[PYTHON] tensorflow : .eval ()은 끝나지 않습니다.
PYTHONtensorflow : .eval ()은 끝나지 않습니다.
내가 cifar-10 데이터 세트를로드 할 때 메서드는 텐서 배열에 데이터를 추가하므로 세션에 .eval ()을 사용하는 데이터에 액세스하려면 일반 tf 상수에서 값을 반환하지만 레이블과 열차에는 어느 것이 어느 것이 tf 배열인지는 모르겠다.
1- 나는 도커를 사용하고 있습니다. tensorflow-jupyter
2 - 파이썬 3을 사용합니다.
3- 배치 파일을 데이터 폴더에 추가해야합니다.
이 파일에서 첫 번째 일괄 처리 [data_batch_1.bin]을 사용하고 있습니다.
http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz
노트북으로 :
https://drive.google.com/open?id=0B_AFMME1kY1obkk1YmJHcjV0ODA
코드 [tensorflow 사이트에서와 마찬가지로 1 패치를 읽도록 수정] [데이터로드의 마지막 7 행 확인] :
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import urllib
import tensorflow as tf
from six.moves import xrange # pylint: disable=redefined-builtin
# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 5000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 1000
IMAGE_SIZE = 32
def _generate_image_and_label_batch(image, label, min_queue_examples,
batch_size, shuffle):
"""Construct a queued batch of images and labels.
Args:
image: 3-D Tensor of [height, width, 3] of type.float32.
label: 1-D Tensor of type.int32
min_queue_examples: int32, minimum number of samples to retain
in the queue that provides of batches of examples.
batch_size: Number of images per batch.
shuffle: boolean indicating whether to use a shuffling queue.
Returns:
images: Images. 4D tensor of [batch_size, height, width, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
# Create a queue that shuffles the examples, and then
# read 'batch_size' images + labels from the example queue.
num_preprocess_threads = 2
if shuffle:
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size,
min_after_dequeue=min_queue_examples)
else:
images, label_batch = tf.train.batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size)
# Display the training images in the visualizer.
tf.image_summary('images', images)
return images, tf.reshape(label_batch, [batch_size])
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(tf.slice(record_bytes, [label_bytes], [image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def inputs(eval_data, data_dir, batch_size):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
filenames=[];
filenames.append(os.path.join(data_dir, 'data_batch_1.bin') )
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
print(filenames)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
width, height)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_whitening(resized_image)
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)
sess = tf.InteractiveSession()
train_data,train_labels = inputs(False,"data",6000)
print (train_data,train_labels)
train_data=train_data.eval()
train_labels=train_labels.eval()
print(train_data)
print(train_labels)
sess.close()
해결법
-
==============================
1.train_data.eval () 또는 train_labels.eval ()을 호출하기 전에 tf.train.start_queue_runners (sess)를 호출해야합니다.
train_data.eval () 또는 train_labels.eval ()을 호출하기 전에 tf.train.start_queue_runners (sess)를 호출해야합니다.
TensorFlow 입력 파이프 라인이 어떻게 구현되는지에 대한 결과는 불행합니다. tf.train.string_input_producer (), tf.train.shuffle_batch () 및 tf.train.batch () 함수는 내부적으로 서로 다른 레코드를 버퍼링하는 대기열을 만듭니다 입력 파이프 라인의 스테이지. tf.train.start_queue_runners () 호출은 TensorFlow에게 이러한 버퍼로 레코드를 가져 오기 시작하도록 지시합니다. 그것을 호출하지 않고 버퍼가 비어 있고 eval ()이 무기한 정지됩니다.
from https://stackoverflow.com/questions/38589255/tensorflow-eval-never-ends by cc-by-sa and MIT license
'PYTHON' 카테고리의 다른 글
[PYTHON] 케라에서 재현 가능한 결과를 얻는 방법 (0) | 2018.11.11 |
---|---|
[PYTHON] Pandas : Excel의 병합 된 헤더 열을 구문 분석합니다. (0) | 2018.11.10 |
[PYTHON] 파이썬 Win32 시뮬레이션 클릭 (0) | 2018.11.10 |
[PYTHON] Matplotlib : 그림 개체를 사용하여 그림 초기화 (0) | 2018.11.10 |
[PYTHON] 세션 쿠키를 공유하기 위해 동일한 하위 도메인에서 별개의 장고 앱을 얻는 방법은 무엇입니까? (0) | 2018.11.10 |