Docs

Author: lvapeab

.coveragerc

@@ -148,8 +148,8 @@ def load_parameters():
                                                   # Linear reduction: new_lr = lr * LR_GAMMA
                                                   # Exponential reduction: new_lr = lr * LR_REDUCER_EXP_BASE ** (current_nb / LR_HALF_LIFE) * LR_GAMMA
                                                   # Noam reduction: new_lr = lr * min(current_nb ** LR_REDUCER_EXP_BASE, current_nb * LR_HALF_LIFE ** WARMUP_EXP)
-    LR_REDUCER_EXP_BASE = -0.5                     # Base for the exponential decay.
-    LR_HALF_LIFE = 100                           # Factor/warmup steps for exponenital/noam decay.
+    LR_REDUCER_EXP_BASE = -0.5                    # Base for the exponential decay.
+    LR_HALF_LIFE = 100                            # Factor/warmup steps for exponenital/noam decay.
     WARMUP_EXP = -1.5                             # Warmup steps for noam decay.
     MIN_LR = 1e-9                                 # Minimum value allowed for the decayed LR
 
@@ -176,7 +176,7 @@ def load_parameters():
     MODEL_TYPE = 'AttentionRNNEncoderDecoder'     # Model to train. See model_zoo.py for more info.
                                                   # Supported architectures: 'AttentionRNNEncoderDecoder' and 'Transformer'.
 
-    # Hyperparameters common to all models
+    # Common hyperparameters for all models
     # # # # # # # # # # # # # # # # # # # # # # # #
     TRAINABLE_ENCODER = True                      # Whether the encoder's weights should be modified during training.
     TRAINABLE_DECODER = True                      # Whether the decoder's weights should be modified during training.

config.py

@@ -139,6 +139,28 @@ class NMTSampler:
     def __init__(self, models, dataset, params, params_prediction, params_training, model_tokenize_f, model_detokenize_f, general_tokenize_f,
                  general_detokenize_f, mapping=None, word2index_x=None, word2index_y=None, index2word_y=None,
                  excluded_words=None, unk_id=1, eos_symbol='/', online=False, verbose=0):
+        """
+        Builds an NMTSampler: An object containing models and dataset, for the interactive-predictive and adaptive framework.
+        :param models:
+        :param dataset:
+        :param dict params: All hyperparameters of the model.
+        :param dict params_prediction: Hyperparameters regarding prediction and search.
+        :param dict params_training:  Hyperparamters regarding incremental training.
+        :param function model_tokenize_f: Function used for tokenizing the input sentence. E.g. BPE.
+        :param function model_detokenize_f: Function used for detokenizing the output sentence. E.g. BPE revert.
+        :param function general_tokenize_f: Function used for tokenizing the input sentence. E.g. Moses tokenizer.
+        :param function general_detokenize_f: Function used for detokenizing the output sentence. E.g. Moses detokenizer.
+        :param dict mapping: Source-target dictionary (for unk_replace heuristics 1 and 2).
+        :param dict word2index_x: Mapping from word strings into indices for the source language.
+        :param dict word2index_y: Mapping from word strings into indices for the target language.
+        :param dict index2word_y: Mapping from indices into word strings for the target language.
+        :param dict excluded_words: words that won't be generated in the middle of two isles. Currenly unused.
+        :param int unk_id: Unknown word index.
+        :param str eos_symbol: End-of-sentence symbol.
+        :param bool online: Whether apply online learning after accepting each hypothesis.
+        :param int verbose: Verbosity level.
+        """
+
         self.models = models
         self.dataset = dataset
         self.params = params
@@ -165,7 +187,7 @@ def __init__(self, models, dataset, params, params_prediction, params_training,
                                                                       excluded_words=self.excluded_words,
                                                                       verbose=self.verbose)
 
