Python tensorflow.python.ops.variables.global_variables_initializer() Examples
The following are 30
code examples of tensorflow.python.ops.variables.global_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.python.ops.variables
, or try the search function
.
Example #1
Source File: resnet_v1_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testUnknownBatchSize(self): batch = 2 height, width = 65, 65 global_pool = True num_classes = 10 inputs = create_test_input(None, height, width, 3) with arg_scope(resnet_utils.resnet_arg_scope()): logits, _ = self._resnet_small( inputs, num_classes, global_pool, scope='resnet') self.assertTrue(logits.op.name.startswith('resnet/logits')) self.assertListEqual(logits.get_shape().as_list(), [None, 1, 1, num_classes]) images = create_test_input(batch, height, width, 3) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(logits, {inputs: images.eval()}) self.assertEqual(output.shape, (batch, 1, 1, num_classes))
Example #2
Source File: sample_inputs_op_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testWeights(self): with self.test_session(): variables.global_variables_initializer().run() (indices, feature_updates, threshold_updates) = (tensor_forest_ops.sample_inputs( self.input_data, [], [], [], [0.5, 0.1, 0.8, 0.7], self.node_map, self.leaves, self.split_features, self.split_thresholds, input_spec=self.data_spec, split_initializations_per_input=1, split_sampling_random_seed=3)) self.assertAllEqual([1, 0], indices.eval()) self.assertAllEqual([[1, 0, 0], [-1, -1, -1]], feature_updates.eval()) self.assertAllEqual([[5., -2., 20.], [0., 0., 0.]], threshold_updates.eval())
Example #3
Source File: sample_inputs_op_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testBadInput(self): del self.split_features[1] with self.test_session(): variables.global_variables_initializer().run() with self.assertRaisesOpError( 'split_features and split_thresholds should be the same shape.'): indices, _, _ = tensor_forest_ops.sample_inputs( self.input_data, [], [], [], [], self.node_map, self.leaves, self.split_features, self.split_thresholds, input_spec=self.data_spec, split_initializations_per_input=1, split_sampling_random_seed=3) self.assertAllEqual([], indices.eval())
Example #4
Source File: sample_inputs_op_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testSimple(self): with self.test_session(): variables.global_variables_initializer().run() (indices, feature_updates, threshold_updates) = (tensor_forest_ops.sample_inputs( self.input_data, [], [], [], [], self.node_map, self.leaves, self.split_features, self.split_thresholds, split_initializations_per_input=1, input_spec=self.data_spec, split_sampling_random_seed=2)) self.assertAllEqual([1, 0], indices.eval()) self.assertAllEqual([[1, 0, 1], [1, 1, -1]], feature_updates.eval()) self.assertAllEqual([[5., -2., 50.], [10., 2., 0.]], threshold_updates.eval())
Example #5
Source File: main_op_impl.py From lambda-packs with MIT License | 6 votes |
def main_op(): """Returns a main op to init variables and tables. Returns the main op including the group of ops that initializes all variables, initializes local variables and initialize all tables. Returns: The set of ops to be run as part of the main op upon the load operation. """ init = variables.global_variables_initializer() init_local = variables.local_variables_initializer() init_tables = lookup_ops.tables_initializer() return control_flow_ops.group(init, init_local, init_tables) # TODO(sukritiramesh): Integrate with Saver for complete restore functionality.
