Python v1.InteractiveSession方法代码示例

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def _load_frozen_graph(self, frozen_graph_path):
    frozen_graph = tf.GraphDef()
    with open(frozen_graph_path, 'rb') as f:
      frozen_graph.ParseFromString(f.read())

    self.graph = tf.Graph()
    with self.graph.as_default():
      self.output_node = tf.import_graph_def(
          frozen_graph, return_elements=[
              'probabilities:0',
          ])
    self.session = tf.InteractiveSession(graph=self.graph)

    tf_probabilities = self.graph.get_tensor_by_name('import/probabilities:0')
    self._output_nodes = [tf_probabilities]
    self.sliding_window = None
    self.frames_since_last_inference = self.config.inference_rate
    self.last_annotations = [] 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def _load_frozen_graph(self, frozen_graph_path):
    trt_graph = tf.GraphDef()
    with open(frozen_graph_path, 'rb') as f:
      trt_graph.ParseFromString(f.read())

    self._is_lstm = self._check_lstm(trt_graph)
    if self._is_lstm:
      print('Loading an LSTM model.')

    self.graph = tf.Graph()
    with self.graph.as_default():
      self.output_node = tf.import_graph_def(
          trt_graph,
          return_elements=[
              'detection_boxes:0', 'detection_classes:0', 'detection_scores:0',
              'num_detections:0'
          ] + (['raw_outputs/lstm_c:0', 'raw_outputs/lstm_h:0']
               if self._is_lstm else []))
    self.session = tf.InteractiveSession(graph=self.graph)

    tf_scores = self.graph.get_tensor_by_name('import/detection_scores:0')
    tf_boxes = self.graph.get_tensor_by_name('import/detection_boxes:0')
    tf_classes = self.graph.get_tensor_by_name('import/detection_classes:0')
    tf_num_detections = self.graph.get_tensor_by_name('import/num_detections:0')
    if self._is_lstm:
      tf_lstm_c = self.graph.get_tensor_by_name('import/raw_outputs/lstm_c:0')
      tf_lstm_h = self.graph.get_tensor_by_name('import/raw_outputs/lstm_h:0')

    self._output_nodes = [tf_scores, tf_boxes, tf_classes, tf_num_detections
                         ] + ([tf_lstm_c, tf_lstm_h] if self._is_lstm else [])

    if self._is_lstm:
      self.lstm_c = np.ones((1, 8, 8, 320))
      self.lstm_h = np.ones((1, 8, 8, 320)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def trainer(model_params):
  """Train a sketch-rnn model."""
  np.set_printoptions(precision=8, edgeitems=6, linewidth=200, suppress=True)

  tf.logging.info('sketch-rnn')
  tf.logging.info('Hyperparams:')
  tf.logging.info('Loading data files.')
  datasets = load_dataset(FLAGS.data_dir, model_params)

  train_set = datasets[0]
  valid_set = datasets[1]
  test_set = datasets[2]
  model_params = datasets[3]
  eval_model_params = datasets[4]

  reset_graph()
  model = sketch_rnn_model.Model(model_params)
  eval_model = sketch_rnn_model.Model(eval_model_params, reuse=True)

  sess = tf.InteractiveSession()
  sess.run(tf.global_variables_initializer())

  if FLAGS.resume_training:
    load_checkpoint(sess, FLAGS.log_root)

  # Write config file to json file.
  tf.gfile.MakeDirs(FLAGS.log_root)
  with tf.gfile.Open(
      os.path.join(FLAGS.log_root, 'model_config.json'), 'w') as f:
    json.dump(list(model_params.values()), f, indent=True)

  train(sess, model, eval_model, train_set, valid_set, test_set) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def make_session(config=None, num_cpu=None, make_default=False, graph=None):
    """Returns a session that will use <num_cpu> CPU's only"""
    if num_cpu is None:
        num_cpu = int(os.getenv('RCALL_NUM_CPU', multiprocessing.cpu_count()))
    if config is None:
        config = tf.ConfigProto(
            allow_soft_placement=True,
            inter_op_parallelism_threads=num_cpu,
            intra_op_parallelism_threads=num_cpu)
        config.gpu_options.allow_growth = True

    if make_default:
        return tf.InteractiveSession(config=config, graph=graph)
    else:
        return tf.Session(config=config, graph=graph) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def _fit(self, X, weights, log_coincidence,
             vocab=None,
             initial_embedding_dict=None,
             fixed_initialization=None):
        if fixed_initialization is not None:
            raise AttributeError("Tensorflow version of Mittens does "
                                 "not support specifying initializations.")