-        # Compile Theano sampling function by generating a fake sample # TODO: Find a better way of doing this
+        # Compile Theano sampling function by generating a fake sample. # TODO: Find a better way of doing this
         logger.info('Compiling sampler...')
         self.generate_sample('i')
         logger.info('Done.')
@@ -186,7 +208,18 @@ def __init__(self, models, dataset, params, params_prediction, params_training,
 
     def generate_sample(self, source_sentence, validated_prefix=None, max_N=5, isle_indices=None,
                         filtered_idx2word=None, unk_indices=None, unk_words=None):
-        print ("In params prediction beam_size: ", self.params_prediction['beam_size'])
+        """
+        Generate sample via constrained search. Options labeled with <<isles>> are untested
+        and likely require some modifications to correctly work.
+        :param source_sentence: Source sentence.
+        :param validated_prefix: Prefix to keep in the output.
+        :param max_N: Maximum number of words to generate between validated segments. <<isles>>
+        :param isle_indices: Indices of the validated segments. <<isles>>
+        :param filtered_idx2word: List of candidate words to be the next one to generate (after generating fixed_words).
+        :param unk_indices: Positions of the unknown words.
+        :param unk_words: Unknown words.
+        :return:
+        """
         logger.log(2, 'Beam size: %d' % (self.params_prediction['beam_size']))
         generate_sample_start_time = time.time()
         if unk_indices is None:
@@ -295,10 +328,6 @@ def generate_sample(self, source_sentence, validated_prefix=None, max_N=5, isle_
         decoding_predictions_end_time = time.time()
         logger.log(2, 'decoding_predictions time: %.6f' % (decoding_predictions_end_time - decoding_predictions_start_time))
 
-        # for (words_idx, starting_pos), words in unk_in_isles:
-        #     for pos_unk_word, pos_hypothesis in enumerate(range(starting_pos, starting_pos + len(words_idx))):
-        #         hypothesis[pos_hypothesis] = words[pos_unk_word]
-
         # UNK words management
         unk_management_start_time = time.time()
         unk_indices = list(unk_words_dict)
@@ -330,7 +359,12 @@ def generate_sample(self, source_sentence, validated_prefix=None, max_N=5, isle_
         return hypothesis
 
     def learn_from_sample(self, source_sentence, target_sentence):
-
+        """
+        Incrementally adapt the model with the validated sample.
+        :param source_sentence: Source sentence (x).
+        :param target_sentence: Target sentence (y).
+        :return:
+        """
         # Tokenize input
         tokenized_input = self.general_tokenize_f(source_sentence, escape=False)
         tokenized_input = self.model_tokenize_f(tokenized_input)
@@ -499,7 +533,6 @@ def main():
                            for i in range(len(args.models))]
         models = [updateModel(model, path, -1, full_path=True) for (model, path) in zip(model_instances, args.models)]
 
-        # Set additional inputs to models if using a custom loss function
         # parameters['USE_CUSTOM_LOSS'] = True if 'PAS' in parameters['OPTIMIZER'] else False
         # if parameters.get('N_BEST_OPTIMIZER', False):
         #     logger.info('Using N-best optimizer')

demo-web/sample_server.py

@@ -11,6 +11,13 @@ for obtaining the required packages for running this library.
 
 Nevertheless, it is highly recommended to install and configure Theano_ or Tensorflow_ with the GPU and speed optimizations enabled.
 
+Alternatively, you can run the `install.sh`_ script, which will also downloads Python::
+
+    git clone https://github.com/lvapeab/nmt-keras
+    cd nmt-keras
+    bash ./install.sh
+
+
 Requirements
 ************
  - Our version of Keras_.
@@ -24,4 +31,5 @@ Requirements
 .. _Coco-caption: https://github.com/lvapeab/coco-caption
 .. _pip: https://en.wikipedia.org/wiki/Pip_(package_manager)
 .. _Theano: http://theano.readthedocs.io/en/latest/install.html#install
-.. _Tensorflow: https://www.tensorflow.org/install/
+.. _Tensorflow: https://www.tensorflow.org/install/
+.. _install.sh: https://github.com/lvapeab/nmt-keras/blob/master/install.sh

docs/source/requirements.rst

@@ -25,7 +25,15 @@ def parse_args():
 
 
 def weighted_average(args):
-
+    """
+    Apply a weighted average to the models.
+    :param args: Options for the averaging function:
+              * models: Path to the models.
+              * dest: Path to the averaged model. If unspecified, the model is saved in './model'
+              * weights: Weight given to each model in the averaging. Should be the same number of weights than models.
+                         If unspecified, it applies the same weight to each model (1/N).
+    :return:
+    """
     logger.info("Averaging %d models" % len(args.models))
     average_models(args.models, args.dest, weights=args.weights)
     logger.info('Averaging finished.')