Python tensorflow.compat.v1.variables_initializer() Examples
The following are 11
code examples of tensorflow.compat.v1.variables_initializer().
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
tensorflow.compat.v1
, or try the search function
.
Example #1
Source File: model_tf1.py From machine-learning-for-programming-samples with MIT License | 6 votes |
def build(self, input_shape): with self._sess.graph.as_default(): self._placeholders["tokens"] = tf.placeholder( dtype=tf.int32, shape=[None, None], name="tokens" ) self._ops["output_logits"] = self.compute_logits( self._placeholders["tokens"] ) self._ops["output_probs"] = tf.nn.softmax(self._ops["output_logits"], -1) result = self.compute_loss_and_acc( rnn_output_logits=self._ops["output_logits"], target_token_seq=self._placeholders["tokens"], ) self._ops["loss"] = result.token_ce_loss self._ops["num_tokens"] = result.num_predictions self._ops["num_correct_tokens"] = result.num_correct_token_predictions self._ops["train_step"] = self._make_training_step(self._ops["loss"]) init_op = tf.variables_initializer( self._sess.graph.get_collection(tf.GraphKeys.GLOBAL_VARIABLES) ) self._sess.run(init_op)
Example #2
Source File: batch_norm_source_op_handler_test.py From morph-net with Apache License 2.0 | 6 votes |
def testCreateRegularizer_Sliced(self): # Call handler to create regularizer. handler = batch_norm_source_op_handler.BatchNormSourceOpHandler( _GAMMA_THRESHOLD) batch_norm_op_slice = orm.OpSlice(self.batch_norm_op, orm.Slice(0, 3)) regularizer = handler.create_regularizer(batch_norm_op_slice) # Verify regularizer is the gamma tensor. with self.cached_session(): # Initialize the gamma tensor to check value equality. with tf.variable_scope('', reuse=tf.AUTO_REUSE): gamma_tensor = tf.get_variable('conv1/BatchNorm/gamma') init = tf.variables_initializer([gamma_tensor]) init.run() # Verify regularizer is the sliced gamma tensor. self.assertAllEqual(gamma_tensor.eval()[0:3], regularizer._gamma.eval())
Example #3
Source File: calibration_metrics_tf1_test.py From models with Apache License 2.0 | 6 votes |
def test_expected_calibration_error_all_bins_filled(self): """Test expected calibration error when all bins contain predictions.""" y_true, y_pred = self._get_calibration_placeholders() expected_ece_op, update_op = calibration_metrics.expected_calibration_error( y_true, y_pred, nbins=2) with self.test_session() as sess: metrics_vars = tf.get_collection(tf.GraphKeys.METRIC_VARIABLES) sess.run(tf.variables_initializer(var_list=metrics_vars)) # Bin calibration errors (|confidence - accuracy| * bin_weight): # - [0,0.5): |0.2 - 0.333| * (3/5) = 0.08 # - [0.5, 1]: |0.75 - 0.5| * (2/5) = 0.1 sess.run( update_op, feed_dict={ y_pred: np.array([0., 0.2, 0.4, 0.5, 1.0]), y_true: np.array([0, 0, 1, 0, 1]) }) actual_ece = 0.08 + 0.1 expected_ece = sess.run(expected_ece_op) self.assertAlmostEqual(actual_ece, expected_ece)
Example #4
Source File: calibration_metrics_tf1_test.py From models with Apache License 2.0 | 6 votes |
def test_expected_calibration_error_all_bins_not_filled(self): """Test expected calibration error when no predictions for one bin.""" y_true, y_pred = self._get_calibration_placeholders() expected_ece_op, update_op = calibration_metrics.expected_calibration_error( y_true, y_pred, nbins=2) with self.test_session() as sess: metrics_vars = tf.get_collection(tf.GraphKeys.METRIC_VARIABLES) sess.run(tf.variables_initializer(var_list=metrics_vars)) # Bin calibration errors (|confidence - accuracy| * bin_weight): # - [0,0.5): |0.2 - 0.333| * (3/5) = 0.08 # - [0.5, 1]: |0.75 - 0.5| * (2/5) = 0.1 sess.run( update_op, feed_dict={ y_pred: np.array([0., 0.2, 0.4]), y_true: np.array([0, 0, 1]) }) actual_ece = np.abs(0.2 - (1 / 3.)) expected_ece = sess.run(expected_ece_op) self.assertAlmostEqual(actual_ece, expected_ece)
