Python 数据增广映射函数中的Tensorflow随机数

我想使用

crop_central

函数，随机浮动范围为0.50-1.00，用于数据扩充。但是，当使用

numpy.random.uniform（0.50,1.00）

并绘制图像时，裁剪是恒定的。我通过使用4个图像和绘制8行进行调试，这些图像是相同的

一般来说，这个问题可以表述如下：如何在数据集映射函数中使用随机数

def data_augment(image, label=None, seed=2020):
    # I want a random number here for every individual image
    image = tf.image.central_crop(image, np.random.uniform(0.50, 1.00)) # random crop central
    image = tf.image.resize(image, INPUT_SHAPE) # the original image size

    return image

train_dataset = (
    tf.data.Dataset
        .from_tensor_slices((train_paths, train_labels))
        .map(decode_image, num_parallel_calls=AUTO)
        .map(data_augment, num_parallel_calls=AUTO)
        .repeat()
        .batch(4)
        .prefetch(AUTO)
    )

# Code to view the images
for idx, (imgs, _) in enumerate(train_dataset):
    show_imgs(imgs, 'image', imgs_per_row=4)
    if idx is 8:
        del imgs
        gc.collect()
        break

---

早些时候，我误解了这个问题。这是你一直在寻找的答案

我可以使用下面的代码重新创建您的问题-

再现问题的代码-作物图像的输出完全相同

%tensorflow_version 2.x
import tensorflow as tf
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array, array_to_img
from matplotlib import pyplot as plt
import numpy as np
AUTOTUNE = tf.data.experimental.AUTOTUNE

# Set the sub plot parameters
f, axarr = plt.subplots(5,4,figsize=(15, 15))

# Load just 4 images of Cifar10
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
images = x_train[:4]

for i in range(4):
  axarr[0,i].title.set_text('Original Image')
  axarr[0,i].imshow(x_train[i])

def data_augment(images):
    image = tf.image.central_crop(images, np.random.uniform(0.50, 1.00)) # random crop central
    image = tf.image.resize(image, (32,32)) # the original image size
    return image

dataset = tf.data.Dataset.from_tensor_slices((images)).map(lambda x: data_augment(x)).repeat(4) 

print(dataset)

ix = 0
i = 1
count = 0

for f in dataset:
  crop_img = array_to_img(f)
  axarr[i,ix].title.set_text('Crop Image')
  axarr[i,ix].imshow(crop_img)
  ix=ix+1
  count = count + 1
  if count == 4:
    i = i + 1
    count = 0
    ix = 0

输出-第一行是原始图像。其余行是裁剪图像

这非常具有挑战性，我们提供了以下两种解决方案-

解决方案1:使用

np.random.uniform

和

tf.py_函数

使用

np.随机.均匀（0.50,1.00）

使用

tf.py_函数

来修饰函数调用-

tf.py_函数（data_augment[x]，[tf.float32]）

解决问题的代码-作物输出图像现在不同且不完全相同。

%tensorflow_version 2.x
import tensorflow as tf
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array, array_to_img
from matplotlib import pyplot as plt
import numpy as np
AUTOTUNE = tf.data.experimental.AUTOTUNE

# Set the sub plot parameters
f, axarr = plt.subplots(5,4,figsize=(15, 15))

# Load just 4 images of Cifar10
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
images = x_train[:4]

for i in range(4):
  axarr[0,i].title.set_text('Original Image')
  axarr[0,i].imshow(x_train[i])

def data_augment(images):
    image = tf.image.central_crop(images, np.random.uniform(0.50, 1.00)) # random crop central
    image = tf.image.resize(image, (32,32)) # the original image size
    return image

dataset = tf.data.Dataset.from_tensor_slices((images)).map(lambda x: tf.py_function(data_augment, [x], [tf.float32])).repeat(4)

ix = 0
i = 1
count = 0

for f in dataset:
  for l in f:
    crop_img = array_to_img(l)
    axarr[i,ix].title.set_text('Crop Image')
    axarr[i,ix].imshow(crop_img)
    ix=ix+1
    count = count + 1
    if count == 4:
      i = i + 1
      count = 0
      ix = 0

%tensorflow_version 2.x
import tensorflow as tf
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array, array_to_img
from matplotlib import pyplot as plt
import numpy as np
AUTOTUNE = tf.data.experimental.AUTOTUNE

