UFCNN値エラー：モデル入力

Question

をチェックするとき

Tensorflow 1.0.1 Keras 2.0とPython 3.4

私はufcnn-keras /ノートブック/ UFCNNのlukovkin/ufcnn-keras'モデル次UFCNNモデルを使用して回帰trainningを実行しています。 ipynb（ "https://github.com/lukovkin/ufcnn-keras/tree/master/notebook"）とkeras funcational APIチュートリアル。 しかし、 "ValueError：モデル入力をチェックしているときにエラーが発生しました：予想される入力に形状（None、64,1）があり、形状が配列（6400,1,1）"になっています。私は誰かが私を助けることができるようにしたい。ここでは以下の私のコードは次のとおりです。

from __future__ import absolute_import 
from __future__ import print_function 
import numpy as np 
import keras 
from keras.models import Model 
from keras.models import Sequential 
from keras.layers import Input, merge 
from keras.layers.core import Activation 
from keras.layers.convolutional import Conv1D 
import matplotlib.pyplot as plt 
from keras.preprocessing import sequence 

## UFCNN function 
def ufcnn_regression_model(sequence_length=5000, 
          features=1, 
          nb_filter=150, 
          filter_length=5, 
          output_dim=1, 
          optimizer='adagrad', 
          loss='mse'): 
    inputs = Input(shape=(sequence_length, features), name = 'input') 

    ######################################################### 
    conv_1 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(inputs) 
    relu_1 = Activation('relu')(conv_1) 
    ######################################################### 
    conv_2 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_1) 
    relu_2 = Activation('relu')(conv_2) 
    ######################################################### 
    conv_3 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_2) 
    relu_3 = Activation('relu')(conv_3) 
    ######################################################### 
    conv_4 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_3) 
    relu_4 = Activation('relu')(conv_4) 
    ######################################################### 
    merge_1 = keras.layers.add([relu_2, relu_4]) 
    conv_5 =Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(merge_1) 
    relu_5 = Activation('relu')(conv_5) 
    ######################################################### 
    merge_2 = keras.layers.add([relu_1, relu_5]) 
    conv_6 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(merge_2) 
    relu_6 = Activation('relu')(conv_6) 
    ######################################################### 
    conv_7 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_6) 
    ######################################################### 
    model = Model(inputs = inputs, outputs = conv_7) 
    model.compile(optimizer=optimizer, loss=loss)  
    print(model.summary()) 
    return model 

## Input & Output function 
def gen_cosine_amp(amp=100, period=25, x0=0, xn=500, step=1, k=0.0001): 
    cos = np.zeros(((xn - x0) * step, 1, 1)) 
    print("Cos. Shape",cos.shape) 
    for i in range(len(cos)): 
     idx = x0 + i * step 
     cos[i, 0, 0] = amp * np.cos(idx/(2 * np.pi * period)) 
     cos[i, 0, 0] = cos[i, 0, 0] * np.exp(-k * idx) 

    lahead = 1 
    expected_output = np.zeros((len(cos), 1)) 
    for i in range(len(cos) - lahead): 
     expected_output[i, 0] = np.mean(cos[i + 1:i + lahead + 1]) 
    return cos, expected_output 

## Parameter 
sequence_length = 64 
features = 1    
nb_filter = 150    
filter_length = 5    
output_dim = 1    
epochs = 5 
batch_size = 128 

## UFCNN_1 model summary 
UFCNN_1 = ufcnn_regression_model(sequence_length=sequence_length) 

## Inputs and ouputs to be trained 
cos = gen_cosine_amp(xn = sequence_length * 100)[0] 
expected_output = gen_cosine_amp(xn = sequence_length * 100)[1] 

## Trainning 
for i in range(epochs): 
    print('Epoch', i, '/', epochs) 
    UFCNN_1.fit(cos, expected_output, verbose=1,epochs=1,shuffle=False, batch_size=batch_size) 
    print('Predicting') 

## Predicting 
predicted_output = model.predict(cos, batch_size=batch_size) 

私のエラーは、次のとおりです。

Epoch 0/5 

--------------------------------------------------------------------------- 
ValueError        Traceback (most recent call last) 
<ipython-input-8-d49a856b74bd> in <module>() 
     1 for i in range(epochs): 
     2  print('Epoch', i, '/', epochs) 
----> 3  UFCNN_1.fit(cos, expected_output, verbose=1,epochs=1,shuffle=False, batch_size=batch_size) 
     4  print('Predicting') 
     5 predicted_output = model.predict(cos, batch_size=batch_size) 

