在转换过程中从 tensorflow 对象中提取 numpy 值

Question

我正在尝试使用 tensorflow 获取词嵌入，并且我已经使用我的语料库创建了相邻的工作列表。

我的词汇表中唯一单词的数量为 8000，相邻单词列表的数量约为 160 万

Word Lists sample photo

由于数据非常大，我正在尝试将单词列表分批写入 TFRecords 文件。

def save_tfrecords_wordlist(toprocess_word_lists, path ):    
    writer = tf.io.TFRecordWriter(path)

    for word_list in toprocess_word_lists:
        features=tf.train.Features(
            feature={
        'word_list_X': tf.train.Feature( bytes_list=tf.train.BytesList(value=[word_list[0].encode('utf-8')] )),
        'word_list_Y': tf.train.Feature( bytes_list=tf.train.BytesList(value=[word_list[1].encode('utf-8') ]))
                }
            )
        example = tf.train.Example(features = features)
        writer.write(example.SerializeToString())
    writer.close()

定义批次

batches = [0,250000,500000,750000,1000000,1250000,1500000,1641790]

for i in range(len(batches) - 1 ):

    batches_start = batches[i]
    batches_end = batches[i + 1]
    print( str(batches_start) + " -- " + str(batches_end ))

    toprocess_word_lists = word_lists[batches_start:batches_end]
    save_tfrecords_wordlist( toprocess_word_lists, path +"/TFRecords/data_" + str(i) +".tfrecords")

##############################

def _parse_function(example_proto):

  features = {"word_list_X": tf.io.FixedLenFeature((), tf.string),
          "word_list_Y": tf.io.FixedLenFeature((), tf.string)}
  parsed_features = tf.io.parse_single_example(example_proto, features)

  """
  word_list_X  = parsed_features['word_list_X'].numpy()
  word_list_Y  = parsed_features['word_list_Y'].numpy()

  ## need help is getting the numpy values from parsed_features variable so that i can get the one hot encoding matrix     which can be directly sent to tensorflow for training

  sample word_list_X value is <tf.Tensor: shape=(10,), dtype=string,   numpy=array([b'for', b'for', b'for', b'you', b'you', b'you', b'you', b'to',b'to', b'to'], dtype=object)>
  sample word_list_Y value is <tf.Tensor: shape=(10,), dtype=string, numpy=array([b'is', b'to', b'recommend', b'to', b'for', b'contact', b'is',b'contact', b'you', b'the'], dtype=object)>)

  """
  return parsed_features['word_list_X'],parsed_features['word_list_Y']

filenames = [ path + "/JustEat_TFRecords/data.tfrecords" ]
dataset = tf.data.TFRecordDataset(filenames)

dataset = dataset.map(_parse_function)
dataset = dataset.batch(10)

# Defining the size of the embedding
embed_size = 100

# Defining the neural network
inp = tf.keras.Input(shape=(7958,))
x = tf.keras.layers.Dense(units=embed_size, activation='linear')(inp)
x = tf.keras.layers.Dense(units=7958, activation='softmax')(x)

model =  tf.keras.Model(inputs=inp, outputs=x)
model.compile(loss = 'categorical_crossentropy', optimizer = 'adam')

# Optimizing the network weights
#model.fit( x=X, y=Y, batch_size=256,epochs= 100)
model.fit(dataset,epochs= 2)

Answer 1

您似乎无法从映射函数内部调用 .numpy() 函数 (1, 2) although i was able to manage by using the py_function from (doc)。

在下面的例子中，我将我解析的数据集映射到一个函数，该函数将我的图像转换为np.uint8 使用 matplotlib 绘制它们。

records_path = data_directory+'TFRecords'+'/data_0.tfrecord'
# Create a dataset
dataset = tf.data.TFRecordDataset(filenames=records_path)
# Map our dataset to the parsing function 
parsed_dataset = dataset.map(parsing_fn)
converted_dataset = parsed_dataset.map(lambda image,label:
                                       tf.py_function(func=converting_function,
                                                      inp=[image,label],
                                                      Tout=[np.uint8,tf.int64]))

# Gets the iterator
iterator = tf.compat.v1.data.make_one_shot_iterator(converted_dataset) 

for i in range(5):
    image,label = iterator.get_next()
    plt.imshow(image)
    plt.show()
    print('label: ', label)

输出：

解析函数：

def parsing_fn(serialized):
    # Define a dict with the data-names and types we expect to
    # find in the TFRecords file.
    features = \
        {
            'image': tf.io.FixedLenFeature([], tf.string),
            'label': tf.io.FixedLenFeature([], tf.int64)            
        }

    # Parse the serialized data so we get a dict with our data.
    parsed_example = tf.io.parse_single_example(serialized=serialized,
                                             features=features)
    # Get the image as raw bytes.
    image_raw = parsed_example['image']

    # Decode the raw bytes so it becomes a tensor with type.
    image = tf.io.decode_jpeg(image_raw)
    
    # Get the label associated with the image.
    label = parsed_example['label']
    
    # The image and label are now correct TensorFlow types.
    return image, label

在转换过程中从 tensorflow 对象中提取 numpy 值

extracting numpy value from tensorflow object during transformation

python

tensorflow

word-embedding

tfrecord

tf.data.dataset

定义批次

您似乎无法从映射函数内部调用 .numpy() 函数 (1, 2) although i was able to manage by using the py_function from (doc)。

输出：

解析函数：