Python tensorflow.compat.v1.global_variables_initializer() Examples
The following are 30
code examples of tensorflow.compat.v1.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.compat.v1
, or try the search function
.
Example #1
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSigmoidAccuracyOneHot(self): logits = np.array([ [-1., 1.], [1., -1.], [-1., 1.], [1., -1.] ]) labels = np.array([ [0, 1], [1, 0], [1, 0], [0, 1] ]) logits = np.expand_dims(np.expand_dims(logits, 1), 1) labels = np.expand_dims(np.expand_dims(labels, 1), 1) with self.test_session() as session: score, _ = metrics.sigmoid_accuracy_one_hot(logits, labels) session.run(tf.global_variables_initializer()) session.run(tf.local_variables_initializer()) s = session.run(score) self.assertEqual(s, 0.5)
Example #2
Source File: lstm_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testLSTMSeq2seqAttentionBidirectionalEncoder(self): vocab_size = 9 x = np.random.randint(1, high=vocab_size, size=(3, 5, 1, 1)) y = np.random.randint(1, high=vocab_size, size=(3, 6, 1, 1)) hparams = lstm.lstm_attention() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size) x = tf.constant(x, dtype=tf.int32) x = tf.placeholder_with_default(x, shape=[None, None, 1, 1]) with self.test_session() as session: features = { "inputs": x, "targets": tf.constant(y, dtype=tf.int32), } model = lstm.LSTMSeq2seqAttentionBidirectionalEncoder( hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 6, 1, 1, vocab_size))
Example #3
Source File: lstm_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testLSTMSeq2seqBidirectionalEncoder(self): vocab_size = 9 x = np.random.randint(1, high=vocab_size, size=(3, 5, 1, 1)) y = np.random.randint(1, high=vocab_size, size=(3, 6, 1, 1)) hparams = lstm.lstm_seq2seq() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) with self.test_session() as session: features = { "inputs": tf.constant(x, dtype=tf.int32), "targets": tf.constant(y, dtype=tf.int32), } model = lstm.LSTMSeq2seqBidirectionalEncoder( hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 6, 1, 1, vocab_size))
Example #4
Source File: ppo_learner.py From tensor2tensor with Apache License 2.0 | 6 votes |
def evaluate(self, env_fn, hparams, sampling_temp): with tf.Graph().as_default(): with tf.name_scope("rl_eval"): eval_env = env_fn(in_graph=True) (collect_memory, _, collect_init) = _define_collect( eval_env, hparams, "ppo_eval", eval_phase=True, frame_stack_size=self.frame_stack_size, force_beginning_resets=False, sampling_temp=sampling_temp, distributional_size=self._distributional_size, ) model_saver = tf.train.Saver( tf.global_variables(hparams.policy_network + "/.*") # tf.global_variables("clean_scope.*") # Needed for sharing params. ) with tf.Session() as sess: sess.run(tf.global_variables_initializer()) collect_init(sess) trainer_lib.restore_checkpoint(self.agent_model_dir, model_saver, sess) sess.run(collect_memory)
Example #5
Source File: glow_ops_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def test_invertibility(self, op, name, dropout=0.0): with tf.Graph().as_default(): tf.set_random_seed(42) x = tf.random_uniform(shape=(16, 32, 32, 4)) if op in [glow_ops.affine_coupling, glow_ops.additive_coupling]: with arg_scope([glow_ops.get_dropout], init=False): x_inv, _ = op(name, x, reverse=False, dropout=dropout) x_inv_inv, _ = op(name, x_inv, reverse=True, dropout=dropout) else: x_inv, _ = op(name, x, reverse=False) x_inv_inv, _ = op(name, x_inv, reverse=True) with tf.Session() as session: session.run(tf.global_variables_initializer()) diff = session.run(x - x_inv_inv) self.assertTrue(np.allclose(diff, 0.0, atol=1e-5))
Example #6
