Python data_utils.add_special_words() Examples

The following are 12 code examples of data_utils.add_special_words(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module data_utils , or try the search function .
Example #1
Source File: neural_programmer.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #2
Source File: neural_programmer.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #3
Source File: neural_programmer.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print("# train examples ", len(train_data))
  print("# dev examples ", len(dev_data))
  print("# test examples ", len(test_data))
  print("running open source")
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #4
Source File: neural_programmer.py    From Action_Recognition_Zoo with MIT License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #5
Source File: neural_programmer.py    From ECO-pytorch with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #6
Source File: neural_programmer.py    From hands-detection with MIT License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #7
Source File: neural_programmer.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #8
Source File: neural_programmer.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #9
Source File: neural_programmer.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print "# train examples ", len(train_data)
  print "# dev examples ", len(dev_data)
  print "# test examples ", len(test_data)
  print "running open source"
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #10
Source File: neural_programmer.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print("# train examples ", len(train_data))
  print("# dev examples ", len(dev_data))
  print("# test examples ", len(test_data))
  print("running open source")
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #11
Source File: neural_programmer.py    From models with Apache License 2.0 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print("# train examples ", len(train_data))
  print("# dev examples ", len(dev_data))
  print("# test examples ", len(test_data))
  print("running open source")
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)
Example #12
Source File: neural_programmer.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def main(args):
  utility = Utility()
  train_name = "random-split-1-train.examples"
  dev_name = "random-split-1-dev.examples"
  test_name = "pristine-unseen-tables.examples"
  #load data
  dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
  train_data, dev_data, test_data = dat.load()
  utility.words = []
  utility.word_ids = {}
  utility.reverse_word_ids = {}
  #construct vocabulary
  data_utils.construct_vocab(train_data, utility)
  data_utils.construct_vocab(dev_data, utility, True)
  data_utils.construct_vocab(test_data, utility, True)
  data_utils.add_special_words(utility)
  data_utils.perform_word_cutoff(utility)
  #convert data to int format and pad the inputs
  train_data = data_utils.complete_wiki_processing(train_data, utility, True)
  dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
  test_data = data_utils.complete_wiki_processing(test_data, utility, False)
  print("# train examples ", len(train_data))
  print("# dev examples ", len(dev_data))
  print("# test examples ", len(test_data))
  print("running open source")
  #construct TF graph and train or evaluate
  master(train_data, dev_data, utility)