Python data_utils.LM1BDataset() Examples

The following are 24 code examples of data_utils.LM1BDataset(). 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: lm_1b_eval.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #2
Source File: lm_1b_eval.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #3
Source File: lm_1b_eval.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #4
Source File: lm_1b_eval.py    From models with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #5
Source File: lm_1b_eval.py    From models with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #6
Source File: lm_1b_eval.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #7
Source File: lm_1b_eval.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #8
Source File: lm_1b_eval.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #9
Source File: lm_1b_eval.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #10
Source File: lm_1b_eval.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #11
Source File: lm_1b_eval.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #12
Source File: lm_1b_eval.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #13
Source File: lm_1b_eval.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #14
Source File: lm_1b_eval.py    From hands-detection with MIT License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #15
Source File: lm_1b_eval.py    From hands-detection with MIT License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #16
Source File: lm_1b_eval.py    From ECO-pytorch with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #17
Source File: lm_1b_eval.py    From ECO-pytorch with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #18
Source File: lm_1b_eval.py    From Action_Recognition_Zoo with MIT License 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #19
Source File: lm_1b_eval.py    From Action_Recognition_Zoo with MIT License 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #20
Source File: lm_1b_eval.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #21
Source File: lm_1b_eval.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #22
Source File: lm_1b_eval.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')
Example #23
Source File: lm_1b_eval.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def _EvalModel(dataset):
  """Evaluate model perplexity using provided dataset.

  Args:
    dataset: LM1BDataset object.
  """
  sess, t = _LoadModel(FLAGS.pbtxt, FLAGS.ckpt)

  current_step = t['global_step'].eval(session=sess)
  sys.stderr.write('Loaded step %d.\n' % current_step)

  data_gen = dataset.get_batch(BATCH_SIZE, NUM_TIMESTEPS, forever=False)
  sum_num = 0.0
  sum_den = 0.0
  perplexity = 0.0
  for i, (inputs, char_inputs, _, targets, weights) in enumerate(data_gen):
    input_dict = {t['inputs_in']: inputs,
                  t['targets_in']: targets,
                  t['target_weights_in']: weights}
    if 'char_inputs_in' in t:
      input_dict[t['char_inputs_in']] = char_inputs
    log_perp = sess.run(t['log_perplexity_out'], feed_dict=input_dict)

    if np.isnan(log_perp):
      sys.stderr.error('log_perplexity is Nan.\n')
    else:
      sum_num += log_perp * weights.mean()
      sum_den += weights.mean()
    if sum_den > 0:
      perplexity = np.exp(sum_num / sum_den)

    sys.stderr.write('Eval Step: %d, Average Perplexity: %f.\n' %
                     (i, perplexity))

    if i > FLAGS.max_eval_steps:
      break
Example #24
Source File: lm_1b_eval.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  vocab = data_utils.CharsVocabulary(FLAGS.vocab_file, MAX_WORD_LEN)

  if FLAGS.mode == 'eval':
    dataset = data_utils.LM1BDataset(FLAGS.input_data, vocab)
    _EvalModel(dataset)
  elif FLAGS.mode == 'sample':
    _SampleModel(FLAGS.prefix, vocab)
  elif FLAGS.mode == 'dump_emb':
    _DumpEmb(vocab)
  elif FLAGS.mode == 'dump_lstm_emb':
    _DumpSentenceEmbedding(FLAGS.sentence, vocab)
  else:
    raise Exception('Mode not supported.')