Source File: xception_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def _test_xception(self, img_size): vocab_size = 9 batch_size = 3 x = np.random.randint( 256, size=(batch_size, img_size, img_size, 3)) y = np.random.randint( 1, high=vocab_size, size=(batch_size, 1, 1, 1)) hparams = xception.xception_tiny() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) p_hparams.modality["inputs"] = modalities.ModalityType.IMAGE p_hparams.modality["targets"] = modalities.ModalityType.CLASS_LABEL with self.test_session() as session: features = { "inputs": tf.constant(x, dtype=tf.int32), "targets": tf.constant(y, dtype=tf.int32), } model = xception.Xception(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (batch_size, 1, 1, 1, vocab_size))
Example #7
Source File: variable_mgr_util_test.py From benchmarks with Apache License 2.0 | 6 votes |
def testAppendGradientsWithLossScaleWithAutoScaleDisabled(self): v = tf.Variable(0) training_ops = [] get_apply_gradients_ops_func = lambda: [tf.assign(v, v + 1)] loss_scale_params = variable_mgr_util.AutoLossScaleParams( enable_auto_loss_scale=False, # no auto loss scale. loss_scale=tf.Variable(4), loss_scale_normal_steps=tf.Variable(10), inc_loss_scale_every_n=10, is_chief=True) variable_mgr_util.append_gradients_with_loss_scale( training_ops, get_apply_gradients_ops_func, loss_scale_params, grad_has_inf_nan=True) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) sess.run(training_ops) self.assertEqual(sess.run(v), 1) self.assertEqual(sess.run(loss_scale_params.loss_scale), 4) self.assertEqual(sess.run(loss_scale_params.loss_scale_normal_steps), 10)
Example #8
Source File: slicenet_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSliceNetImageToText(self): x = np.random.randint(256, size=(3, 5, 5, 3)) y = np.random.randint(10, size=(3, 5, 1, 1)) hparams = slicenet.slicenet_params1_tiny() hparams.add_hparam("data_dir", "") problem = registry.problem("image_ms_coco_characters") p_hparams = problem.get_hparams(hparams) hparams.problem_hparams = p_hparams with self.test_session() as session: features = { "inputs": tf.constant(x, dtype=tf.int32), "targets": tf.constant(y, dtype=tf.int32), "target_space_id": tf.constant(1, dtype=tf.int32), } model = slicenet.SliceNet(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 5, 1, 1, 258))
Example #9
Source File: variable_mgr_util_test.py From benchmarks with Apache License 2.0 | 6 votes |
def testAppendGradientsWithLossScaleForNonChiefWorker(self): v = tf.Variable(0) training_ops = [] get_apply_gradients_ops_func = lambda: [tf.assign(v, v + 1)] loss_scale_params = variable_mgr_util.AutoLossScaleParams( enable_auto_loss_scale=True, loss_scale=tf.Variable(4), loss_scale_normal_steps=tf.Variable(10), inc_loss_scale_every_n=10, is_chief=False) # Non-chief variable_mgr_util.append_gradients_with_loss_scale( training_ops, get_apply_gradients_ops_func, loss_scale_params, grad_has_inf_nan=False) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) sess.run(training_ops) self.assertEqual(sess.run(v), 1) self.assertEqual(sess.run(loss_scale_params.loss_scale), 4) self.assertEqual(sess.run(loss_scale_params.loss_scale_normal_steps), 10)
Example #10
Source File: variable_mgr_util_test.py From benchmarks with Apache License 2.0 | 6 votes |
def testAppendGradientsWithLossScaleWithtNan(self): v = tf.Variable(0) training_ops = [] get_apply_gradients_ops_func = lambda: [tf.assign(v, v + 1)] loss_scale_params = variable_mgr_util.AutoLossScaleParams( enable_auto_loss_scale=True, loss_scale=tf.Variable(4, dtype=tf.float32), loss_scale_normal_steps=tf.Variable(10), inc_loss_scale_every_n=10, is_chief=True) variable_mgr_util.append_gradients_with_loss_scale( training_ops, get_apply_gradients_ops_func, loss_scale_params, grad_has_inf_nan=tf.constant(True)) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) sess.run(training_ops) self.assertEqual(sess.run(v), 0) # Skip updating for v. # halve loss_scale and reset local_scale_normal_steps. self.assertEqual(sess.run(loss_scale_params.loss_scale), 2) self.assertEqual(sess.run(loss_scale_params.loss_scale_normal_steps), 0)
Example #11
Source File: player_utils.py From tensor2tensor with Apache License 2.0 | 6 votes |
