Python util.load_ckpt方法代码示例

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def restore_best_model(self):
    """Load bestmodel file from eval directory, add variables for adagrad, and save to train directory"""
    tf.logging.info("Restoring bestmodel for training...")

    # Initialize all vars in the model
    sess = tf.Session(config=util.get_config())
    print("Initializing all variables...")
    sess.run(tf.initialize_all_variables())

    # Restore the best model from eval dir
    saver = tf.train.Saver([v for v in tf.all_variables() if "Adagrad" not in v.name])
    print("Restoring all non-adagrad variables from best model in eval dir...")
    curr_ckpt = util.load_ckpt(saver, sess, "eval")
    print("Restored %s." % curr_ckpt)

    # Save this model to train dir and quit
    new_model_name = curr_ckpt.split("/")[-1].replace("bestmodel", "model")
    new_fname = os.path.join(FLAGS.log_root, "train", new_model_name)
    print("Saving model to %s..." % (new_fname))
    new_saver = tf.train.Saver() # this saver saves all variables that now exist, including Adagrad variables
    new_saver.save(sess, new_fname)
    print("Saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_coverage_model(self):
    """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
    tf.logging.info("converting non-coverage model to coverage model..")

    # initialize an entire coverage model from scratch
    sess = tf.Session(config=util.get_config())
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-coverage weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables() if "coverage" not in v.name and "Adagrad" not in v.name])
    print("restoring non-coverage variables...")
    curr_ckpt = util.load_ckpt(saver, sess)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt + '_cov_init'
    print("saving model to %s..." % (new_fname))
    new_saver = tf.train.Saver() # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_reinforce_model(self):
    """Load non-reinforce checkpoint, add initialized extra variables for reinforce, and save as new checkpoint"""
    tf.logging.info("converting non-reinforce model to reinforce model..")

    # initialize an entire reinforce model from scratch
    sess = tf.Session(config=util.get_config())
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-reinforce weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables() if "reinforce" not in v.name and "Adagrad" not in v.name])
    print("restoring non-reinforce variables...")
    curr_ckpt = util.load_ckpt(saver, sess)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt + '_rl_init'
    print("saving model to %s..." % (new_fname))
    new_saver = tf.train.Saver() # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def restore_best_model():
    """Load bestmodel file from eval directory, add variables for adagrad, and save to train directory"""
    tf.logging.info("Restoring best model for training...")

    # Initialize all vars in the model
    sess = tf.Session(config=util.get_config())
    print("Initializing all variables...")
    sess.run(tf.initialize_all_variables())

    # Restore the best model from eval dir
    saver = tf.train.Saver([v for v in tf.all_variables() if "Adagrad" not in v.name])
    print("Restoring all non-adagrad variables from best model in eval dir...")
    curr_ckpt = util.load_ckpt(saver, sess, "eval")
    print("Restored %s." % curr_ckpt)

    # Save this model to train dir and quit
    new_model_name = curr_ckpt.split("/")[-1].replace("bestmodel", "model")
    new_fname = os.path.join(FLAGS.log_root, "train", new_model_name)
    print("Saving model to %s..." % new_fname)
    new_saver = tf.train.Saver()  # this saver saves all variables that now exist, including Adagrad variables
    new_saver.save(sess, new_fname)
    print("Saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_coverage_model():
    """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
    tf.logging.info("converting non-coverage model to coverage model..")

    # initialize an entire coverage model from scratch
    sess = tf.Session(config=util.get_config())
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-coverage weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables() if "coverage" not in v.name and "Adagrad" not in v.name])
    print("restoring non-coverage variables...")
    curr_ckpt = util.load_ckpt(saver, sess, FLAGS.ckpt_dir)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt + '_cov_init'
    print("saving model to %s..." % new_fname)
    new_saver = tf.train.Saver()  # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_coverage_model():
    """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
    tf.logging.info("converting non-coverage model to coverage model..")

    # initialize an entire coverage model from scratch
    sess = tf.Session(config=util.get_config())
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-coverage weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables(
    ) if "coverage" not in v.name and "Adagrad" not in v.name])
    print("restoring non-coverage variables...")
    curr_ckpt = util.load_ckpt(saver, sess)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt + '_cov_init'
    print("saving model to %s..." % (new_fname))
    new_saver = tf.train.Saver()  # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def restore_best_model():
  """Load bestmodel file from eval directory, add variables for adagrad, and save to train directory"""
  tf.logging.info("Restoring bestmodel for training...")

