如何从特定班级中抽样批次? [英] How to sample batch from a specific class?

问题描述

我想在一个 ImageNet 数据集上训练分类器(1000 个类，每个类有大约 1300 张图像).出于某种原因，我需要每个批次包含来自特定类(以 int 或占位符形式提供)的 64 张图像.如何使用最新的 TensorFlow 高效地做到这一点?

I'd like to train a classifier on one ImageNet dataset (1000 classes each with around 1300 images). For some reason, I need each batch to contain 64 images from a specific class (provided as int or placeholder). How to do it efficiently with the latest TensorFlow?

这是如何在每次迭代中仅从一个类中采样批次.

我目前的想法是使用tf.data.Dataset.filter:

specific_class = 2  # as an example

dataset = tf.data.TFRecordDataset(filenames)
# __parser_fun__ produces datum tuple (x, y)
dataset = dataset.map(__parser_fun__, num_parallel_calls=num_threads)
dataset = dataset.shuffle(20000)
# print(dataset) gives <ShuffleDataset shapes: ((3, 128, 128), (1,)), 
# types: (tf.float32, tf.int64)>

dataset = dataset.filter(lambda x, y: tf.equal(y[0], specific_class))
dataset = dataset.batch(64)
dataset = dataset.repeat()
iterator = dataset.make_one_shot_iterator()
x_batch, y_batch = iterator.get_next()

filter 的一个小问题是，每次我想从一个新类中采样时，我都需要构造一个迭代器.

A minor problem with filter is that I need to construct an iterator every time I want to sample from a new class.

另一个想法是使用 tf.contrib.data.rejection_resample 但它在计算上似乎令人望而却步(或者是吗?).

Another idea is to use tf.contrib.data.rejection_resample but it seems prohibitive computationally (or is it?).

我想知道是否有其他有效的方法可以从特定类中抽样批次?

I wonder if there is other efficient way to sample batches from a particular class?

推荐答案

从概念上讲，您的数据集是由一个变量(要采样的标签)参数化的.这是完全可行的！

Conceptually your Dataset is parameterized by a variable (the label to sample). This is totally doable!

急切地执行:

import numpy as np
import tensorflow as tf
tf.enable_eager_execution()

data = dict(
    x=tf.constant([1., 2., 3., 4.]),
    y=tf.constant([1, 2, 1, 2])
)

requested_label = tf.Variable(1)
dataset = (
    tf.data.Dataset.from_tensor_slices(data)
    .repeat()
    .filter(lambda d: tf.equal(d["y"], requested_label)))


it = dataset.make_one_shot_iterator()
for i, datum in enumerate(it):
  assert int(datum["y"]) == 1
  assert float(datum["x"]) in [1., 3.]
  if i > 5:
    break

requested_label.assign(2)

for i, datum in enumerate(it):
  assert int(datum["y"]) == 2
  assert float(datum["x"]) in [2., 4.]
  if i > 5:
    break

图构建:

import tensorflow as tf

graph = tf.Graph()
with graph.as_default():
  data = dict(
      x=tf.constant([1., 2., 3., 4.]),
      y=tf.constant([1, 2, 1, 2])
  )

  requested_label = tf.Variable(1)
  dataset = (
      tf.data.Dataset.from_tensor_slices(data)
      .repeat()
      .filter(lambda d: tf.equal(d["y"], requested_label)))


  it = dataset.make_initializable_iterator()
  datum_tensors = it.get_next()
  switch_label_op = requested_label.assign(2)

  graph.finalize()
  with tf.Session() as session:
    session.run(requested_label.initializer)  # label=1
    session.run(it.initializer)
    for _ in range(5):
      datum = session.run(datum_tensors)
      assert int(datum["y"]) == 1
      assert float(datum["x"]) in [1., 3.]

    session.run(switch_label_op)  # label=2

    for _ in range(5):
      datum = session.run(datum_tensors)
      assert int(datum["y"]) == 2
      assert float(datum["x"]) in [2., 4.]

这篇关于如何从特定班级中抽样批次?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！