Example #6
Source File: supervisor.py From lambda-packs with MIT License | 6 votes |
def _init_init_op(self, init_op=USE_DEFAULT, init_feed_dict=None): """Initializes init_op. Args: init_op: `Operation` to initialize the variables. If set to USE_DEFAULT, create an op that initializes all variables and tables. init_feed_dict: A dictionary that maps `Tensor` objects to feed values. This feed dictionary will be used when `init_op` is evaluated. """ if init_op is Supervisor.USE_DEFAULT: init_op = self._get_first_op_from_collection(ops.GraphKeys.INIT_OP) if init_op is None: init_op = variables.global_variables_initializer() ops.add_to_collection(ops.GraphKeys.INIT_OP, init_op) self._init_op = init_op self._init_feed_dict = init_feed_dict
Example #7
Source File: session_debug_testlib.py From lambda-packs with MIT License | 6 votes |
def testDebugCondWatchingWholeGraphWorks(self): with session.Session() as sess: x = variables.Variable(10.0, name="x") y = variables.Variable(20.0, name="y") cond = control_flow_ops.cond( x > y, lambda: math_ops.add(x, 1), lambda: math_ops.add(y, 1)) sess.run(variables.global_variables_initializer()) run_options = config_pb2.RunOptions(output_partition_graphs=True) debug_utils.watch_graph(run_options, sess.graph, debug_urls=self._debug_urls()) run_metadata = config_pb2.RunMetadata() self.assertEqual( 21, sess.run(cond, options=run_options, run_metadata=run_metadata)) dump = debug_data.DebugDumpDir( self._dump_root, partition_graphs=run_metadata.partition_graphs) self.assertAllClose( [21.0], dump.get_tensors("cond/Merge", 0, "DebugIdentity"))
Example #8
Source File: session_bundle_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def setUp(self): self.base_path = os.path.join(test.get_temp_dir(), "no_vars") if not os.path.exists(self.base_path): os.mkdir(self.base_path) # Create a simple graph with a variable, then convert variables to # constants and export the graph. with ops.Graph().as_default() as g: x = array_ops.placeholder(dtypes.float32, name="x") w = variables.Variable(3.0) y = math_ops.subtract(w * x, 7.0, name="y") # pylint: disable=unused-variable ops.add_to_collection("meta", "this is meta") with self.test_session(graph=g) as session: variables.global_variables_initializer().run() new_graph_def = graph_util.convert_variables_to_constants( session, g.as_graph_def(), ["y"]) filename = os.path.join(self.base_path, constants.META_GRAPH_DEF_FILENAME) saver.export_meta_graph( filename, graph_def=new_graph_def, collection_list=["meta"])
Example #9
Source File: learning_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testNoneGlobalStep(self): with ops.Graph().as_default(): random_seed.set_random_seed(0) tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32) tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32) tf_predictions = BatchNormClassifier(tf_inputs) loss_ops.log_loss(tf_predictions, tf_labels) total_loss = loss_ops.get_total_loss() optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0) train_op = learning.create_train_op( total_loss, optimizer, global_step=None) global_step = variables_lib2.get_or_create_global_step() with session.Session() as sess: # Initialize all variables sess.run(variables_lib.global_variables_initializer()) for _ in range(10): sess.run([train_op]) global_step = global_step.eval() # Since train_op don't use global_step it shouldn't change. self.assertAllClose(global_step, 0)
Example #10
Source File: learning_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testUseGlobalStep(self): with ops.Graph().as_default(): random_seed.set_random_seed(0) tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32) tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32) tf_predictions = BatchNormClassifier(tf_inputs) loss_ops.log_loss(tf_predictions, tf_labels) total_loss = loss_ops.get_total_loss() optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0) train_op = learning.create_train_op(total_loss, optimizer) global_step = variables_lib2.get_or_create_global_step() with session.Session() as sess: # Initialize all variables sess.run(variables_lib.global_variables_initializer()) for _ in range(10): sess.run([train_op]) global_step = global_step.eval() # After 10 updates global_step should be 10. self.assertAllClose(global_step, 10)
Example #11