Example #5
Source File: cnn_util_test.py From benchmarks with Apache License 2.0 | 5 votes |
def _test_image_producer(self, batch_group_size, put_slower_than_get): # We use the variable x to simulate a staging area of images. x represents # the number of batches in the staging area. x = tf.Variable(0, dtype=tf.int32) if put_slower_than_get: put_dep = self._slow_tensorflow_op() get_dep = tf.no_op() else: put_dep = tf.no_op() get_dep = self._slow_tensorflow_op() with tf.control_dependencies([put_dep]): put_op = x.assign_add(batch_group_size, use_locking=True) with tf.control_dependencies([get_dep]): get_op = x.assign_sub(1, use_locking=True) with self.test_session() as sess: sess.run(tf.variables_initializer([x])) image_producer = cnn_util.ImageProducer(sess, put_op, batch_group_size, use_python32_barrier=False) image_producer.start() for _ in range(5 * batch_group_size): sess.run(get_op) # We assert x is nonnegative, to ensure image_producer never causes # an unstage op to block. We assert x is at most 2 * batch_group_size, # to ensure it doesn't use too much memory by storing too many batches # in the staging area. self.assertGreaterEqual(sess.run(x), 0) self.assertLessEqual(sess.run(x), 2 * batch_group_size) image_producer.notify_image_consumption() self.assertGreaterEqual(sess.run(x), 0) self.assertLessEqual(sess.run(x), 2 * batch_group_size) image_producer.done() time.sleep(0.1) self.assertGreaterEqual(sess.run(x), 0) self.assertLessEqual(sess.run(x), 2 * batch_group_size)
Example #6
Source File: model_tf1.py From machine-learning-for-programming-samples with MIT License | 5 votes |
def restore(cls, saved_model_path: str) -> "LanguageModelTF1": with gzip.open(saved_model_path) as f: saved_data = pickle.load(f) model = cls(saved_data["hyperparameters"], saved_data["vocab"]) model.build((None, None)) variables_to_initialize = [] with model._sess.graph.as_default(): with tf.name_scope("restore"): restore_ops = [] used_vars = set() for variable in sorted( model._sess.graph.get_collection(tf.GraphKeys.GLOBAL_VARIABLES), key=lambda v: v.name, ): used_vars.add(variable.name) if variable.name in saved_data["weights"]: # print('Initializing %s from saved value.' % variable.name) restore_ops.append( variable.assign(saved_data["weights"][variable.name]) ) else: print( "Freshly initializing %s since no saved value was found." % variable.name ) variables_to_initialize.append(variable) for var_name in sorted(saved_data["weights"]): if var_name not in used_vars: if ( var_name.endswith("Adam:0") or var_name.endswith("Adam_1:0") or var_name in ["beta1_power:0", "beta2_power:0"] ): continue print("Saved weights for %s not used by model." % var_name) restore_ops.append(tf.variables_initializer(variables_to_initialize)) model._sess.run(restore_ops) return model
Example #7
Source File: depthwise_convolution_op_handler_test.py From morph-net with Apache License 2.0 | 5 votes |
