def test_random_contrast_int_dtype(self):
with CustomObjectScope(
{'RandomContrast': image_preprocessing.RandomContrast}):
input_images = np.random.randint(low=0,
high=255,
size=(2, 5, 8, 3))
with tf_test_util.use_gpu():
layer = image_preprocessing.RandomContrast((0.1, 0.2))
layer(input_images)
def test_random_contrast_inference(self):
with CustomObjectScope(
{'RandomContrast': image_preprocessing.RandomContrast}):
input_images = np.random.random((2, 5, 8, 3)).astype(np.float32)
expected_output = input_images
with tf_test_util.use_gpu():
layer = image_preprocessing.RandomContrast((0.1, 0.2))
actual_output = layer(input_images, training=False)
self.assertAllClose(expected_output, actual_output)
def _run_test(self, lower, upper, expected_output=None, mock_random=None):
np.random.seed(1337)
num_samples = 2
orig_height = 5
orig_width = 8
channels = 3
if mock_random is None:
mock_random = 0.2
inp = np.random.random(
(num_samples, orig_height, orig_width, channels))
if expected_output is None:
# reduce mean on height.
inp_mean = np.mean(inp, axis=1, keepdims=True)
# reduce mean on width.
inp_mean = np.mean(inp_mean, axis=2, keepdims=True)
expected_output = (inp - inp_mean) * mock_random + inp_mean
with test.mock.patch.object(random_ops,
'random_uniform',
return_value=mock_random):
with tf_test_util.use_gpu():
layer = image_preprocessing.RandomContrast((lower, upper))
actual_output = layer(inp, training=True)
self.assertAllClose(expected_output, actual_output)
def test_config_with_custom_name(self): layer = image_preprocessing.RandomContrast((.5, .6), name='image_preproc') config = layer.get_config() layer_1 = image_preprocessing.RandomContrast.from_config(config) self.assertEqual(layer_1.name, layer.name)
import tensorflow as tf # 2.4
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.python.keras.layers.preprocessing import image_preprocessing
from tensorflow.keras.applications import EfficientNetB1, Xception
# 数据增强
image_augmentation = Sequential(
[
image_preprocessing.RandomRotation(factor=0.1), # 随机旋转
image_preprocessing.RandomTranslation(height_factor=0.1,
width_factor=0.1), # 随机平移
image_preprocessing.RandomFlip(), # 随机翻转
image_preprocessing.RandomContrast(factor=0.1), # 随机改变对比度
image_preprocessing.RandomZoom(height_factor=0.1,
width_factor=0.1), # 随机缩放
# image_preprocessing.RandomHeight(factor=0.1), # 随机改变高度
# image_preprocessing.RandomWidth(factor=0.1), # 随机改变宽度
# image_preprocessing.RandomCrop(height, width), # 随机裁剪
# image_preprocessing.CenterCrop(height, width), # 中心裁剪
],
name="img_augmentation",
)
def get_time_suffix(suffix_len=15):
"""获取一个时间后缀"""
import time
time_suffix = str(time.perf_counter())