出于某种原因,我写入 tensorflow 记录的 numpy 数组(形状为 55,290)在我再次读取时与同一 tensorflow 记录的输出不匹配。
这是我用来编写 tfrecord 的代码:
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _float_feature(value):
"""Returns a float_list from a float / double."""
return tf.train.Feature(float_list=tf.train.FloatList(value=value))
def serialize_data(X, y):
feature = {
'n_wavelength_channels': _int64_feature(55),
'n_time_steps': _int64_feature(290),
'rel_radii': _float_feature(y),
'rel_flux': _float_feature(X.flatten()),
}
return tf.train.Example(features=tf.train.Features(feature=feature)).SerializeToString()
def tf_record_generator():
X_file_chunk = ["E:/ml_data_challenge_database/noisy_train/0001_01_01.txt"]
y_file_chunk = ["E:/ml_data_challenge_database/params_train/0001_01_01.txt"]
data = []
labels = []
for X_file, y_file in zip(X_file_chunk, y_file_chunk):
X = np.genfromtxt(X_file, dtype=np.float32)[:,10:]
y = np.genfromtxt(y_file, dtype=np.float32)
yield serialize_data(X, y)
n_splits = 1
tfrecord_filename = "training_record_{}.tfrecords"
for index in range(n_splits): # Number of splits
writer = tf.data.experimental.TFRecordWriter(tfrecord_filename.format(index))
serialized_features_dataset = tf.data.Dataset.from_generator(tf_record_generator, output_types=tf.string, output_shapes=())
writer.write(serialized_features_dataset)
这是我用来读取刚刚写入的记录的代码:
def parse_record(record):
name_to_features = {
'n_wavelength_channels': tf.io.FixedLenFeature([], tf.int64),
'n_time_steps': tf.io.FixedLenFeature([], tf.int64),
'rel_radii': tf.io.FixedLenFeature([55], tf.float32),
'rel_flux': tf.io.FixedLenFeature([55*290], tf.float32),
}
return tf.io.parse_single_example(record, name_to_features)
def decode_record(record):
parsed_record = parse_record(record)
flux = parsed_record['rel_flux']
radii = parsed_record['rel_radii']
return flux, radii
def get_batched_dataset(filenames):
option_no_order = tf.data.Options()
option_no_order.experimental_deterministic = False
dataset = tf.data.Dataset.list_files(filenames)
dataset = dataset.with_options(option_no_order)
dataset = dataset.interleave(tf.data.TFRecordDataset, num_parallel_calls=tf.data.AUTOTUNE)
dataset = dataset.map(decode_record, num_parallel_calls=tf.data.AUTOTUNE)
dataset = dataset.repeat()
dataset = dataset.shuffle(2048)
dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)
dataset = dataset.prefetch(tf.data.AUTOTUNE) #
return dataset
def get_training_dataset():
return get_batched_dataset(training_filenames)
BATCH_SIZE=1
training_filenames = tf.io.gfile.glob("training_record_*.tfrecords")
training_data = get_training_dataset()
X_batch, y_batch = next(iter(training_data))
def show_batch(X_batch, y_batch):
for i in X_batch:
plt.plot(i.reshape(290,55))
plt.show()
show_batch(X_batch.numpy(), y_batch.numpy())
这是我正在研究的神经网络输入的一部分,我尝试修改它以从单个训练观察创建一个 tfrecord,然后输出该观察。
tfrecord 的输出如下所示:
这是它应该是什么样子(原始观察):
X = np.genfromtxt("E:/ml_data_challenge_database/noisy_train/0001_01_01.txt")
plt.plot(X.T[10:,:])
plt.show()
(同时绘制所有 55 行)。
The y values read in from the tfrecord actually match the true y values, but I've got no idea why the X data seems to be incorrect. I've been following a number of guides closely but am very new at working with TF data. Could someone please take a look at my code and point out anything I may have done wrong? Thank you very much in advance!
Here's a Google drive link to the X data (referenced in "X_file_chunk" inside tf_record_generator) and here's one to the y data (also inside tf_record_generator)
When you're reshaping back to 2D you mixing up with dimensions - it should be i.reshape(55,290).T
In this case, the plot is identical to the original data.
顺便说一句,您的数据确实是float64
格式,因此当您读取/绘制原始数据时,您使用float64
. 来自tf.Dataset
is 的数据float32
。虽然这不是你的情节不同的原因。
本文收集自互联网,转载请注明来源。
如有侵权,请联系 [email protected] 删除。
我来说两句