def testDepthwiseChannelMapping(self): """Verify depth multiplier maps input to output as expected.""" tf.reset_default_graph() # Construct input tensor with shape [1, 4, 4, 5]. There are 5 channels # where each channel has values corresponding to the channel index. channel0 = tf.ones([1, 4, 4, 1]) * 0 channel1 = tf.ones([1, 4, 4, 1]) * 1 channel2 = tf.ones([1, 4, 4, 1]) * 2 channel3 = tf.ones([1, 4, 4, 1]) * 3 channel4 = tf.ones([1, 4, 4, 1]) * 4 inputs = tf.concat( [channel0, channel1, channel2, channel3, channel4], axis=3) # Sanity check that input tensor is the right shape. self.assertAllEqual([1, 4, 4, 5], inputs.shape.as_list()) conv = layers.separable_conv2d( inputs, num_outputs=None, kernel_size=3, depth_multiplier=2, weights_initializer=identity_initializer, scope='depthwise_conv') with self.cached_session(): with tf.variable_scope('', reuse=tf.AUTO_REUSE): weights = tf.get_variable('depthwise_conv/depthwise_weights') biases = tf.get_variable('depthwise_conv/biases', [10], initializer=tf.zeros_initializer) init = tf.variables_initializer([weights, biases]) init.run() # The depth_multiplier replicates channels with [a, a, b, b, c, c, ...] # pattern. Expected output has shape [1, 4, 4, 10]. expected_output = tf.concat( [channel0, channel0, channel1, channel1, channel2, channel2, channel3, channel3, channel4, channel4], axis=3) # Sanity check that output tensor is the right shape. self.assertAllEqual([1, 4, 4, 10], expected_output.shape.as_list()) self.assertAllEqual(expected_output.eval(), conv.eval())
Example #8
Source File: reconstruction.py From graphics with Apache License 2.0 | 5 votes |
def _initialize_uninitialized(self, sess): global_vars = tf.global_variables() is_not_initialized = sess.run( [tf.is_variable_initialized(var) for var in global_vars]) not_initialized_vars = [v for (v, f) in zip(global_vars, is_not_initialized) if not f] if not_initialized_vars: sess.run(tf.variables_initializer(not_initialized_vars))
Example #9
Source File: util.py From nni with MIT License | 5 votes |
def initialize(): """Initialize all the uninitialized variables in the global scope.""" new_variables = set(tf.global_variables()) - ALREADY_INITIALIZED get_session().run(tf.variables_initializer(new_variables)) ALREADY_INITIALIZED.update(new_variables)
Example #10
Source File: calibration_evaluation_tf1_test.py From models with Apache License 2.0 | 5 votes |
def _get_ece(self, ece_op, update_op): """Return scalar expected calibration error.""" with self.test_session() as sess: metrics_vars = tf.get_collection(tf.GraphKeys.METRIC_VARIABLES) sess.run(tf.variables_initializer(var_list=metrics_vars)) _ = sess.run(update_op) return sess.run(ece_op)
Example #11
Source File: calibration_metrics_tf1_test.py From models with Apache License 2.0 | 5 votes |
def test_expected_calibration_error_with_multiple_data_streams(self): """Test expected calibration error when multiple data batches provided.""" y_true, y_pred = self._get_calibration_placeholders() expected_ece_op, update_op = calibration_metrics.expected_calibration_error( y_true, y_pred, nbins=2) with self.test_session() as sess: metrics_vars = tf.get_collection(tf.GraphKeys.METRIC_VARIABLES) sess.run(tf.variables_initializer(var_list=metrics_vars)) # Identical data to test_expected_calibration_error_all_bins_filled, # except split over three batches. sess.run( update_op, feed_dict={ y_pred: np.array([0., 0.2]), y_true: np.array([0, 0]) }) sess.run( update_op, feed_dict={ y_pred: np.array([0.4, 0.5]), y_true: np.array([1, 0]) }) sess.run( update_op, feed_dict={ y_pred: np.array([1.0]), y_true: np.array([1]) }) actual_ece = 0.08 + 0.1 expected_ece = sess.run(expected_ece_op) self.assertAlmostEqual(actual_ece, expected_ece)