# Set the sub plot parameters
f, axarr = plt.subplots(5,4,figsize=(15, 15))

# Load just 4 images of Cifar10
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
images = x_train[:4]

for i in range(4):
  axarr[0,i].title.set_text('Original Image')
  axarr[0,i].imshow(x_train[i])

def data_augment(images):
    image = tf.image.central_crop(images, tf.random.uniform(shape=(), minval=0.50, maxval=1).numpy()) # random crop central
    image = tf.image.resize(image, (32,32)) # the original image size
    return image

dataset = tf.data.Dataset.from_tensor_slices((images)).map(lambda x: tf.py_function(data_augment, [x], [tf.float32])).repeat(4)

ix = 0
i = 1
count = 0

for f in dataset:
  for l in f:
    crop_img = array_to_img(l)
    axarr[i,ix].title.set_text('Crop Image')
    axarr[i,ix].imshow(crop_img)
    ix=ix+1
    count = count + 1
    if count == 4:
      i = i + 1
      count = 0
      ix = 0

输出-第一行是原始图像。其余行是裁剪图像

解决方案2:使用

tf.random.uniform

和

tf.py_函数

使用了

tf.random.uniform（shape=（），minval=0.50，maxval=1）.numpy（）

仅通过使用上述选项，代码就无法工作，因为它会抛出错误

AttributeError:“Tensor”对象没有属性“numpy”

。要解决此问题，您需要使用

tf.py\u函数（data\u augment[x]，[tf.float32]）

来修饰函数

解决问题的代码-作物输出图像现在不同且不完全相同。

%tensorflow_version 2.x
import tensorflow as tf
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array, array_to_img
from matplotlib import pyplot as plt
import numpy as np
AUTOTUNE = tf.data.experimental.AUTOTUNE

# Set the sub plot parameters
f, axarr = plt.subplots(5,4,figsize=(15, 15))

# Load just 4 images of Cifar10
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
images = x_train[:4]

for i in range(4):
  axarr[0,i].title.set_text('Original Image')
  axarr[0,i].imshow(x_train[i])

def data_augment(images):
    image = tf.image.central_crop(images, np.random.uniform(0.50, 1.00)) # random crop central
    image = tf.image.resize(image, (32,32)) # the original image size
    return image

dataset = tf.data.Dataset.from_tensor_slices((images)).map(lambda x: tf.py_function(data_augment, [x], [tf.float32])).repeat(4)

ix = 0
i = 1
count = 0

for f in dataset:
  for l in f:
    crop_img = array_to_img(l)
    axarr[i,ix].title.set_text('Crop Image')
    axarr[i,ix].imshow(crop_img)
    ix=ix+1
    count = count + 1
    if count == 4:
      i = i + 1
      count = 0
      ix = 0

%tensorflow_version 2.x
import tensorflow as tf
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array, array_to_img
from matplotlib import pyplot as plt
import numpy as np
AUTOTUNE = tf.data.experimental.AUTOTUNE

# Set the sub plot parameters
f, axarr = plt.subplots(5,4,figsize=(15, 15))

# Load just 4 images of Cifar10
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
images = x_train[:4]

for i in range(4):
  axarr[0,i].title.set_text('Original Image')
  axarr[0,i].imshow(x_train[i])

def data_augment(images):
    image = tf.image.central_crop(images, tf.random.uniform(shape=(), minval=0.50, maxval=1).numpy()) # random crop central
    image = tf.image.resize(image, (32,32)) # the original image size
    return image

dataset = tf.data.Dataset.from_tensor_slices((images)).map(lambda x: tf.py_function(data_augment, [x], [tf.float32])).repeat(4)

ix = 0
i = 1
count = 0

for f in dataset:
  for l in f:
    crop_img = array_to_img(l)
    axarr[i,ix].title.set_text('Crop Image')
    axarr[i,ix].imshow(crop_img)
    ix=ix+1
    count = count + 1
    if count == 4:
      i = i + 1
      count = 0
      ix = 0

输出-第一行是原始图像。其余行是裁剪图像

---

希望这能回答你的问题。快乐学习。

@Mark wijkhuizen-如果答案回答了您的问题，请您接受并投票表决。非常感谢。