  # Initialize all vars in the model
  sess = tf.Session(config=util.get_config())
  print("Initializing all variables...")
  sess.run(tf.initialize_all_variables())

  # Restore the best model from eval dir
  saver = tf.train.Saver([v for v in tf.all_variables() if "Adagrad" not in v.name])
  print("Restoring all non-adagrad variables from best model in eval dir...")
  curr_ckpt = util.load_ckpt(saver, sess, "eval")
  print("Restored %s." % curr_ckpt)

  # Save this model to train dir and quit
  new_model_name = curr_ckpt.split("/")[-1].replace("bestmodel", "model")
  new_fname = os.path.join(FLAGS.log_root, "train", new_model_name)
  print("Saving model to %s..." % (new_fname))
  new_saver = tf.train.Saver() # this saver saves all variables that now exist, including Adagrad variables
  new_saver.save(sess, new_fname)
  print("Saved.")
  exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_linear_attn_to_hier_model():
    """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
    tf.logging.info("converting linear model to hier model..")

    # initialize an entire coverage model from scratch
    sess = tf.Session(config=util.get_config())
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-coverage weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables(
    ) if "Linear--Section-Features" not in v.name and "v_sec" not in v.name and "Adagrad" not in v.name])
    print("restoring variables...")
    curr_ckpt = util.load_ckpt(saver, sess)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt
    print(("saving model to %s..." % (new_fname)))
    new_saver = tf.train.Saver()  # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def setup_training_generator(model):
  """Does setup before starting training (run_training)"""
  train_dir = os.path.join(FLAGS.log_root, "train-generator")
  if not os.path.exists(train_dir): os.makedirs(train_dir)

  model.build_graph() # build the graph

  saver = tf.train.Saver(max_to_keep=20)  # we use this to load checkpoints for decoding
  sess = tf.Session(config=util.get_config())
  #sess.run(tf.train.Saver(max_to_keep=20))
  #init = tf.global_variables_initializer()
  #sess.run(init)

  # Load an initial checkpoint to use for decoding
  util.load_ckpt(saver, sess, ckpt_dir="train-generator")


  return sess, saver,train_dir 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def setup_training_discriminator(model):
    """Does setup before starting training (run_training)"""
    train_dir = os.path.join(FLAGS.log_root, "train-discriminator")
    if not os.path.exists(train_dir): os.makedirs(train_dir)

    model.build_graph()  # build the graph

    saver = tf.train.Saver(max_to_keep=20)  # we use this to load checkpoints for decoding
    sess = tf.Session(config=util.get_config())
    #init = tf.global_variables_initializer()
    #sess.run(init)
    util.load_ckpt(saver, sess, ckpt_dir="train-discriminator")



    return sess, saver,train_dir 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def restore_best_model():
  """Load bestmodel file from eval directory, add variables for adagrad, and save to train directory"""
  tf.logging.info("Restoring bestmodel for training...")

  # Initialize all vars in the model
  sess = tf.Session(config=util.get_config())
  print "Initializing all variables..."
  sess.run(tf.initialize_all_variables())

  # Restore the best model from eval dir
  saver = tf.train.Saver([v for v in tf.all_variables() if "Adagrad" not in v.name])
  print "Restoring all non-adagrad variables from best model in eval dir..."
  curr_ckpt = util.load_ckpt(saver, sess, "eval")
  print "Restored %s." % curr_ckpt

  # Save this model to train dir and quit
  new_model_name = curr_ckpt.split("/")[-1].replace("bestmodel", "model")
  new_fname = os.path.join(FLAGS.log_root, "train", new_model_name)
  print "Saving model to %s..." % (new_fname)
  new_saver = tf.train.Saver() # this saver saves all variables that now exist, including Adagrad variables
  new_saver.save(sess, new_fname)
  print "Saved."
  exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_coverage_model():
  """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
  tf.logging.info("converting non-coverage model to coverage model..")

  # initialize an entire coverage model from scratch
  sess = tf.Session(config=util.get_config())
  print "initializing everything..."
  sess.run(tf.global_variables_initializer())

  # load all non-coverage weights from checkpoint
  saver = tf.train.Saver([v for v in tf.global_variables() if "coverage" not in v.name and "Adagrad" not in v.name])
  print "restoring non-coverage variables..."
  curr_ckpt = util.load_ckpt(saver, sess)
  print "restored."