Source File: stepper_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def setUp(self): self.a = variables.Variable(2.0, name="a") self.b = variables.Variable(3.0, name="b") self.c = math_ops.multiply(self.a, self.b, name="c") # Should be 6.0. self.d = math_ops.multiply(self.a, self.a, name="d") # Should be 4.0. self.e = math_ops.multiply(self.d, self.c, name="e") # Should be 24.0. self.f_y = constant_op.constant(0.30, name="f_y") self.f = math_ops.div(self.b, self.f_y, name="f") # Should be 10.0. # The there nodes x, y and z form a graph with "cross-links" in. I.e., x # and y are both direct inputs to z, but x is also a direct input to y. self.x = variables.Variable(2.0, name="x") # Should be 2.0 self.y = math_ops.negative(self.x, name="y") # Should be -2.0. self.z = math_ops.multiply(self.x, self.y, name="z") # Should be -4.0. self.sess = session.Session() self.sess.run(variables.global_variables_initializer()) self.sess = session.Session() self.sess.run(variables.global_variables_initializer())
Example #12
Source File: supervisor.py From ctw-baseline with MIT License | 6 votes |
def _init_init_op(self, init_op=USE_DEFAULT, init_feed_dict=None): """Initializes init_op. Args: init_op: `Operation` to initialize the variables. If set to USE_DEFAULT, create an op that initializes all variables and tables. init_feed_dict: A dictionary that maps `Tensor` objects to feed values. This feed dictionary will be used when `init_op` is evaluated. """ if init_op is Supervisor.USE_DEFAULT: init_op = self._get_first_op_from_collection(ops.GraphKeys.INIT_OP) if init_op is None: init_op = variables.global_variables_initializer() ops.add_to_collection(ops.GraphKeys.INIT_OP, init_op) self._init_op = init_op self._init_feed_dict = init_feed_dict
Example #13
Source File: resnet_v1_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)): with ops.Graph().as_default(): with self.test_session() as sess: random_seed.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small( inputs, None, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. variable_scope.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, global_pool=False) sess.run(variables.global_variables_initializer()) self.assertAllClose( output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #14
Source File: inception_v2_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testUnknownImageShape(self): ops.reset_default_graph() batch_size = 2 height, width = 224, 224 num_classes = 1000 input_np = np.random.uniform(0, 1, (batch_size, height, width, 3)) with self.test_session() as sess: inputs = array_ops.placeholder( dtypes.float32, shape=(batch_size, None, None, 3)) logits, end_points = inception_v2.inception_v2(inputs, num_classes) self.assertTrue(logits.op.name.startswith('InceptionV2/Logits')) self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes]) pre_pool = end_points['Mixed_5c'] feed_dict = {inputs: input_np} variables.global_variables_initializer().run() pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict) self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
Example #15
Source File: inception_v3_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testUnknownImageShape(self): ops.reset_default_graph() batch_size = 2 height, width = 299, 299 num_classes = 1000 input_np = np.random.uniform(0, 1, (batch_size, height, width, 3)) with self.test_session() as sess: inputs = array_ops.placeholder( dtypes.float32, shape=(batch_size, None, None, 3)) logits, end_points = inception_v3.inception_v3(inputs, num_classes) self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes]) pre_pool = end_points['Mixed_7c'] feed_dict = {inputs: input_np} variables.global_variables_initializer().run() pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict) self.assertListEqual(list(pre_pool_out.shape), [batch_size, 8, 8, 2048])
Example #16
Source File: resnet_v2_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)): with ops.Graph().as_default(): with self.test_session() as sess: random_seed.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small( inputs, None, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. variable_scope.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, global_pool=False) sess.run(variables.global_variables_initializer()) self.assertAllClose( output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #17
