Python data_utils.safe_exp() Examples

The following are 10 code examples of data_utils.safe_exp(). 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_gpu_trainer.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #2
Source File: neural_gpu_trainer.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #3
Source File: neural_gpu_trainer.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #4
Source File: neural_gpu_trainer.py    From hands-detection with MIT License 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #5
Source File: neural_gpu_trainer.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #6
Source File: neural_gpu_trainer.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #7
Source File: neural_gpu_trainer.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #8
Source File: neural_gpu_trainer.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #9
Source File: neural_gpu_trainer.py    From models with Apache License 2.0 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)
Example #10
Source File: neural_gpu_trainer.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def single_test(bin_id, model, sess, nprint, batch_size, dev, p, print_out=True,
                offset=None, beam_model=None):
  """Test model on test data of length l using the given session."""
  if not dev[p][bin_id]:
    data.print_out("  bin %d (%d)\t%s\tppl NA errors NA seq-errors NA"
                   % (bin_id, data.bins[bin_id], p))
    return 1.0, 1.0, 0.0
  inpt, target = data.get_batch(
      bin_id, batch_size, dev[p], FLAGS.height, offset)
  if FLAGS.beam_size > 1 and beam_model:
    loss, res, new_tgt, scores = m_step(
        model, beam_model, sess, batch_size, inpt, target, bin_id,
        FLAGS.eval_beam_steps, p)
    score_avgs = [sum(s) / float(len(s)) for s in scores]
    score_maxs = [max(s) for s in scores]
    score_str = ["(%.2f, %.2f)" % (score_avgs[i], score_maxs[i])
                 for i in xrange(FLAGS.eval_beam_steps)]
    data.print_out("  == scores (avg, max): %s" % "; ".join(score_str))
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint, new_tgt, scores[-1])
  else:
    loss, res, _, _ = model.step(sess, inpt, target, False)
    errors, total, seq_err = data.accuracy(inpt, res, target, batch_size,
                                           nprint)
  seq_err = float(seq_err) / batch_size
  if total > 0:
    errors = float(errors) / total
  if print_out:
    data.print_out("  bin %d (%d)\t%s\tppl %.2f errors %.2f seq-errors %.2f"
                   % (bin_id, data.bins[bin_id], p, data.safe_exp(loss),
                      100 * errors, 100 * seq_err))
  return (errors, seq_err, loss)