/usr/local/lib/python3.4/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs) 
    1403    class_weight=class_weight, 
    1404    check_batch_axis=False, 
-> 1405    batch_size=batch_size) 
    1406   # prepare validation data 
    1407   if validation_data: 

/usr/local/lib/python3.4/dist-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size) 
    1293          self._feed_input_shapes, 
    1294          check_batch_axis=False, 
-> 1295          exception_prefix='model input') 
    1296   y = _standardize_input_data(y, self._feed_output_names, 
    1297          output_shapes, 

/usr/local/lib/python3.4/dist-packages/keras/engine/training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 
    131        ' to have shape ' + str(shapes[i]) + 
    132        ' but got array with shape ' + 
--> 133        str(array.shape)) 
    134  return arrays 
    135 

ValueError: Error when checking model input: expected input to have shape (None, 64, 1) but got array with shape (6400, 1, 1) 

それを動作させるためにあなたの助けをありがとう!!!!!

BTW：このモデルはlukovkin/ufcnn-kerasのモデルとほとんど同じですが、kerasとtensorflowの新しいバージョンに合わせてコードを更新するだけです。

Answer 1

Theano 1.0.0、2.1.3 Keras、Pythonの2.7.10

ブロードキャスト入力と出力：あなたは、サンプルにネットを訓練する必要がありますkerasとCNNの私は（まだ狭い）理解に形状は(n_samples, sequence_length, features)です。これは、rolling window viewであなたの時系列を広げて、形(6400, 1, 1)を(6400, 64, 1)に放送することを意味します。あなたはas_stridedを経由して次の操作を行います。

## reshape data 
cos_view = np.lib.stride_tricks.as_strided(
    cos, 
    shape=[cos.shape[0] - sequence_length, sequence_length, 1], 
    strides=cos.strides 
) 
expected_output_view = np.lib.stride_tricks.as_strided(
    expected_output, 
    shape=[expected_output.shape[0] - sequence_length, sequence_length, 1], 
    strides=expected_output.strides 
) 

expected_outputはまた、より高い次元のものでなければならないが。 gen_cosine_ampで：モデルのバグを修正

UFCNN_1.fit(cos_view, expected_output_view, verbose=1,epochs=1,shuffle=False, batch_size=batch_size) 

：

def gen_cosine_amp(amp=100, period=25, x0=0, xn=500, step=1, k=0.0001): 
    ... 
    expected_output = np.zeros((len(cos), 1, 1)) 
    for i in range(len(cos) - lahead): 
     expected_output[i, 0, 0] = np.mean(cos[i + 1:i + lahead + 1]) 

現在、これらの放送ビューにモデルを訓練することができますしかし、あなたのコード内の別のバグがあることに注意してください。層conv_7は出力層です。データ上のこれらの変更のトレーニングは非常にうまく機能して、このモデルは、将来に見える場合、私は見当がつかないにもかかわらず：それを出力/フィルタ寸法だnb_filterが、output_dim

conv_7 = Conv1D(filters=output_dim, kernel_size=filter_length, padding='same')(relu_6) 

懸念すべきではありません時系列（あなたの信号はルコブキンのufcnn-kerasの時系列と仮定します）。おそらく、padding="causal"とdilation_rate=x（x> 1）のConv1Dの層が良いでしょう。それをすべて一緒に置く

を（私はまだ時系列予測で自分自身を試しています）：

from __future__ import absolute_import 
from __future__ import print_function 
import numpy as np 
import keras 
from keras.models import Model 
from keras.models import Sequential 
from keras.layers import Input, merge 
from keras.layers.core import Activation 
from keras.layers.convolutional import Conv1D 
import matplotlib.pyplot as plt 
from keras.preprocessing import sequence 

def ufcnn_regression_model(sequence_length=5000, 
          features=1, 
          nb_filter=150, 
          filter_length=5, 
          output_dim=1, 
          optimizer='adagrad', 
          loss='mse'): 
    inputs = Input(shape=(sequence_length, features), name = 'input') 

