TensorFlow正弦函数预测

《TensorFlow实战Google深度学习框架》8.4.2

代码：

#!/usr/bin/env python
#-*-coding:UTF-8-*-

import numpy as np
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.estimators.estimator import SKCompat
import matplotlib.pyplot as plt

learn = tf.contrib.learn

HIDDEN_SIZE = 30
NUM_LAYERS = 2

TIMESTEPS = 10
TRAINING_STEPS = 3000
BATCH_SIZE = 32

TRAINING_EXAMPLES = 10000
TESTING_EXAMPLES = 1000
SAMPLE_GAP = 0.01

def generate_data(seq):
    X = []
    y = []
    #序列的第i项和后面的TIMESTEPS-1项合在一起作为输入：第i + TIMESTEPS项作为输出。
    #即用sin函数前面的TIMESTEPS个点的信息，预测第i + TIMESTEPS个点的函数值
    for i in range(len(seq) - TIMESTEPS - 1):
        X.append([seq[i: i + TIMESTEPS]])
        y.append([seq[i + TIMESTEPS]])
    return np.array(X, dtype=np.float32), np.array(y, dtype=np.float32)

def lstm_model(X, y):
    
    lstm_cell = tf.contrib.rnn.BasicLSTMCell(HIDDEN_SIZE, state_is_tuple=True)
    cell = tf.contrib.rnn.MultiRNNCell([lstm_cell] * NUM_LAYERS)

    output, _ = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)
    
    output = tf.reshape(output, [-1, HIDDEN_SIZE])
    #对LSTM网络的输出再做加一层全连接层并计算损失。注意这里默认的损失为平均平方差损失函数
    
    predictions = tf.contrib.layers.fully_connected(output, 1, None)

    labels = tf.reshape(y,[-1])
    predictions = tf.reshape(predictions,[-1])

    loss = tf.losses.mean_squared_error(predictions, labels)

    train_op = tf.contrib.layers.optimize_loss(
        loss, tf.contrib.framework.get_global_step(),
        optimizer="Adagrad", learning_rate=0.1)

    return predictions, loss, train_op


regressor = SKCompat(learn.Estimator(model_fn=lstm_model,model_dir="/home/jim/TensorFlow/Models"))

test_start = TRAINING_EXAMPLES * SAMPLE_GAP
test_end = (TRAINING_EXAMPLES + TESTING_EXAMPLES) * SAMPLE_GAP
train_X, train_y = generate_data(np.sin(np.linspace(
    0, test_start, TRAINING_EXAMPLES, dtype=np.float32)))
test_X, test_y = generate_data(np.sin(np.linspace(
    test_start, test_end, TESTING_EXAMPLES, dtype=np.float32)))

regressor.fit(train_X, train_y, batch_size=BATCH_SIZE,
              steps=TRAINING_STEPS)

predicted = [[pred] for pred in regressor.predict(test_X)]

rmse = np.sqrt(((predicted - test_y) ** 2).mean(axis=0))
print ("Mean Square Error is: %f" % rmse[0])

fig = plt.figure()
plot_predicted, = plt.plot(predicted, label='predicted')
plot_test, = plt.plot(test_y, label='real_sin')
plt.legend([plot_predicted, plot_test],['predicted','real_sin'])
#fig.savefig('sin.png')
plt.show()

错误：

Traceback (most recent call last):
  File "/home/jim/TensorFlow/sin_prediction.py", line 73, in 
    steps=TRAINING_STEPS)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1527, in fit
    monitors=all_monitors)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 432, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 524, in fit
    loss = self._train_model(input_fn=input_fn, hooks=hooks)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1041, in _train_model
    model_fn_ops = self._get_train_ops(features, labels)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1264, in _get_train_ops
    return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1227, in _call_model_fn
    model_fn_results = self._model_fn(features, labels, **kwargs)
  File "/home/jim/TensorFlow/sin_prediction.py", line 44, in lstm_model
    output, _ = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 618, in dynamic_rnn
    dtype=dtype)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 815, in _dynamic_rnn_loop
    swap_memory=swap_memory)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 3209, in while_loop
    result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2941, in BuildLoop
    pred, body, original_loop_vars, loop_vars, shape_invariants)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2878, in _BuildLoop
    body_result = body(*packed_vars_for_body)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 3179, in 
    body = lambda i, lv: (i + 1, orig_body(*lv))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 786, in _time_step
    (output, new_state) = call_cell()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 772, in 
    call_cell = lambda: cell(input_t, state)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 232, in __call__
    return super(RNNCell, self).__call__(inputs, state)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/base.py", line 329, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 703, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1325, in call
    cur_inp, new_state = cell(cur_inp, cur_state)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 339, in __call__
    *args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/base.py", line 329, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 703, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 638, in call
    array_ops.concat([inputs, h], 1), self._kernel)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 2014, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 4279, in mat_mul
    name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3414, in create_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1756, in __init__
    control_input_ops)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1592, in _create_c_op
    raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 60 and 40 for 'rnn/while/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/MatMul_1' (op: 'MatMul') with input shapes: [?,60], [40,120].

解决：

将以下两句修改

lstm_cell = tf.contrib.rnn.BasicLSTMCell(HIDDEN_SIZE, state_is_tuple=True)
cell = tf.contrib.rnn.MultiRNNCell([lstm_cell] * NUM_LAYERS)

def lstm_cell():
    lstm = tf.contrib.rnn.BasicLSTMCell(HIDDEN_SIZE, forget_bias=1.0)
    return lstm

def lstm_model(X,y):
    cell = tf.contrib.rnn.MultiRNNCell([lstm_cell() for _ in range(NUM_LAYERS)])
    ...