Question

这是我的代码的简化版本，引发标题中提到的错误：

import tensorflow as tf

BATCH_SIZE = 3
SEQ_LENGTH = 4
NUM_CLASSES = 2
LSTM_UNITS = 64
NUM_SHARDS = 4
NUM_CHANNELS = 2

tf.enable_eager_execution()

def keras_model():
    inputs = tf.keras.layers.Input(shape=(SEQ_LENGTH, NUM_CHANNELS))
    x = tf.keras.layers.Bidirectional(
        tf.keras.layers.LSTM(LSTM_UNITS, return_sequences=True))(inputs)
    outputs = tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(NUM_CLASSES, activation='relu'))(x)
    return tf.keras.Model(inputs, outputs)

dataset = tf.data.experimental.CsvDataset(filenames='../../input/aFile.csv', header=True,record_defaults=[tf.int64] * 3, select_cols=[0,1,2])
dataset=  dataset.window(size=SEQ_LENGTH, shift=1, drop_remainder=True).flat_map(lambda f1,f2, label:
            tf.data.Dataset.zip((tf.data.Dataset.zip((f1.batch(SEQ_LENGTH),f2.batch(SEQ_LENGTH))), label.batch(SEQ_LENGTH))))
dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)


train_iterator = dataset.make_one_shot_iterator()
train_features, train_labels = train_iterator.get_next()

print(train_features)
print(train_labels)

model = keras_model()
model.summary()
model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])
model.fit(x=train_features,y=train_labels, batch_size=BATCH_SIZE,epochs=1, steps_per_epoch=10)

这是代码的输出：

...
(<tf.Tensor: id=44, shape=(3, 4), dtype=int64, numpy=
array([[0, 1, 2, 3],
       [1, 2, 3, 4],
       [2, 3, 4, 5]], dtype=int64)>, <tf.Tensor: id=45, shape=(3, 4), dtype=int64, numpy=
array([[100, 101, 102, 103],
       [101, 102, 103, 104],
       [102, 103, 104, 105]], dtype=int64)>)
tf.Tensor(
[[0 0 0 0]
 [0 0 0 1]
 [0 0 1 0]], shape=(3, 4), dtype=int64)
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 4, 2)              0         
_________________________________________________________________
bidirectional (Bidirectional (None, 4, 128)            34304     
_________________________________________________________________
time_distributed (TimeDistri (None, 4, 2)              258       
=================================================================
Total params: 34,562
Trainable params: 34,562
Non-trainable params: 0
_________________________________________________________________
...
ValueError: Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (3, 4)

Process finished with exit code 1

我正在使用此csv文件进行演示

f1,f2,label
0,100,0
1,101,0
2,102,0
3,103,0
4,104,1
5,105,0
6,106,0
7,107,0
8,108,1
9,109,0
10,110,0

前两列是来自两个不同渠道的要素列，最后一列包含标签。我需要使用例如四行数据的序列作为输入模型的时间，而批处理大小例如为三，因此输入形状就像四行的三批，每行包含两个值。我想我需要使用某种重塑功能，但不知道如何操作。有人可以告诉我如何解决此问题吗？

Answer 1

在第一次尝试解决问题时，我更改了代码，以首先组合通道以构建特征列，然后对特征列进行排序。这将输入的形状从[batch_size，channel_num，sequence_length]更改为[batch_size，sequence_length，channel_num]，并根据模型的期望为标签添加了尺寸。这是新代码：

import tensorflow as tf
import numpy as np

BATCH_SIZE = 3
SEQ_LENGTH = 4
NUM_CLASSES = 2
LSTM_UNITS = 64
NUM_SHARDS = 4
NUM_CHANNELS = 2

tf.enable_eager_execution()

def parse_values(f1, f2, label):
    features = [f1,f2]
    return features, label

def keras_model():
    inputs = tf.keras.layers.Input(shape=(SEQ_LENGTH,NUM_CHANNELS))
    x = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM_UNITS, return_sequences=True))(inputs)
    outputs = tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(NUM_CLASSES, activation='relu'))(x)
    return tf.keras.Model(inputs, outputs)

dataset = tf.data.experimental.CsvDataset(filenames='../../input/aFile.csv', header=True,record_defaults=[tf.int64] * 3, select_cols=[0,1,2])
dataset=  dataset.map(parse_values).window(size=SEQ_LENGTH, shift=1, drop_remainder=True).flat_map(lambda features, label:
            tf.data.Dataset.zip((features.batch(SEQ_LENGTH), label.batch(SEQ_LENGTH))))
dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)


train_iterator = dataset.make_one_shot_iterator()
train_features, train_labels = train_iterator.get_next()

print(train_features)
#train_labels = train_labels[:,SEQ_LENGTH-1] # output => [0 1 0]
#print(train_labels)
train_labels = np.expand_dims(train_labels, axis=2)
print(train_labels)

model = keras_model()
model.summary()
model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])
model.fit(x=train_features,y=train_labels, batch_size=BATCH_SIZE,epochs=1, steps_per_epoch=10)

