Tensorflow数据集：作物/调整的图像，每批处理后的数据集。批()

一般来说，可以尝试一些东西，像这样：

import tensorflow as tf
import numpy as np

dataset1 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 300, 300, 3)))
dataset2 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 224, 224, 3)))
dataset3 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 400, 400, 3)))
dataset = dataset1.concatenate(dataset2.concatenate(dataset3))
dataset = dataset.shuffle(1).repeat().batch(32, drop_remainder=True)

def resize_data(images):
  tf.print('Original shape -->', tf.shape(images))
  SIZE = (180, 180)

  return tf.image.resize(images, SIZE)

dataset = dataset.map(resize_data)

for images in dataset.take(3):
  tf.print('New shape -->', tf.shape(images))

Original shape --> [32 300 300 3]
New shape --> [32 180 180 3]
Original shape --> [32 224 224 3]
New shape --> [32 180 180 3]
Original shape --> [32 400 400 3]
New shape --> [32 180 180 3]

你也可以使用 tf.image.resize_with_crop_or_pad 如果你想要的：

def resize_data(images):
  tf.print('Original shape -->', tf.shape(images))
  SIZE = (180, 180)
  return tf.image.resize_with_crop_or_pad(images, SIZE[0], SIZE[1])

dataset = dataset.map(resize_data)

for images in dataset.take(3):
  tf.print('New shape -->', tf.shape(images))

注意使用 repeat() 将创建一个无限的数据集。

1更新

如果你想要一个随机的尺寸，对每批的，试试这样的事情：

import tensorflow as tf
import numpy as np

dataset1 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 300, 300, 3)))
dataset2 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 224, 224, 3)))
dataset3 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 400, 400, 3)))
dataset = dataset1.concatenate(dataset2.concatenate(dataset3))
dataset = dataset.batch(32, drop_remainder=True).shuffle(96)


def resize_data(images):
  batch_size = tf.shape(images)[0]
  images_resized = tf.TensorArray(dtype=tf.float32, size = 0, dynamic_size=True)
  SIZE = tf.random.uniform((2,), minval=300, maxval=500, dtype=tf.int32)
  for i in range(batch_size):
    images_resized = images_resized.write(images_resized.size(), tf.image.resize(images[i], SIZE))
  return images_resized.stack()

dataset = dataset.map(resize_data)

for images in dataset:
  tf.print('New shape -->', tf.shape(images))

New shape --> [32 392 385 3]
New shape --> [32 468 459 3]
New shape --> [32 466 461 3]

更新2

一个非常灵活的选择，适用于任何批的大小看起来是这样的：

import tensorflow as tf
import numpy as np

dataset1 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 300, 300, 3)))
dataset2 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 224, 224, 3)))
dataset3 = tf.data.Dataset.from_tensor_slices(np.random.random((32, 400, 400, 3)))
dataset = dataset1.concatenate(dataset2.concatenate(dataset3))

def resize_and_batch(dataset, batch_size):
  final_dataset = None
  duration = len(dataset)//batch_size
  random_sizes = [tf.random.uniform((2,), minval=300, maxval=500, dtype=tf.int32) for _ in range(duration)]

  for i, size in zip(range(duration), random_sizes):
    idx = i * batch_size
    if i == 0:
      final_dataset = tf.data.Dataset.from_tensor_slices([tf.image.resize(x, size) for x in dataset.take(batch_size)])
    else:
      final_dataset = final_dataset.concatenate(tf.data.Dataset.from_tensor_slices([tf.image.resize(x, size) for x in dataset.skip(idx).take(batch_size)]))
  return final_dataset

batch_size = 10
ds = resize_and_batch(dataset, batch_size)
ds = ds.batch(batch_size).shuffle(len(ds))
for images in ds:
 tf.print('New shape -->', images.shape)

New shape --> TensorShape([10, 399, 348, 3])
New shape --> TensorShape([10, 356, 329, 3])
New shape --> TensorShape([10, 473, 373, 3])
New shape --> TensorShape([10, 489, 489, 3])
New shape --> TensorShape([10, 421, 335, 3])
New shape --> TensorShape([10, 447, 455, 3])
New shape --> TensorShape([10, 355, 382, 3])
New shape --> TensorShape([10, 310, 396, 3])
New shape --> TensorShape([10, 345, 356, 3])