В TensorFlow не хватает диапазона во время фитинга: локальное свидание прерывается со статусом: out_of_range: конец посл ⇐ Python

[Anonymous]

У меня есть набор данных, содержащий семантические векторы длины 384. Я группирую их в окна, каждая из которых содержит 100. Я перечисляю их до размеров пакетов 32. Однако я получаю ошибку при подгонке модели. Я чувствую, что это может быть связано с тем, что он создает 48 партии 32 размера из 1515 Windows, что делает последнюю партию неполной, учитывая, что 1515/32 = 47,34375 , но я не знаю, действительно ли это вызывает проблема-у меня никогда не было проблемы в прошлом.
. PrettyPrint-Override ">

Код: Выделить всё

model.fit(training_data, epochs=50, validation_data=validation_data)
< /code>
Так явно я не устанавливаю шаги, которые должны означать, что никто не должен привести к тому, что Tensorflow будет проходить через весь training_data в каждую эпоху. Если так, не могли бы вы привести пример, как его отбросить?2025-04-03 12:20:03 [INFO]: Training (151508, 2)
2025-04-03 12:20:03 [INFO]: Validation (26514, 2)
2025-04-03 12:20:03 [INFO]: Test (22728, 2)
I0000 00:00:1743675604.435011    6880 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2025-04-03 12:20:04.435109: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2343] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2025-04-03 12:20:04.838231: I tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence
Number of windows created: 1515
Input shape: (32, 100, 384)
Label shape: (32, 100, 384)
2025-04-03 12:20:07.074530: I tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence
Counted training batches: 48
Epoch 1/50
2025-04-03 12:20:09.798596: E tensorflow/core/util/util.cc:131] oneDNN supports DT_INT32 only on platforms with AVX-512. Falling back to the default Eigen-based implementation if present.
47/Unknown 5s 48ms/step - loss: 0.00172025-04-03 12:20:12.186355: I tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence
[[{{node IteratorGetNext}}]]
/home/xaver/Documents/Repos/logAnomalyDetection/venv/lib/python3.12/site-packages/keras/src/trainers/epoch_iterator.py:151: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches.  You may need to use the `.repeat()` function when building your dataset.
self._interrupted_warning()
< /code>
 code < /h1>
"""
Semi-supervised log anomaly detection using sentence vector embeddings and a sliding window
"""

import logging
import pickle
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow.keras import layers, models, Input
from sklearn.metrics import (
confusion_matrix, matthews_corrcoef, precision_score, recall_score,
f1_score, roc_auc_score, average_precision_score
)

from tensorflow.python.client import device_lib
device_lib.list_local_devices()

WINDOW_SIZE = 100
BATCH_SIZE = 32

# Configure logging
logging.basicConfig(
format="%(asctime)s [%(levelname)s]: %(message)s",
level=logging.INFO,
datefmt="%Y-%m-%d %H:%M:%S"
)

# Step 1: Load and prepare data
input_pickle = "outputs/parsed_openstack_logs_with_embeddings_final.pickle"
with open(input_pickle, "rb") as handle:
df = pickle.load(handle)

logging.info("DataFrame loaded successfully.")
# embeddings will be the input and output since AE tries to create the representation from the latent space
# label contains whether the data is anomalous (1) or normal (0).
logging.debug(f"{df.columns}")
logging.debug(f"\n{df.head()}")

# split data so that training data contains no anomalies, validation and testing contain an equal number of normal and abnormal entries
embedding_length = len(df["embeddings"][0])
print("Length of embedding vector:", embedding_length)
normal_data = df[df['label'] == 0]
test_data_abnormal = df[df['label'] == 1]
abnormal_normal_ratio = len(test_data_abnormal) / len(normal_data)
logging.info(f"N normal: {len(normal_data)};  N abnormal: {len(test_data_abnormal)} -- Ratio: {abnormal_normal_ratio}")

training_data, rest_data = train_test_split(normal_data, train_size=0.8, shuffle=False)
validation_data, test_data_normal = train_test_split(rest_data, test_size=0.3, shuffle=False)

test_data_normal = test_data_normal.head(len(test_data_abnormal))
test_data_abnormal = test_data_abnormal.head(len(test_data_normal))

test_data = pd.concat([test_data_normal, test_data_abnormal])

def create_window_tf_dataset(dataset):
# transforms the embeddings into a windowed dataset
embeddings_list = dataset["embeddings"].tolist()
embeddings_array = np.array(embeddings_list)
embedding_tensor = tf.convert_to_tensor(embeddings_array)
df_tensor  = tf.convert_to_tensor(embedding_tensor)
tensor_dataset = tf.data.Dataset.from_tensor_slices(df_tensor)
windowed_dataset = tensor_dataset.window(WINDOW_SIZE, shift=WINDOW_SIZE, drop_remainder=True)
windowed_dataset = windowed_dataset.flat_map(lambda window: window.batch(WINDOW_SIZE))
return windowed_dataset

logging.info(f"Training {training_data.shape}")
logging.info(f"Validation {validation_data.shape}")
logging.info(f"Test {test_data.shape}")

num_windows = sum(1 for _ in create_window_tf_dataset(training_data))
print(f"Number of windows created: {num_windows}") # 1515

training_data = create_window_tf_dataset(training_data).map(lambda window: (window, window)) # training data is normal
validation_data = create_window_tf_dataset(validation_data).map(lambda window: (window, window)) # training data is normal
test_data_normal = create_window_tf_dataset(test_data_normal).map(lambda window: (window, window)) # normal training data is normal
test_data_abnormal = create_window_tf_dataset(test_data_abnormal).map(lambda window: (window, window)) # abnormal training data is abnormal

# group normal and abnormal data
test_data = test_data_normal.concatenate(test_data_abnormal)

training_data = training_data.batch(BATCH_SIZE)
validation_data = validation_data.batch(BATCH_SIZE)
test_data = test_data.batch(BATCH_SIZE)
for x, y in training_data.take(1):
print("Input shape:", x.shape) # (32, 100, 384)
print("Label shape:", y.shape) # (32, 100, 384)
train_batches = sum(1 for _ in training_data)
print(f"Counted training batches: {train_batches}") # 48

# Build the Autoencoder model
model = models.Sequential([
Input(shape=(WINDOW_SIZE, embedding_length)),
layers.LSTM(64, return_sequences=True),
layers.LSTM(32, return_sequences=False),
layers.RepeatVector(WINDOW_SIZE),
layers.LSTM(32, return_sequences=True),
layers.LSTM(64, return_sequences=True),
layers.TimeDistributed(layers.Dense(embedding_length))
])

# Compile the model
model.compile(optimizer='adam', loss='mse')

# Train the model
model.fit(training_data, epochs=50, validation_data=validation_data) # error occurs here
# [... evaluation ...]

Дополнительная информация
Моя версия Tensorflow - 2.17.0 .


Подробнее здесь: https://stackoverflow.com/questions/795 ... ing-with-s