def __init__(self, hparams, action_space, observation_space, policy_dir): assert hparams.base_algo == "ppo" ppo_hparams = trainer_lib.create_hparams(hparams.base_algo_params) frame_stack_shape = (1, hparams.frame_stack_size) + observation_space.shape self._frame_stack = np.zeros(frame_stack_shape, dtype=np.uint8) with tf.Graph().as_default(): self.obs_t = tf.placeholder(shape=self.frame_stack_shape, dtype=np.uint8) self.logits_t, self.value_function_t = get_policy( self.obs_t, ppo_hparams, action_space ) model_saver = tf.train.Saver( tf.global_variables(scope=ppo_hparams.policy_network + "/.*") # pylint: disable=unexpected-keyword-arg ) self.sess = tf.Session() self.sess.run(tf.global_variables_initializer()) trainer_lib.restore_checkpoint(policy_dir, model_saver, self.sess)
Example #12
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSequenceEditDistanceMetric(self): predictions = np.array([[3, 4, 5, 1, 0, 0], [2, 1, 3, 4, 0, 0], [2, 1, 3, 4, 0, 0]]) # Targets are just a bit different: # - first sequence has a different prediction # - second sequence has a different prediction and one extra step # - third sequence is identical targets = np.array([[5, 4, 5, 1, 0, 0], [2, 5, 3, 4, 1, 0], [2, 1, 3, 4, 0, 0]]) # Reshape to match expected input format by metric fns. predictions = np.reshape(predictions, [3, 6, 1, 1]) targets = np.reshape(targets, [3, 6, 1, 1]) with self.test_session() as session: scores, weight = metrics.sequence_edit_distance( tf.one_hot(predictions, depth=6, dtype=tf.float32), tf.constant(targets, dtype=tf.int32)) session.run(tf.global_variables_initializer()) actual_scores, actual_weight = session.run([scores, weight]) self.assertAlmostEqual(actual_scores, 3.0 / 13) self.assertEqual(actual_weight, 13)
Example #13
Source File: mtf_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfTransformerEncoderDataModelParallel(self): hparams = mtf_transformer.mtf_transformer_enc_single() model, features, hparams = get_model(hparams) hparams.mesh_shape = "batch:2;model:2" hparams.layout = "batch:batch;vocab:model;d_ff:model;heads:model" mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, TARGET_LENGTH, VOCAB_SIZE))
Example #14
Source File: mtf_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfTransformerModelParallel(self): hparams = mtf_transformer.mtf_transformer_single() model, features, hparams = get_model(hparams) hparams.mesh_shape = "all:2" hparams.layout = "length:all" mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, TARGET_LENGTH, VOCAB_SIZE))
Example #15
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testNegativeLogPerplexityMaskedAssert(self): predictions = np.random.randint(4, size=(12, 12, 12, 1)) targets = np.random.randint(4, size=(12, 12, 12, 1)) features = {} with self.assertRaisesRegexp( ValueError, 'masked_neg_log_perplexity requires targets_mask feature'): with self.test_session() as session: scores, _ = metrics.padded_neg_log_perplexity_with_masking( tf.one_hot(predictions, depth=4, dtype=tf.float32), tf.constant(targets, dtype=tf.int32), features) a = tf.reduce_mean(scores) session.run(tf.global_variables_initializer()) _ = session.run(a)
Example #16
Source File: lstm_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testLSTMSeq2Seq(self): vocab_size = 9 x = np.random.randint(1, high=vocab_size, size=(3, 5, 1, 1)) y = np.random.randint(1, high=vocab_size, size=(3, 6, 1, 1)) hparams = lstm.lstm_seq2seq() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) with self.test_session() as session: features = { "inputs": tf.constant(x, dtype=tf.int32), "targets": tf.constant(y, dtype=tf.int32), } model = lstm.LSTMSeq2seq(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 6, 1, 1, vocab_size))
Example #17
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSigmoidPrecisionOneHot(self): logits = np.array([ [-1., 1.], [1., -1.], [1., -1.], [1., -1.] ]) labels = np.array([ [0, 1], [0, 1], [0, 1], [0, 1] ]) logits = np.expand_dims(np.expand_dims(logits, 1), 1) labels = np.expand_dims(np.expand_dims(labels, 1), 1) with self.test_session() as session: score, _ = metrics.sigmoid_precision_one_hot(logits, labels) session.run(tf.global_variables_initializer()) session.run(tf.local_variables_initializer()) s = session.run(score) self.assertEqual(s, 0.25)