Source File: inception_v3_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testTrainEvalWithReuse(self): train_batch_size = 5 eval_batch_size = 2 height, width = 150, 150 num_classes = 1000 train_inputs = random_ops.random_uniform( (train_batch_size, height, width, 3)) inception_v3.inception_v3(train_inputs, num_classes) eval_inputs = random_ops.random_uniform((eval_batch_size, height, width, 3)) logits, _ = inception_v3.inception_v3( eval_inputs, num_classes, is_training=False, reuse=True) predictions = math_ops.argmax(logits, 1) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(predictions) self.assertEquals(output.shape, (eval_batch_size,))
Example #18
Source File: inception_v1_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testUnknownImageShape(self): ops.reset_default_graph() batch_size = 2 height, width = 224, 224 num_classes = 1000 input_np = np.random.uniform(0, 1, (batch_size, height, width, 3)) with self.test_session() as sess: inputs = array_ops.placeholder( dtypes.float32, shape=(batch_size, None, None, 3)) logits, end_points = inception_v1.inception_v1(inputs, num_classes) self.assertTrue(logits.op.name.startswith('InceptionV1/Logits')) self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes]) pre_pool = end_points['Mixed_5c'] feed_dict = {inputs: input_np} variables.global_variables_initializer().run() pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict) self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
Example #19
Source File: inception_v1_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testTrainEvalWithReuse(self): train_batch_size = 5 eval_batch_size = 2 height, width = 224, 224 num_classes = 1000 train_inputs = random_ops.random_uniform( (train_batch_size, height, width, 3)) inception_v1.inception_v1(train_inputs, num_classes) eval_inputs = random_ops.random_uniform((eval_batch_size, height, width, 3)) logits, _ = inception_v1.inception_v1(eval_inputs, num_classes, reuse=True) predictions = math_ops.argmax(logits, 1) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(predictions) self.assertEquals(output.shape, (eval_batch_size,))
Example #20
Source File: evaluation_test.py From auto-alt-text-lambda-api with MIT License | 6 votes |
def testRestoredModelPerformance(self): checkpoint_path = os.path.join(self.get_temp_dir(), 'model.ckpt') log_dir = os.path.join(self.get_temp_dir(), 'log_dir1/') # First, save out the current model to a checkpoint: init_op = control_flow_ops.group(variables.global_variables_initializer(), variables.local_variables_initializer()) saver = saver_lib.Saver(write_version=saver_pb2.SaverDef.V1) with self.test_session() as sess: sess.run(init_op) saver.save(sess, checkpoint_path) # Next, determine the metric to evaluate: value_op, update_op = metric_ops.streaming_accuracy(self._predictions, self._labels) # Run the evaluation and verify the results: accuracy_value = evaluation.evaluate_once( '', checkpoint_path, log_dir, eval_op=update_op, final_op=value_op) self.assertAlmostEqual(accuracy_value, self._expected_accuracy)
Example #21
Source File: inception_v2_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testUnknownBatchSize(self): batch_size = 1 height, width = 224, 224 num_classes = 1000 inputs = array_ops.placeholder(dtypes.float32, (None, height, width, 3)) logits, _ = inception_v2.inception_v2(inputs, num_classes) self.assertTrue(logits.op.name.startswith('InceptionV2/Logits')) self.assertListEqual(logits.get_shape().as_list(), [None, num_classes]) images = random_ops.random_uniform((batch_size, height, width, 3)) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(logits, {inputs: images.eval()}) self.assertEquals(output.shape, (batch_size, num_classes))
Example #22
Source File: inception_v3_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testEvaluation(self): batch_size = 2 height, width = 299, 299 num_classes = 1000 eval_inputs = random_ops.random_uniform((batch_size, height, width, 3)) logits, _ = inception_v3.inception_v3( eval_inputs, num_classes, is_training=False) predictions = math_ops.argmax(logits, 1) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(predictions) self.assertEquals(output.shape, (batch_size,))
Example #23