  # save this model and quit
  new_fname = curr_ckpt + '_cov_init'
  print "saving model to %s..." % (new_fname)
  new_saver = tf.train.Saver() # this one will save all variables that now exist
  new_saver.save(sess, new_fname)
  print "saved."
  exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def __init__(self, model, batcher, vocab):
    """Initialize decoder.

    Args:
      model: a Seq2SeqAttentionModel object.
      batcher: a Batcher object.
      vocab: Vocabulary object
    """
    self._model = model
    self._model.build_graph()
    self._batcher = batcher
    self._vocab = vocab
    self._saver = tf.train.Saver() # we use this to load checkpoints for decoding
    self._sess = tf.Session(config=util.get_config())

    # Load an initial checkpoint to use for decoding
    ckpt_path = util.load_ckpt(self._saver, self._sess)


    # if FLAGS.single_pass:
    #   # Make a descriptive decode directory name
    #   ckpt_name = "ckpt-" + ckpt_path.split('-')[-1] # this is something of the form "ckpt-123456"
    #   self._decode_dir = os.path.join(FLAGS.log_root, get_decode_dir_name(ckpt_name))
    #   if os.path.exists(self._decode_dir):
    #     raise Exception("single_pass decode directory %s should not already exist" % self._decode_dir)
    #
    # else: # Generic decode dir name
    self._decode_dir = os.path.join(FLAGS.log_root, "decode")

    # Make the decode dir if necessary
    if not os.path.exists(self._decode_dir): os.mkdir(self._decode_dir)

    # if FLAGS.single_pass:
    #   # Make the dirs to contain output written in the correct format for pyrouge
    #   self._rouge_ref_dir = os.path.join(self._decode_dir, "reference")
    #   if not os.path.exists(self._rouge_ref_dir): os.mkdir(self._rouge_ref_dir)
    #   self._rouge_dec_dir = os.path.join(self._decode_dir, "decoded")
    #   if not os.path.exists(self._rouge_dec_dir): os.mkdir(self._rouge_dec_dir) 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def restore_best_model():
    """Load bestmodel file from eval directory, add variables for adagrad, and save to train directory"""
    tf.logging.info("Restoring bestmodel for training...")

    # Initialize all vars in the model
    sess = tf.Session(config=util.get_config())
    print("Initializing all variables...")
    sess.run(tf.initialize_all_variables())

    # Restore the best model from eval dir
    saver = tf.train.Saver(
        [v for v in tf.all_variables() if "Adagrad" not in v.name])
    print("Restoring all non-adagrad variables from best model in eval dir...")
    curr_ckpt = util.load_ckpt(saver, sess, "eval")
    print("Restored %s." % curr_ckpt)

    # Save this model to train dir and quit
    new_model_name = curr_ckpt.split("/")[-1].replace("bestmodel", "model")
    new_fname = os.path.join(FLAGS.log_root, "train", new_model_name)
    print("Saving model to %s..." % (new_fname))
    # this saver saves all variables that now exist, including Adagrad
    # variables
    new_saver = tf.train.Saver()
    new_saver.save(sess, new_fname)
    print("Saved.")
    exit() 

# 需要导入模块: import util [as 别名]
# 或者: from util import load_ckpt [as 别名]
def convert_to_coverage_model():
    """Load non-coverage checkpoint, add initialized extra variables for coverage, and save as new checkpoint"""
    tf.logging.info("converting non-coverage model to coverage model..")

    # initialize an entire coverage model from scratch
    sess = tf.Session(config=util.get_config())
    if FLAGS.debug:
      print('entering debug mode')
      sess = tf_debug.LocalCLIDebugWrapperSession(sess, ui_type=FLAGS.ui_type)
      sess.add_tensor_filter("has_inf_or_nan", tf_debug.has_inf_or_nan)
    print("initializing everything...")
    sess.run(tf.global_variables_initializer())

    # load all non-coverage weights from checkpoint
    saver = tf.train.Saver([v for v in tf.global_variables(
    ) if "coverage" not in v.name and "Adagrad" not in v.name])
    print("restoring non-coverage variables...")
    curr_ckpt = util.load_ckpt(saver, sess)
    print("restored.")

    # save this model and quit
    new_fname = curr_ckpt + '_cov_init'
    print(("saving model to %s..." % (new_fname)))
    new_saver = tf.train.Saver()  # this one will save all variables that now exist
    new_saver.save(sess, new_fname)
    print("saved.")
    exit()