Example #18
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSigmoidRecallOneHot(self): logits = np.array([ [-1., 1.], [1., -1.], [1., -1.], [1., -1.] ]) labels = np.array([ [0, 1], [0, 1], [0, 1], [0, 1] ]) logits = np.expand_dims(np.expand_dims(logits, 1), 1) labels = np.expand_dims(np.expand_dims(labels, 1), 1) with self.test_session() as session: score, _ = metrics.sigmoid_recall_one_hot(logits, labels) session.run(tf.global_variables_initializer()) session.run(tf.local_variables_initializer()) s = session.run(score) self.assertEqual(s, 0.25)
Example #19
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testSigmoidCrossEntropyOneHot(self): logits = np.array([ [-1., 1.], [1., -1.], [1., -1.], [1., -1.] ]) labels = np.array([ [0, 1], [1, 0], [0, 0], [0, 1] ]) logits = np.expand_dims(np.expand_dims(logits, 1), 1) labels = np.expand_dims(np.expand_dims(labels, 1), 1) with self.test_session() as session: score, _ = metrics.sigmoid_cross_entropy_one_hot(logits, labels) session.run(tf.global_variables_initializer()) session.run(tf.local_variables_initializer()) s = session.run(score) self.assertAlmostEqual(s, 0.688, places=3)
Example #20
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testRocAuc(self): logits = np.array([ [-1., 1.], [1., -1.], [1., -1.], [1., -1.] ]) labels = np.array([ [1], [0], [1], [0] ]) logits = np.expand_dims(np.expand_dims(logits, 1), 1) labels = np.expand_dims(np.expand_dims(labels, 1), 1) with self.test_session() as session: score, _ = metrics.roc_auc(logits, labels) session.run(tf.global_variables_initializer()) session.run(tf.local_variables_initializer()) s = session.run(score) self.assertAlmostEqual(s, 0.750, places=3)
Example #21
Source File: metrics_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMultilabelMatch3(self): predictions = np.random.randint(1, 5, size=(100, 1, 1, 1)) targets = np.random.randint(1, 5, size=(100, 10, 1, 1)) weights = np.random.randint(0, 2, size=(100, 1, 1, 1)) targets *= weights predictions_repeat = np.repeat(predictions, 10, axis=1) expected = (predictions_repeat == targets).astype(float) expected = np.sum(expected, axis=(1, 2, 3)) expected = np.minimum(expected / 3.0, 1.) expected = np.sum(expected * weights[:, 0, 0, 0]) / weights.shape[0] with self.test_session() as session: scores, weights_ = metrics.multilabel_accuracy_match3( tf.one_hot(predictions, depth=5, dtype=tf.float32), tf.constant(targets, dtype=tf.int32)) a, a_op = tf.metrics.mean(scores, weights_) session.run(tf.local_variables_initializer()) session.run(tf.global_variables_initializer()) _ = session.run(a_op) actual = session.run(a) self.assertAlmostEqual(actual, expected, places=6)
Example #22
Source File: mtf_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfTransformerDataParallel(self): hparams = mtf_transformer.mtf_transformer_single() model, features, hparams = get_model(hparams) hparams.mesh_shape = "all:2" hparams.layout = "batch:all" mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, TARGET_LENGTH, VOCAB_SIZE))
Example #23
Source File: mtf_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfTransformer(self): hparams = mtf_transformer.mtf_transformer_single() model, features, hparams = get_model(hparams) hparams.mesh_shape = "" hparams.layout = "" mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, TARGET_LENGTH, VOCAB_SIZE))
Example #24
Source File: rouge_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testRougeLMetricE2E(self): vocab_size = 4 batch_size = 12 seq_length = 12 predictions = tf.one_hot( np.random.randint(vocab_size, size=(batch_size, seq_length, 1, 1)), depth=4, dtype=tf.float32) targets = np.random.randint(4, size=(12, 12, 1, 1)) with self.test_session() as session: scores, _ = rouge.rouge_l_fscore( predictions, tf.constant(targets, dtype=tf.int32)) a = tf.reduce_mean(scores) session.run(tf.global_variables_initializer()) session.run(a)
