def test_distribution(self, distribution):
if "CentralStorage" in type(distribution).__name__:
self.skipTest("Does not work with CentralStorageStrategy yet.")
# TODO(b/159738418): large image input causes OOM in ubuntu multi gpu.
np_images = np.random.random((32, 32, 32, 3)).astype(np.float32)
image_dataset = dataset_ops.Dataset.from_tensor_slices(
np_images).batch(16, drop_remainder=True)
with distribution.scope():
input_data = keras.Input(shape=(32, 32, 3), dtype=dtypes.float32)
image_preprocessor = keras.Sequential([
image_preprocessing.Resizing(height=256, width=256),
image_preprocessing.RandomCrop(height=224, width=224),
image_preprocessing.RandomTranslation(.1, .1),
image_preprocessing.RandomRotation(.2),
image_preprocessing.RandomFlip(),
image_preprocessing.RandomZoom(.2, .2)
])
preprocessed_image = image_preprocessor(input_data)
flatten_layer = keras.layers.Flatten(data_format="channels_last")
output = flatten_layer(preprocessed_image)
cls_layer = keras.layers.Dense(units=1, activation="sigmoid")
output = cls_layer(output)
model = keras.Model(inputs=input_data, outputs=output)
model.compile(loss="binary_crossentropy")
_ = model.predict(image_dataset)
def test_random_zoom_inference(self):
with CustomObjectScope({'RandomZoom': image_preprocessing.RandomZoom}):
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.RandomZoom(.5, .5)
actual_output = layer(input_images, training=0)
self.assertAllClose(expected_output, actual_output)
def test_random_zoom_in_numeric(self):
for dtype in (np.int64, np.float32):
with tf_test_util.use_gpu():
input_image = np.reshape(np.arange(0, 25), (5, 5, 1)).astype(dtype)
layer = image_preprocessing.RandomZoom((-.5, -.5), (-.5, -.5),
interpolation='nearest')
output_image = layer(np.expand_dims(input_image, axis=0))
# pyformat: disable
expected_output = np.asarray([
[6, 7, 7, 8, 8],
[11, 12, 12, 13, 13],
[11, 12, 12, 13, 13],
[16, 17, 17, 18, 18],
[16, 17, 17, 18, 18]
]).astype(dtype)
# pyformat: enable
expected_output = np.reshape(expected_output, (1, 5, 5, 1))
self.assertAllEqual(expected_output, output_image)
def test_random_zoom_out_numeric_preserve_aspect_ratio(self):
for dtype in (np.int64, np.float32):
with tf_test_util.use_gpu():
input_image = np.reshape(np.arange(0, 25), (5, 5, 1)).astype(dtype)
layer = image_preprocessing.RandomZoom((.5, .5),
fill_mode='constant',
interpolation='nearest')
output_image = layer(np.expand_dims(input_image, axis=0))
# pyformat: disable
expected_output = np.asarray([
[0, 0, 0, 0, 0],
[0, 6, 7, 9, 0],
[0, 11, 12, 14, 0],
[0, 21, 22, 24, 0],
[0, 0, 0, 0, 0]
]).astype(dtype)
# pyformat: enable
expected_output = np.reshape(expected_output, (1, 5, 5, 1))
self.assertAllEqual(expected_output, output_image)
def bm_layer_implementation(self, batch_size):
with ops.device_v2("/gpu:0"):
img = keras.Input(shape=(256, 256, 3), dtype=dtypes.float32)
preprocessor = keras.Sequential([
image_preprocessing.Resizing(224, 224),
image_preprocessing.RandomCrop(height=224, width=224),
image_preprocessing.RandomRotation(factor=(.2, .4)),
image_preprocessing.RandomFlip(mode="horizontal"),
image_preprocessing.RandomZoom(.2, .2)
])
_ = preprocessor(img)
num_repeats = 5
starts = []
ends = []
for _ in range(num_repeats):
ds = dataset_ops.Dataset.from_tensor_slices(
np.random.random((batch_size, 256, 256, 3)))
ds = ds.shuffle(batch_size * 100)
ds = ds.batch(batch_size)
ds = ds.prefetch(batch_size)
starts.append(time.time())
count = 0
# Benchmarked code begins here.
for i in ds:
_ = preprocessor(i)
count += 1
# Benchmarked code ends here.
ends.append(time.time())
avg_time = np.mean(np.array(ends) - np.array(starts)) / count
name = "image_preprocessing|batch_%s" % batch_size
baseline = self.run_dataset_implementation(batch_size)
extras = {
"dataset implementation baseline": baseline,
"delta seconds": (baseline - avg_time),
"delta percent": ((baseline - avg_time) / baseline) * 100
}
self.report_benchmark(iters=num_repeats,
wall_time=avg_time,
extras=extras,
name=name)
def test_distribution(self, distribution):
np_images = np.random.random((1000, 32, 32, 3)).astype(np.float32)
image_dataset = dataset_ops.Dataset.from_tensor_slices(
np_images).batch(32, drop_remainder=True)
with distribution.scope():
input_data = keras.Input(shape=(32, 32, 3), dtype=dtypes.float32)
image_preprocessor = keras.Sequential([
image_preprocessing.Resizing(height=256, width=256),
image_preprocessing.RandomCrop(height=224, width=224),
image_preprocessing.RandomTranslation(.1, .1),
image_preprocessing.RandomRotation(.2),
image_preprocessing.RandomFlip(),
image_preprocessing.RandomZoom(.2, .2)
])
preprocessed_image = image_preprocessor(input_data)
flatten_layer = keras.layers.Flatten(data_format="channels_last")
output = flatten_layer(preprocessed_image)
cls_layer = keras.layers.Dense(units=1, activation="sigmoid")
output = cls_layer(output)
model = keras.Model(inputs=input_data, outputs=preprocessed_image)
model.compile(loss="binary_crossentropy")
_ = model.predict(image_dataset)
def test_config_with_custom_name(self): layer = image_preprocessing.RandomZoom(.5, .6, name='image_preproc') config = layer.get_config() layer_1 = image_preprocessing.RandomZoom.from_config(config) self.assertEqual(layer_1.name, layer.name)
def test_random_zoom_invalid_factor(self):
with self.assertRaises(ValueError):
image_preprocessing.RandomZoom((.5, .4), .2)
with self.assertRaises(ValueError):
image_preprocessing.RandomZoom(.2, (.5, .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())
time_suffix = time_suffix.replace('.', '')
time_suffix.rjust(suffix_len, '0')
