def main(unused_argv): if FLAGS.checkpoint is None or not FLAGS.checkpoint: raise ValueError( 'Need to provide a path to checkpoint directory.') wmodel = lib_graph.load_checkpoint(FLAGS.checkpoint) if FLAGS.eval_logdir is None: raise ValueError( 'Set flag eval_logdir to specify a path for saving eval statistics.') else: eval_logdir = os.path.join(FLAGS.eval_logdir, 'eval_stats') tf.gfile.MakeDirs(eval_logdir) evaluator = lib_evaluation.BaseEvaluator.make( FLAGS.unit, wmodel=wmodel, chronological=FLAGS.chronological) evaluator = lib_evaluation.EnsemblingEvaluator(evaluator, FLAGS.ensemble_size) if not FLAGS.sample_npy_path and FLAGS.fold is None: raise ValueError( 'Either --fold must be specified, or paths of npy files to load must ' 'be given, but not both.') if FLAGS.fold is not None: evaluate_fold(FLAGS.fold, evaluator, wmodel.hparams, eval_logdir) if FLAGS.sample_npy_path is not None: evaluate_paths([FLAGS.sample_npy_path], evaluator, wmodel.hparams, eval_logdir) print('Done')
def main(unused_argv): if FLAGS.checkpoint is None or not FLAGS.checkpoint: raise ValueError( 'Need to provide a path to checkpoint directory.') if FLAGS.destination is None or not FLAGS.destination: raise ValueError( 'Need to provide a destination directory for the SavedModel.') model = lib_graph.load_checkpoint(FLAGS.checkpoint) export_saved_model(model, FLAGS.destination) tf.logging.info('Exported SavedModel to %s.', FLAGS.destination)
def export(checkpoint, destination, use_tf_sampling): model = None if use_tf_sampling: model = lib_tfsampling.CoconetSampleGraph(checkpoint) model.instantiate_sess_and_restore_checkpoint() else: model = lib_graph.load_checkpoint(checkpoint) tf.logging.info('Loaded graph.') lib_saved_model.export_saved_model(model, destination, [tf.saved_model.tag_constants.SERVING], use_tf_sampling)
def main(unused_argv): if FLAGS.checkpoint is None or not FLAGS.checkpoint: raise ValueError('Need to provide a path to checkpoint directory.') if FLAGS.destination is None or not FLAGS.destination: raise ValueError( 'Need to provide a destination directory for the SavedModel.') model = None if FLAGS.use_tf_sampling: model = lib_tfsampling.CoconetSampleGraph(FLAGS.checkpoint) model.instantiate_sess_and_restore_checkpoint() else: model = lib_graph.load_checkpoint(FLAGS.checkpoint) tf.logging.info('Loaded graph.') lib_saved_model.export_saved_model(model, FLAGS.destination, [tf.saved_model.tag_constants.SERVING], FLAGS.use_tf_sampling) tf.logging.info('Exported SavedModel to %s.', FLAGS.destination)
def main(ckpt, evaldir, unit, chronological, ensemble_size, sample_path, folder, index, data_dir): checkpoint_dir = ckpt if not checkpoint_dir: # If a checkpoint directory is not specified, see if there is only one # subdir in this folder and use that. possible_checkpoint_dirs = tf.gfile.ListDirectory(evaldir) possible_checkpoint_dirs = [ i for i in possible_checkpoint_dirs if tf.gfile.IsDirectory(os.path.join(evaldir, i)) ] if EVAL_SUBDIR in possible_checkpoint_dirs: possible_checkpoint_dirs.remove(EVAL_SUBDIR) if len(possible_checkpoint_dirs) == 1: checkpoint_dir = os.path.join(evaldir, possible_checkpoint_dirs[0]) tf.logging.info('Using checkpoint dir: %s', checkpoint_dir) else: raise ValueError( 'Need to provide a path to checkpoint directory or use an ' 'eval_logdir with only 1 checkpoint subdirectory.') wmodel = lib_graph.load_checkpoint(checkpoint_dir) if evaldir is None: raise ValueError( 'Set flag eval_logdir to specify a path for saving eval statistics.' ) else: eval_logdir = os.path.join(evaldir, EVAL_SUBDIR) tf.gfile.MakeDirs(eval_logdir) evaluator = lib_evaluation.BaseEvaluator.make(unit, wmodel=wmodel, chronological=chronological) evaluator = lib_evaluation.EnsemblingEvaluator(evaluator, ensemble_size) if not sample_path and folder is None: raise ValueError( 'Either --fold must be specified, or paths of npy files to load must ' 'be given, but not both.') if folder is not None: evaluate_fold(folder, evaluator, wmodel.hparams, eval_logdir, checkpoint_dir, index, unit, ensemble_size, chronological, data_dir) if sample_path is not None: evaluate_paths([sample_path], evaluator, wmodel.hparams, eval_logdir, unit, ensemble_size, chronological) tf.logging.info('Done')
def main(unused_argv): checkpoint_dir = FLAGS.checkpoint if not checkpoint_dir: # If a checkpoint directory is not specified, see if there is only one # subdir in this folder and use that. possible_checkpoint_dirs = tf.gfile.ListDirectory(FLAGS.eval_logdir) possible_checkpoint_dirs = [ i for i in possible_checkpoint_dirs if tf.gfile.IsDirectory(os.path.join(FLAGS.eval_logdir, i))] if EVAL_SUBDIR in possible_checkpoint_dirs: possible_checkpoint_dirs.remove(EVAL_SUBDIR) if len(possible_checkpoint_dirs) == 1: checkpoint_dir = os.path.join( FLAGS.eval_logdir, possible_checkpoint_dirs[0]) tf.logging.info('Using checkpoint dir: %s', checkpoint_dir) else: raise ValueError( 'Need to provide a path to checkpoint directory or use an ' 'eval_logdir with only 1 checkpoint subdirectory.') wmodel = lib_graph.load_checkpoint(checkpoint_dir) if FLAGS.eval_logdir is None: raise ValueError( 'Set flag eval_logdir to specify a path for saving eval statistics.') else: eval_logdir = os.path.join(FLAGS.eval_logdir, EVAL_SUBDIR) tf.gfile.MakeDirs(eval_logdir) evaluator = lib_evaluation.BaseEvaluator.make( FLAGS.unit, wmodel=wmodel, chronological=FLAGS.chronological) evaluator = lib_evaluation.EnsemblingEvaluator(evaluator, FLAGS.ensemble_size) if not FLAGS.sample_npy_path and FLAGS.fold is None: raise ValueError( 'Either --fold must be specified, or paths of npy files to load must ' 'be given, but not both.') if FLAGS.fold is not None: evaluate_fold( FLAGS.fold, evaluator, wmodel.hparams, eval_logdir, checkpoint_dir) if FLAGS.sample_npy_path is not None: evaluate_paths([FLAGS.sample_npy_path], evaluator, wmodel.hparams, eval_logdir) tf.logging.info('Done')
def instantiate_model(checkpoint, instantiate_sess=True): wmodel = lib_graph.load_checkpoint( checkpoint, instantiate_sess=instantiate_sess) return wmodel
def instantiate_model(checkpoint, instantiate_sess=True): wmodel = lib_graph.load_checkpoint(checkpoint, instantiate_sess=instantiate_sess) return wmodel
def instantiate_model(checkpoint): wmodel = lib_graph.load_checkpoint(checkpoint) return wmodel