    ######################################################### 
    conv_1 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(inputs) 
    relu_1 = Activation('relu')(conv_1) 
    ######################################################### 
    conv_2 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_1) 
    relu_2 = Activation('relu')(conv_2) 
    ######################################################### 
    conv_3 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_2) 
    relu_3 = Activation('relu')(conv_3) 
    ######################################################### 
    conv_4 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(relu_3) 
    relu_4 = Activation('relu')(conv_4) 
    ######################################################### 
    merge_1 = keras.layers.add([relu_2, relu_4]) 
    conv_5 =Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(merge_1) 
    relu_5 = Activation('relu')(conv_5) 
    ######################################################### 
    merge_2 = keras.layers.add([relu_1, relu_5]) 
    conv_6 = Conv1D(filters=nb_filter, kernel_size=filter_length, padding='same')(merge_2) 
    relu_6 = Activation('relu')(conv_6) 
    ######################################################### 
    conv_7 = Conv1D(filters=output_dim, kernel_size=filter_length, padding='same')(relu_6) 
    ######################################################### 
    model = Model(inputs = inputs, outputs = conv_7) 
    model.compile(optimizer=optimizer, loss=loss) 
    print(model.summary()) 
    return model 

## Input & Output function 
def gen_cosine_amp(amp=100, period=25, x0=0, xn=500, step=1, k=0.0001): 
    cos = np.zeros(((xn - x0) * step, 1, 1)) 
    print("Cos. Shape",cos.shape) 
    for i in range(len(cos)): 
     idx = x0 + i * step 
     cos[i, 0, 0] = amp * np.cos(idx/(2 * np.pi * period)) 
     cos[i, 0, 0] = cos[i, 0, 0] * np.exp(-k * idx) 

    lahead = 1 
    expected_output = np.zeros((len(cos), 1)) 
    for i in range(len(cos) - lahead): 
     expected_output[i, 0] = np.mean(cos[i + 1:i + lahead + 1]) 
    return cos, expected_output 

def gen_cosine_amp(amp=100, period=25, x0=0, xn=500, step=1, k=0.0001): 
    cos = np.zeros(((xn - x0) * step, 1, 1)) 
    print("Cos. Shape",cos.shape) 
    for i in range(len(cos)): 
     idx = x0 + i * step 
     cos[i, 0, 0] = amp * np.cos(idx/(2 * np.pi * period)) 
     cos[i, 0, 0] = cos[i, 0, 0] * np.exp(-k * idx) 

    lahead = 1 
    expected_output = np.zeros((len(cos), 1, 1)) 
    for i in range(len(cos) - lahead): 
     expected_output[i, 0, 0] = np.mean(cos[i + 1:i + lahead + 1]) 
    return cos, expected_output 

## Parameter 
sequence_length = 64 
features = 1 
nb_filter = 150 
filter_length = 5 
output_dim = 1 
epochs = 5 
batch_size = 128 

## UFCNN_1 model summary 
UFCNN_1 = ufcnn_regression_model(sequence_length=sequence_length) 

## Inputs and ouputs to be trained 
cos = gen_cosine_amp(xn = sequence_length * 100)[0] 
expected_output = gen_cosine_amp(xn = sequence_length * 100)[1] 

## reshape data 
cos_view = np.lib.stride_tricks.as_strided(
    cos, 
    shape=[cos.shape[0] - sequence_length, sequence_length, 1], 
    strides=cos.strides 
) 
expected_output_view = np.lib.stride_tricks.as_strided(
    expected_output, 
    shape=[expected_output.shape[0] - sequence_length, sequence_length, 1], 
    strides=expected_output.strides 
) 

print("Cos. Shape Input ",cos_view.shape) 
## Trainning 
for i in range(epochs): 
    print('Epoch', i, '/', epochs) 
    UFCNN_1.fit(cos_view, expected_output_view, verbose=1,epochs=1,shuffle=False, batch_size=batch_size)  

print('Predicting') 
predicted_output = UFCNN_1.predict(cos_view, batch_size=batch_size) 
rmse = np.sqrt(((predicted_output - cos_view) ** 2).mean(axis=None)) 
print ("RMSE ", rmse)