我想使用crop_central
函数,且其随机浮点在0.50-1.00之间,以进行数据增强。但是,当使用numpy.random.uniform(0.50, 1.00)
并绘制图像时,裁切是恒定的。我通过使用4张图像并绘制8行进行调试,这些图像是相同的。
通常,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
以前,我误读了这个问题。这是您正在寻找的答案。
我可以使用以下代码重新创建您的问题-
重现该问题的代码-裁剪图像的输出全部相同。
%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
Output-第一行是原始图像。剩余的行是作物图像。
嗯,这非常具有挑战性,下面提供了两种解决方案-
解决方案1:使用np.random.uniform
和tf.py_function
。
np.random.uniform(0.50, 1.00)
。tf.py_function
修饰功能调用-tf.py_function(data_augment, [x], [tf.float32])
。解决问题的代码- 裁切输出图像现在不同并且不相同。
%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
Output-第一行是原始图像。剩余的行是“裁剪图像”。
解决方案2:使用tf.random.uniform
和tf.py_function
。
tf.random.uniform(shape=(), minval=0.50, maxval=1).numpy()
。AttributeError: 'Tensor' object has no attribute 'numpy'
而无法正常工作。要解决此问题,您需要使用tf.py_function(data_augment, [x], [tf.float32])
装饰您的功能。解决问题的代码- 裁切输出图像现在不同并且不相同。
%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, 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
Output-第一行是原始图像。剩余的行是作物图像。
希望这能回答您的问题。祝您学习愉快。