        # Start the session:
        tf.reset_default_graph()
        self.sess = tf.InteractiveSession()

        # Build the computation graph.
        self._build_graph(vocab, initial_embedding_dict)

        # Optimizer set-up:
        self.cost = self._get_cost_function()
        self.optimizer = self._get_optimizer()

        # Set up logging for Tensorboard
        if self.log_dir:
            n_subdirs = len(os.listdir(self.log_dir))
            subdir = self.log_subdir or str(n_subdirs + 1)
            directory = os.path.join(self.log_dir, subdir)
            log_writer = tf.summary.FileWriter(directory, flush_secs=1)

        # Run training
        self.sess.run(tf.global_variables_initializer())
        if self.test_mode:
            self.W_start = self.sess.run(self.W)
            self.C_start = self.sess.run(self.C)
            self.bw_start = self.sess.run(self.bw)
            self.bc_start = self.sess.run(self.bc)

        merged_logs = tf.summary.merge_all()
        for i in range(1, self.max_iter+1):
            _, loss, stats = self.sess.run(
                [self.optimizer, self.cost, merged_logs],
                feed_dict={
                    self.weights: weights,
                    self.log_coincidence: log_coincidence})

            # Keep track of losses
            if self.log_dir and i % 10 == 0:
                log_writer.add_summary(stats)
            self.errors.append(loss)

            if loss < self.tol:
                # Quit early if tolerance is met
                self._progressbar("stopping with loss < self.tol", i)
                break
            else:
                self._progressbar("loss: {}".format(loss), i)

        # Return the sum of the two learned matrices, as recommended
        # in the paper:
        return self.sess.run(tf.add(self.W, self.C)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def test(sess, network, acc, X_test, y_test, x, y_, batch_size, cost=None):
    """
    Test a given non time-series network by the given test data and metric.

    Parameters
    ----------
    sess : TensorFlow session
        sess = tf.InteractiveSession()
    network : a TensorLayer layer
        the network will be trained
    acc : the TensorFlow expression of accuracy (or other metric) or None
        if None, would not display the metric
    X_test : numpy array
        the input of test data
    y_test : numpy array
        the target of test data
    x : placeholder
        for inputs
    y_ : placeholder
        for targets
    batch_size : int or None
        batch size for testing, when dataset is large, we should use minibatche for testing.
        when dataset is small, we can set it to None.
    cost : the TensorFlow expression of cost or None
        if None, would not display the cost

    Examples
    --------
    >>> see tutorial_mnist_simple.py
    >>> tl.utils.test(sess, network, acc, X_test, y_test, x, y_, batch_size=None, cost=cost)
    """
    print('Start testing the network ...')
    if batch_size is None:
        dp_dict = dict_to_one( network.all_drop )
        feed_dict = {x: X_test, y_: y_test}
        feed_dict.update(dp_dict)
        if cost is not None:
            print("   test loss: %f" % sess.run(cost, feed_dict=feed_dict))
        print("   test acc: %f" % sess.run(acc, feed_dict=feed_dict))
            # print("   test acc: %f" % np.mean(y_test == sess.run(y_op,
            #                                           feed_dict=feed_dict)))
    else:
        test_loss, test_acc, n_batch = 0, 0, 0
        for X_test_a, y_test_a in iterate.minibatches(
                                    X_test, y_test, batch_size, shuffle=True):
            dp_dict = dict_to_one( network.all_drop )    # disable noise layers
            feed_dict = {x: X_test_a, y_: y_test_a}
            feed_dict.update(dp_dict)
            if cost is not None:
                err, ac = sess.run([cost, acc], feed_dict=feed_dict)
                test_loss += err
            else:
                ac = sess.run(acc, feed_dict=feed_dict)
            test_acc += ac; n_batch += 1
        if cost is not None:
            print("   test loss: %f" % (test_loss/ n_batch))
        print("   test acc: %f" % (test_acc/ n_batch)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import InteractiveSession [as 别名]
def predict(sess, network, X, x, y_op, batch_size=None):
    """
    Return the predict results of given non time-series network.

    Parameters
    ----------
    sess : TensorFlow session
        sess = tf.InteractiveSession()
    network : a TensorLayer layer
        the network will be trained
    X : numpy array
        the input
    x : placeholder
        for inputs
    y_op : placeholder
        the argmax expression of softmax outputs
    batch_size : int or None
        batch size for prediction, when dataset is large, we should use minibatche for prediction.
        when dataset is small, we can set it to None.

    Examples
    --------
    >>> see tutorial_mnist_simple.py
    >>> y = network.outputs
    >>> y_op = tf.argmax(tf.nn.softmax(y), 1)
    >>> print(tl.utils.predict(sess, network, X_test, x, y_op))
    """
    if batch_size is None:
        dp_dict = dict_to_one( network.all_drop )    # disable noise layers
        feed_dict = {x: X,}
        feed_dict.update(dp_dict)
        return sess.run(y_op, feed_dict=feed_dict)
    else:
        result = None
        for X_a, _ in iterate.minibatches(
                X, X, batch_size, shuffle=False):
            dp_dict = dict_to_one( network.all_drop )
            feed_dict = {x: X_a, }
            feed_dict.update(dp_dict)
            result_a = sess.run(y_op, feed_dict=feed_dict)
            if result is None:
                result = result_a
            else:
                result = np.hstack((result, result_a))
        return result


## Evaluation