neuralmonkey package¶
Subpackages¶
- neuralmonkey.config package
- neuralmonkey.decoders package
- Submodules
- neuralmonkey.decoders.decoder module
- neuralmonkey.decoders.encoder_projection module
- neuralmonkey.decoders.multi_decoder module
- neuralmonkey.decoders.output_projection module
- neuralmonkey.decoders.sequence_classifier module
- neuralmonkey.decoders.sequence_labeler module
- neuralmonkey.decoders.word_alignment_decoder module
- Module contents
- neuralmonkey.encoders package
- neuralmonkey.evaluators package
- neuralmonkey.model package
- neuralmonkey.nn package
- Submodules
- neuralmonkey.nn.bidirectional_rnn_layer module
- neuralmonkey.nn.init_ops module
- neuralmonkey.nn.mlp module
- neuralmonkey.nn.noisy_gru_cell module
- neuralmonkey.nn.ortho_gru_cell module
- neuralmonkey.nn.pervasive_dropout_wrapper module
- neuralmonkey.nn.projection module
- neuralmonkey.nn.utils module
- Module contents
- neuralmonkey.processors package
- neuralmonkey.readers package
- neuralmonkey.runners package
- neuralmonkey.tests package
- neuralmonkey.trainers package
Submodules¶
neuralmonkey.checking module¶
This module servers as a library of API checks used as assertions during constructing the computational graph.
-
exception
neuralmonkey.checking.
CheckingException
¶ Bases:
Exception
-
neuralmonkey.checking.
assert_same_shape
(tensor_a: tensorflow.python.framework.ops.Tensor, tensor_b: tensorflow.python.framework.ops.Tensor) → None¶ Check if two tensors have the same shape.
-
neuralmonkey.checking.
assert_shape
(tensor: tensorflow.python.framework.ops.Tensor, expected_shape: typing.List[typing.Union[int, NoneType]]) → None¶ Check shape of a tensor.
Parameters: - tensor – Tensor to be chcecked.
- expected_shape – Expected shape where None means the same as in TF and -1 means not checking the dimension.
-
neuralmonkey.checking.
assert_type
(obj, name, value, expected_type, can_be_none=False)¶
-
neuralmonkey.checking.
check_dataset_and_coders
(dataset, runners)¶
-
neuralmonkey.checking.
missing_attributes
(obj, attributes)¶
-
neuralmonkey.checking.
type_to_str
(type_obj)¶
neuralmonkey.dataset module¶
neuralmonkey.decoding_function module¶
Module which implements decoding functions using multiple attentions for RNN decoders.
See http://arxiv.org/abs/1606.07481
-
class
neuralmonkey.decoding_function.
Attention
(attention_states, scope, input_weights=None, attention_fertility=None)¶ Bases:
object
-
attention
(query_state)¶ Put attention masks on att_states_reshaped using hidden_features and query.
-
get_logits
(y)¶
-
-
class
neuralmonkey.decoding_function.
CoverageAttention
(attention_states, scope, input_weights=None, attention_fertility=5)¶ Bases:
neuralmonkey.decoding_function.Attention
-
get_logits
(y)¶
-
neuralmonkey.functions module¶
-
neuralmonkey.functions.
inverse_sigmoid_decay
(param, rate, min_value=0.0, max_value=1.0, name=None, dtype=tf.float32)¶ Inverse sigmoid decay: k/(k+exp(x/k)).
The result will be scaled to the range (min_value, max_value).
Parameters: - param – The parameter x from the formula.
- rate – Non-negative k from the formula.
-
neuralmonkey.functions.
piecewise_function
(param, values, changepoints, name=None, dtype=tf.float32)¶ A piecewise function.
Parameters: - param – The function parameter.
- values – List of function values (numbers or tensors).
- changepoints – Sorted list of points where the function changes from one value to the next. Must be one item shorter than values.
neuralmonkey.learning_utils module¶
neuralmonkey.logging module¶
-
class
neuralmonkey.logging.
Logging
¶ Bases:
object
-
static
debug
(message, label=None)¶
-
debug_disabled
= ['']¶
-
debug_enabled
= ['none']¶
-
static
log
(message, color='yellow')¶ Logs message with a colored timestamp.
-
log_file
= None¶
-
static
log_print
(text: str) → None¶ Prints a string both to console and a log file is it is defined.
-
static
print_header
(title)¶ Prints the title of the experiment and the set of arguments it uses.
-
static
set_log_file
(path)¶ Sets up the file where the logging will be done.
-
static
-
neuralmonkey.logging.
debug
(message, label=None)¶
-
neuralmonkey.logging.
log
(message, color='yellow')¶ Logs message with a colored timestamp.
-
neuralmonkey.logging.
log_print
(text: str) → None¶ Prints a string both to console and a log file is it is defined.
neuralmonkey.run module¶
neuralmonkey.server module¶
neuralmonkey.tf_manager module¶
neuralmonkey.tf_utils module¶
Small helper functions for TensorFlow.
-
neuralmonkey.tf_utils.
gpu_memusage
() → str¶ Return ‘’ or a string showing current GPU memory usage.
nvidia-smi result parsing based on https://github.com/wookayin/gpustat
-
neuralmonkey.tf_utils.
has_gpu
() → bool¶ Check if TensorFlow can access GPU.
- The test is based on
- https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/platform/test.py
...but we are interested only in CUDA GPU devices.
Returns: True, if TF can access the GPU
neuralmonkey.train module¶
neuralmonkey.vocabulary module¶
Module contents¶
The neuralmonkey package is the root package of this project.