Source File: inception_v3_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testUnknownBatchSize(self): batch_size = 1 height, width = 299, 299 num_classes = 1000 inputs = array_ops.placeholder(dtypes.float32, (None, height, width, 3)) logits, _ = inception_v3.inception_v3(inputs, num_classes) self.assertTrue(logits.op.name.startswith('InceptionV3/Logits')) self.assertListEqual(logits.get_shape().as_list(), [None, num_classes]) images = random_ops.random_uniform((batch_size, height, width, 3)) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(logits, {inputs: images.eval()}) self.assertEquals(output.shape, (batch_size, num_classes))
Example #24
Source File: sample_inputs_op_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testSparse(self): sparse_shape = [4, 10] sparse_indices = [[0, 0], [0, 4], [0, 9], [1, 0], [1, 7], [2, 0], [3, 1], [3, 4]] sparse_values = [3.0, -1.0, 0.5, 1.5, 6.0, -2.0, -0.5, 2.0] spec_proto = data_ops.TensorForestDataSpec() f1 = spec_proto.sparse.add() f1.name = 'f1' f1.original_type = data_ops.DATA_FLOAT f1.size = -1 spec_proto.dense_features_size = 0 data_spec = spec_proto.SerializeToString() with self.test_session(): variables.global_variables_initializer().run() (indices, feature_updates, threshold_updates) = (tensor_forest_ops.sample_inputs( [], sparse_indices, sparse_values, sparse_shape, [], self.node_map, self.leaves, self.split_features, self.split_thresholds, input_spec=data_spec, split_initializations_per_input=1, split_sampling_random_seed=3)) self.assertAllEqual([1, 0], indices.eval()) self.assertAllEqual([[1, 0, 0], [4, 0, -1]], feature_updates.eval()) self.assertAllEqual([[5., -2., -2.], [-1., 1.5, 0.]], threshold_updates.eval())
Example #25
Source File: scatter_add_ndim_op_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def test1dim(self): input_data = variables.Variable( [1., 2., 3., 4., 5., 6., 7., 8., 9., 10., 11., 12.]) indices = [[1], [10]] updates = [100., 200.] with self.test_session(): variables.global_variables_initializer().run() tensor_forest_ops.scatter_add_ndim(input_data, indices, updates).run() self.assertAllEqual( [1., 102., 3., 4., 5., 6., 7., 8., 9., 10., 211., 12.], input_data.eval())
Example #26
Source File: vgg_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testForward(self): batch_size = 1 height, width = 224, 224 with self.test_session() as sess: inputs = random_ops.random_uniform((batch_size, height, width, 3)) logits, _ = vgg.vgg_16(inputs) sess.run(variables.global_variables_initializer()) output = sess.run(logits) self.assertTrue(output.any())
Example #27
Source File: vgg_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testForward(self): batch_size = 1 height, width = 224, 224 with self.test_session() as sess: inputs = random_ops.random_uniform((batch_size, height, width, 3)) logits, _ = vgg.vgg_19(inputs) sess.run(variables.global_variables_initializer()) output = sess.run(logits) self.assertTrue(output.any())
Example #28
Source File: inception_v2_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testLogitsNotSqueezed(self): num_classes = 25 images = random_ops.random_uniform([1, 224, 224, 3]) logits, _ = inception_v2.inception_v2( images, num_classes=num_classes, spatial_squeeze=False) with self.test_session() as sess: variables.global_variables_initializer().run() logits_out = sess.run(logits) self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
Example #29
Source File: inception_v1_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testUnknownBatchSize(self): batch_size = 1 height, width = 224, 224 num_classes = 1000 inputs = array_ops.placeholder(dtypes.float32, (None, height, width, 3)) logits, _ = inception_v1.inception_v1(inputs, num_classes) self.assertTrue(logits.op.name.startswith('InceptionV1/Logits')) self.assertListEqual(logits.get_shape().as_list(), [None, num_classes]) images = random_ops.random_uniform((batch_size, height, width, 3)) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(logits, {inputs: images.eval()}) self.assertEquals(output.shape, (batch_size, num_classes))
Example #30
Source File: inception_v2_test.py From auto-alt-text-lambda-api with MIT License | 5 votes |
def testEvaluation(self): batch_size = 2 height, width = 224, 224 num_classes = 1000 eval_inputs = random_ops.random_uniform((batch_size, height, width, 3)) logits, _ = inception_v2.inception_v2( eval_inputs, num_classes, is_training=False) predictions = math_ops.argmax(logits, 1) with self.test_session() as sess: sess.run(variables.global_variables_initializer()) output = sess.run(predictions) self.assertEquals(output.shape, (batch_size,))