#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Tensorflow op performing correlation cost operation."""
import tensorflow as tf
from typeguard import typechecked
from tensorflow_addons.utils.resource_loader import LazySO
_correlation_cost_so = LazySO("custom_ops/layers/_correlation_cost_ops.so")
def _correlation_cost(
input_a,
input_b,
kernel_size,
max_displacement,
stride_1,
stride_2,
pad,
data_format="channels_last",
name=None,
):
"""Correlation Cost Volume computation.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Python layer for distort_image_ops."""
import tensorflow as tf
from tensorflow_addons.utils.resource_loader import LazySO
_distort_image_so = LazySO("custom_ops/image/_distort_image_ops.so")
# pylint: disable=invalid-name
def random_hsv_in_yiq(image,
max_delta_hue=0,
lower_saturation=1,
upper_saturation=1,
lower_value=1,
upper_value=1,
seed=None,
name=None):
"""Adjust hue, saturation, value of an RGB image randomly in YIQ color
space.
Equivalent to `adjust_yiq_hsv()` but uses a `delta_h` randomly
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Parse time ops."""
import tensorflow as tf
from tensorflow_addons.utils.resource_loader import LazySO
_parse_time_so = LazySO("custom_ops/text/_parse_time_op.so")
tf.no_gradient("Addons>ParseTime")
def parse_time(time_string: str, time_format: str, output_unit: str) -> str:
"""Parse an input string according to the provided format string into a
Unix time.
Parse an input string according to the provided format string into a Unix
time, the number of seconds / milliseconds / microseconds / nanoseconds
elapsed since January 1, 1970 UTC.
Uses strftime()-like formatting options, with the same extensions as
FormatTime(), but with the exceptions that %E#S is interpreted as %E*S, and
%E#f as %E*f. %Ez and %E*z also accept the same inputs.
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
import warnings
import tensorflow as tf
from tensorflow_addons.utils.types import Number
from tensorflow_addons.utils import types
from tensorflow_addons.utils.resource_loader import LazySO
from tensorflow_addons import options
_activation_so = LazySO("custom_ops/activations/_activation_ops.so")
@tf.keras.utils.register_keras_serializable(package="Addons")
def hardshrink(
x: types.TensorLike, lower: Number = -0.5, upper: Number = 0.5
) -> tf.Tensor:
"""Hard shrink function.
Computes hard shrink function:
`x if x < lower or x > upper else 0`.
Args:
x: A `Tensor`. Must be one of the following types:
`float16`, `float32`, `float64`.
lower: `float`, lower bound for setting values to zeros.
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
import tensorflow as tf
from typeguard import typechecked
from tensorflow_addons.utils.types import Constraint, Initializer, Regularizer
from tensorflow_addons.utils.resource_loader import LazySO
_embedding_bag_so = LazySO("custom_ops/layers/_embedding_bag_ops.so")
def _embedding_bag(
indices,
params,
weights=None,
combiner="sum",
name=None,
):
"""EmbeddingBag computation.
See [PyTorch op](https://pytorch.org/docs/stable/generated/torch.nn.EmbeddingBag.html).
Equivalent to tf.gather() followed by tf.reduce_{sum,mean}() across the last dimension, with optional
weights. Fusing these into a single op has massive benefits for execution speed and particularly
from datetime import datetime
from malaya import home, _delete_folder, gpu_available, __gpu__
URL = 'https://f000.backblazeb2.com/file/malaya-model/'
def check_tf_version():
version = tf.__version__
return int(version.split('.')[0])
if check_tf_version() > 1:
try:
from tensorflow_addons.utils.resource_loader import LazySO
_beam_search_so = LazySO('custom_ops/seq2seq/_beam_search_ops.so')
gather_tree = _beam_search_so.ops.addons_gather_tree
except:
import warnings
warnings.warn(
'Cannot import beam_search_ops from Tensorflow Addons, `deep_model` for stemmer will not available to use, make sure Tensorflow Addons version >= 0.12.0'
)
else:
try:
from tensorflow.contrib.seq2seq.python.ops import beam_search_ops
except:
import warnings
warnings.warn(
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Skip-gram sampling ops from https://arxiv.org/abs/1301.3781."""
import csv
import tensorflow as tf
from tensorflow_addons.utils.resource_loader import LazySO
from tensorflow_addons.utils.types import AcceptableDTypes, FloatTensorLike, TensorLike
from typing import Optional
_skip_gram_so = LazySO("custom_ops/text/_skip_gram_ops.so")
tf.no_gradient("Addons>SkipGramGenerateCandidates")
def skip_gram_sample(
input_tensor: TensorLike,
min_skips: FloatTensorLike = 1,
max_skips: FloatTensorLike = 5,
start: FloatTensorLike = 0,
limit: FloatTensorLike = -1,
emit_self_as_target: bool = False,
vocab_freq_table: tf.lookup.KeyValueTensorInitializer = None,
vocab_min_count: Optional[FloatTensorLike] = None,
vocab_subsampling: Optional[FloatTensorLike] = None,
corpus_size: Optional[FloatTensorLike] = None,
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Python layer for Resampler."""
import tensorflow as tf
from tensorflow_addons.utils import types
from tensorflow_addons.utils.resource_loader import LazySO
from typing import Optional
_resampler_so = LazySO("custom_ops/image/_resampler_ops.so")
@tf.function
def resampler(data: types.TensorLike,
warp: types.TensorLike,
name: Optional[str] = None) -> tf.Tensor:
"""Resamples input data at user defined coordinates.
The resampler currently only supports bilinear interpolation of 2D data.
Args:
data: Tensor of shape `[batch_size, data_height, data_width,
data_num_channels]` containing 2D data that will be resampled.
warp: Tensor of minimum rank 2 containing the coordinates at
which resampling will be performed. Since only bilinear
