_test = min_max_scaler.transform(x_test)
x_val = min_max_scaler.transform(x_val)
# reshape dataset
x_train = numpy.reshape(x_train, (x_train.shape[0], 1, x_train.shape[1]))
x_test = numpy.reshape(x_test, (x_test.shape[0], 1, x_test.shape[1]))
x_val = numpy.reshape(x_val, (x_val.shape[0], 1, x_val.shape[1]))
y_train = numpy.reshape(y_train, (y_train.shape[0], 1, y_train.shape[1]))
y_test = numpy.reshape(y_test, (y_test.shape[0], 1, y_test.shape[1]))
y_val = numpy.reshape(y_val, (y_val.shape[0], 1, y_val.shape[1]))
# RNN model
model = Sequential()
model.add(SimpleRNN(64, activation="relu", kernel_initializer='random_uniform', input_shape=input_shape, return_sequences=True))
model.add(Dense(32, activation="relu", kernel_initializer= 'random_uniform'))
model.add(Dense(1, activation="linear", kernel_initializer= 'random_uniform'))
# train and predict
callback = keras.callbacks.EarlyStopping(monitor='val_loss', min_delta=0, patience=2, verbose=0, mode='auto')
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy', tf.keras.metrics.MeanSquaredError()])
history = model.fit(x_train, y_train, epochs=100, batch_size=8, validation_data=(x_val, y_val), callbacks=[callback])
results = model.evaluate(x_test, y_test)
# plot
test_predictions = model.predict(x_test)
test_predictions = min_max_scaler.inverse_transform(test_predictions)
y_test = y_test[:,:,0]
test_predictions = test_predictions[:,:,0]
plt.plot(y_test)
plt.plot(test_predictions)
plt.legend(['y_test', 'predictions'], loc='upper left')
plt.show()