Example #25
Source File: image_transformer_2d_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def _test_imagetransformer_2d(self, net): batch_size = 3 size = 7 vocab_size = 256 hparams = image_transformer_2d.imagetransformer2d_tiny() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) inputs = np.random.randint( vocab_size, size=(batch_size, 1, 1, 1)) targets = np.random.randint( vocab_size, size=(batch_size, size, size, 3)) with self.test_session() as session: features = { "inputs": tf.constant(inputs, dtype=tf.int32), "targets": tf.constant(targets, dtype=tf.int32), "target_space_id": tf.constant(1, dtype=tf.int32), } model = net(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (batch_size, size, size, 3, vocab_size))
Example #26
Source File: bytenet_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testByteNet(self): vocab_size = 9 x = np.random.randint(1, high=vocab_size, size=(3, 5, 1, 1)) y = np.random.randint(1, high=vocab_size, size=(3, 6, 1, 1)) hparams = bytenet.bytenet_base() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) with self.test_session() as session: features = { "inputs": tf.constant(x, dtype=tf.int32), "targets": tf.constant(y, dtype=tf.int32), } model = bytenet.ByteNet( hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 50, 1, 1, vocab_size))
Example #27
Source File: mtf_image_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfImageTransformerModelParallel(self): hparams = mtf_image_transformer.mtf_image_transformer_single() # need to know layout ahead of time for local attention. hparams.mesh_shape = "all:2" hparams.layout = "length:all" model, features, hparams = get_model(hparams) mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual( res.shape, (BATCH_SIZE, IMG_LENGTH, IMG_LENGTH, hparams.num_channels, VOCAB_SIZE))
Example #28
Source File: gene_expression_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def _test_model(self, hparams, model_cls): batch_size = 3 target_length = 6 target_out = 10 # GeneExpressionProblem.num_output_predictions input_length = target_length * 128 // 4 # chunk_size=4 input_vocab_size = 5 inputs = np.random.randint( 1, input_vocab_size + 1, size=(batch_size, input_length, 1, 1)) targets = np.random.random_sample((batch_size, target_length, 1, target_out)) features = { "inputs": tf.constant(inputs, dtype=tf.int32), "targets": tf.constant(targets, dtype=tf.float32), } p_hparams = hparams.problem_hparams logits, _ = model_cls( hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)(features) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) res = sess.run(logits) self.assertEqual(res.shape, (batch_size, target_length, 1, target_out))
Example #29
Source File: mtf_image_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfImageTransformerDataParallel(self): hparams = mtf_image_transformer.mtf_image_transformer_single() # need to know layout ahead of time for local attention. hparams.mesh_shape = "all:2" hparams.layout = "batch:all" model, features, hparams = get_model(hparams) mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, IMG_LENGTH, IMG_LENGTH, hparams.num_channels, VOCAB_SIZE))
Example #30
Source File: mtf_image_transformer_test.py From tensor2tensor with Apache License 2.0 | 6 votes |
def testMtfImageTransformer(self): hparams = mtf_image_transformer.mtf_image_transformer_single() # need to know layout ahead of time for local attention. hparams.mesh_shape = "" hparams.layout = "" model, features, hparams = get_model(hparams) mesh, mesh_impl = get_placement_mesh(hparams) logits, _ = model.mtf_model_fn(features, mesh) lowering = mtf.Lowering(mesh.graph, {mesh: mesh_impl}) tf_group = lowering.copy_masters_to_slices() tf_logits = lowering.export_to_tf_tensor(logits) with self.test_session() as session: session.run(tf.global_variables_initializer()) session.run(tf_group) res = session.run(tf_logits) self.assertEqual(res.shape, (BATCH_SIZE, IMG_LENGTH, IMG_LENGTH, hparams.num_channels, VOCAB_SIZE))