下面是输出：

...tf.Tensor(
[[[  0 100]
  [  1 101]
  [  2 102]
  [  3 103]]

 [[  1 101]
  [  2 102]
  [  3 103]
  [  4 104]]

 [[  2 102]
  [  3 103]
  [  4 104]
  [  5 105]]], shape=(3, 4, 2), dtype=int64)
[[[0]
  [0]
  [0]
  [0]]

 [[0]
  [0]
  [0]
  [1]]

 [[0]
  [0]
  [1]
  [0]]]
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 4, 2)              0         
_________________________________________________________________
bidirectional (Bidirectional (None, 4, 128)            34304     
_________________________________________________________________
time_distributed (TimeDistri (None, 4, 2)              258       
=================================================================
Total params: 34,562
Trainable params: 34,562
Non-trainable params: 0
_________________________________________________________________

 1/10 [==>...........................] - ETA: 8s - loss: 13.3860 - acc: 0.1667
10/10 [==============================] - 1s 101ms/step - loss: 12.9909 - acc: 0.1667

Process finished with exit code 0

对我来说，每个序列只有一个标签可以确定该序列属于0类还是1类（在我的情况下，每个批次3个值，因为批次大小为3）对我来说更有意义。我试图通过添加一行代码（如下所示）来做到这一点，由于这会导致异常“不兼容的形状：[3]与[3,4]”，因此不得不稍后注释掉

train_labels = train_labels [：，SEQ_LENGTH-1]＃输出=> [0 1 0]

我不知道如何解决该错误，因此，正如您在输出中所看到的，我将序列中包含的所有行的标签提供给了模型。后来，我想出了一个技巧，可以使序列中的所有项目都具有相同的标签。我决定将序列中的所有标签设置为序列的最后一个标签。例如，[0 0 0 1]将更改为[1 1 1 1]，[0 0 1 0]将更改为[0 0 0 0]。我还将损失函数更改为“ binary_crossentropy”，因为这里的问题是二进制分类。下面是代码：

import tensorflow as tf
import numpy as np

BATCH_SIZE = 3
SEQ_LENGTH = 4
NUM_CLASSES = 1
LSTM_UNITS = 64
NUM_SHARDS = 4
NUM_CHANNELS = 2

tf.enable_eager_execution()

def parse_values(f1, f2, label):
    features = [f1,f2]
    return features, label

def map_label(features, label):
    sequence_label1 = tf.fill([SEQ_LENGTH],label[SEQ_LENGTH-1])
    return features, sequence_label1

def keras_model():
    inputs = tf.keras.layers.Input(shape=(SEQ_LENGTH,NUM_CHANNELS),batch_size=BATCH_SIZE)
    x = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM_UNITS, return_sequences=True))(inputs)
    outputs = tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(NUM_CLASSES, activation='sigmoid'))(x)
    return tf.keras.Model(inputs, outputs)

dataset = tf.data.experimental.CsvDataset(filenames='../../input/aFile.csv', header=True,record_defaults=[tf.int64] * 3, select_cols=[0,1,2])
dataset=  dataset.map(parse_values).window(size=SEQ_LENGTH, shift=1, drop_remainder=True).flat_map(lambda features, label:
            tf.data.Dataset.zip((features.batch(SEQ_LENGTH), label.batch(SEQ_LENGTH)))).map(map_label)
dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)

train_iterator = dataset.make_one_shot_iterator()
train_features, train_labels = train_iterator.get_next()

print(train_features)
train_labels = np.expand_dims(train_labels, axis=2)
print(train_labels)

model = keras_model()
model.summary()
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
model.fit(x=train_features,y=train_labels, batch_size=BATCH_SIZE,epochs=1, steps_per_epoch=10)

下面是输出：

...tf.Tensor(
[[[  0 100]
  [  1 101]
  [  2 102]
  [  3 103]]

 [[  1 101]
  [  2 102]
  [  3 103]
  [  4 104]]

 [[  2 102]
  [  3 103]
  [  4 104]
  [  5 105]]], shape=(3, 4, 2), dtype=int64)
[[[0]
  [0]
  [0]
  [0]]

 [[1]
  [1]
  [1]
  [1]]

 [[0]
  [0]
  [0]
  [0]]]
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (3, 4, 2)                 0         
_________________________________________________________________
bidirectional (Bidirectional (3, 4, 128)               34304     
_________________________________________________________________
time_distributed (TimeDistri (3, 4, 1)                 129       
=================================================================
Total params: 34,433
Trainable params: 34,433
Non-trainable params: 0
_________________________________________________________________
...

 1/10 [==>...........................] - ETA: 10s - loss: 0.6866 - acc: 0.5833
10/10 [==============================] - 1s 124ms/step - loss: 0.6571 - acc: 0.6500

Process finished with exit code 0

我希望这会对遇到类似问题的人有所帮助。

Answer 2

我今天再次调查了这个问题，我认为您可以通过修改以下解析函数来解决此问题：

def parse_values(f1, f2, label):
    features = tf.stack([f1, f2], 0)
    return features, label

预期input_1具有3个维度，但数组的形状为（3，4）

2 个答案: