| /external/tensorflow/tensorflow/contrib/eager/python/examples/gan/ |
| mnist.py | 211 dataset: Dataset of images to train on.
221 tf.assign_add(tf.train.get_global_step(), 1)
270 .from_tensor_slices(data.train.images)
278 generator_optimizer = tf.train.AdamOptimizer(FLAGS.lr)
280 discriminator_optimizer = tf.train.AdamOptimizer(FLAGS.lr)
286 latest_cpkt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
293 global_step = tf.train.get_or_create_global_step()
|
| /external/tensorflow/tensorflow/contrib/eager/python/examples/mnist/ |
| mnist.py | 122 tf.train.get_or_create_global_step()
158 train_ds = tf.data.Dataset.from_tensor_slices((data.train.images,
159 data.train.labels))
178 optimizer = tf.train.MomentumOptimizer(FLAGS.lr, FLAGS.momentum)
181 train_dir = os.path.join(FLAGS.output_dir, 'train')
196 tf.train.latest_checkpoint(FLAGS.checkpoint_dir)):
197 global_step = tf.train.get_or_create_global_step()
|
| mnist_graph_test.py | 46 optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.0)
60 # Train using the optimizer.
|
| /external/tensorflow/tensorflow/contrib/learn/python/learn/datasets/ |
| mnist.py | 227 train = fake()
230 return base.Datasets(train=train, validation=validation, test=test)
235 TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
236 TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
271 train = DataSet(train_images, train_labels, **options)
275 return base.Datasets(train=train, validation=validation, test=test)
|
| /external/tensorflow/tensorflow/examples/get_started/regression/ |
| imports85.py | 75 """Load the imports85 data as a (train,test) pair of `Dataset`.
84 A (train,test) pair of `Datasets`
140 train = (base_dataset
151 return train, test
195 # Split the data into train/test subsets.
|
| /external/tensorflow/tensorflow/examples/tutorials/mnist/ |
| mnist_softmax_xla.py | 56 train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
68 # Train
71 batch_xs, batch_ys = mnist.train.next_batch(100)
|
| mnist_deep.py | 145 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
160 batch = mnist.train.next_batch(50)
|
| /external/tensorflow/tensorflow/python/ops/ |
| batch_norm_benchmark.py | 68 def build_graph(device, input_shape, axes, num_layers, mode, scale, train):
78 train: if true, also run backprop.
98 if train:
111 if train:
127 train, num_iters):
137 train: if true, also run backprop.
146 train)
154 print("%s shape:%d/%d #layers:%d mode:%s scale:%r train:%r - %f secs" %
155 (device, len(input_shape), len(axes), num_layers, mode, scale, train,
161 "train_{train}")
[all...] |
| /external/tensorflow/tensorflow/contrib/eager/python/examples/rnn_ptb/ |
| rnn_ptb_test.py | 42 optimizer = tf.train.GradientDescentOptimizer(1.0)
43 # Train two epochs
44 rnn_ptb.train(model, optimizer, data, sequence_length, 0.25)
45 rnn_ptb.train(model, optimizer, data, sequence_length, 0.25)
109 optimizer = tf.train.GradientDescentOptimizer(1.)
|
| rnn_ptb.py | 188 def train(model, optimizer, train_data, sequence_length, clip_ratio): function
225 self.train = self.tokenize(os.path.join(path, "ptb.train.txt"))
298 train_data = _divide_into_batches(corpus.train, FLAGS.batch_size)
305 tf.train.latest_checkpoint(FLAGS.logdir)):
314 optimizer = tf.train.GradientDescentOptimizer(learning_rate)
318 train(model, optimizer, train_data, FLAGS.seq_len, FLAGS.clip)
|
| /external/tensorflow/tensorflow/contrib/timeseries/python/timeseries/state_space_models/ |
| structural_ensemble_test.py | 79 estimator.train(input_fn=train_input_fn, max_steps=1)
81 estimator.train(input_fn=train_input_fn, max_steps=3)
119 regressor.train(input_fn=train_input_fn, steps=1)
143 regressor.train(input_fn=train_input_fn, steps=1)
|
| /external/tensorflow/tensorflow/python/debug/examples/ |
| debug_mnist.py | 48 def feed_dict(train):
49 if train or FLAGS.fake_data:
50 xs, ys = mnist.train.next_batch(FLAGS.train_batch_size,
111 with tf.name_scope("train"):
112 train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
|
| /external/tensorflow/tensorflow/contrib/model_pruning/examples/cifar10/ |
| cifar10_pruning.py | 30 train_op = train(loss, global_step)
153 eval_data: bool, indicating if one should use the train or eval data set.
309 loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
324 def train(total_loss, global_step): function
325 """Train CIFAR-10 model.
342 lr = tf.train.exponential_decay(
355 opt = tf.train.GradientDescentOptimizer(lr)
371 variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,
376 train_op = tf.no_op(name='train')
|
| /external/tensorflow/tensorflow/contrib/factorization/python/ops/ |
| kmeans_test.py | 162 kmeans.train(input_fn=self.input_fn(), steps=1)
168 kmeans.train(input_fn=self.input_fn(), steps=1)
171 kmeans.train(input_fn=self.input_fn(), steps=steps)
190 kmeans.train(
192 # Force it to train until the relative tolerance monitor stops it.
222 kmeans.train(input_fn=self.input_fn(), max_steps=max_steps)
243 kmeans.train(
259 kmeans.train(
277 kmeans.train(
341 self.kmeans.train(input_fn=self.input_fn(), max_steps=max_steps
[all...] |
| /external/tensorflow/tensorflow/contrib/slim/python/slim/ |
| learning_test.py | 256 loss = learning.train(
443 loss = learning.train(
462 loss = learning.train(
482 loss = learning.train(
492 """Test that slim.learning.train can take `session_wrapper` args.
517 loss = learning.train(
543 loss = learning.train(
571 learning.train(
589 learning.train(
608 learning.train(
[all...] |
| /external/tensorflow/tensorflow/contrib/learn/python/learn/ |
| graph_actions_test.py | 152 # TODO(ptucker): Test start_queue_runners for both eval & train.
403 # TODO(ispir): remove following tests after deprecated train.
405 """Tests for train."""
475 learn.graph_actions.train(
478 learn.graph_actions.train(
484 learn.graph_actions.train(
487 learn.graph_actions.train(
493 learn.graph_actions.train(
510 loss = learn.graph_actions.train(
527 learn.graph_actions.train(
[all...] |
| /external/tensorflow/tensorflow/python/grappler/ |
| memory_optimizer_test.py | 35 from tensorflow.python.training import training as train
122 optimizer = train.AdamOptimizer(0.001)
125 metagraph = train.export_meta_graph()
190 train.import_meta_graph(metagraph)
243 optimizer = train.AdamOptimizer(0.001)
265 metagraph = train.export_meta_graph()
|
| /external/tensorflow/tensorflow/contrib/boosted_trees/examples/ |
| binary_mnist.py | 60 images_batch, labels_batch = tf.train.shuffle_batch(
102 train_input_fn = get_input_fn(data.train, FLAGS.batch_size)
|
| mnist.py | 55 images_batch, labels_batch = tf.train.shuffle_batch(
104 train_input_fn = get_input_fn(data.train, FLAGS.batch_size)
|
| /external/tensorflow/tensorflow/contrib/eager/python/examples/linear_regression/ |
| linear_regression_test.py | 75 optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
100 optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
|
| /external/tensorflow/tensorflow/contrib/nn/python/ops/ |
| sampling_ops.py | 157 if mode == "train":
259 This is a faster way to train a softmax classifier over a huge number of
271 if mode == "train":
|
| /external/tensorflow/tensorflow/examples/learn/ |
| random_forest_mnist.py | 52 """Train and evaluate the model."""
61 x={'images': mnist.train.images},
62 y=mnist.train.labels.astype(numpy.int32),
|
| /packages/apps/TV/tests/input/tools/ |
| get_test_logos.sh | 34 snow sport star swim taxi train
|
| /external/tensorflow/tensorflow/contrib/eager/python/examples/resnet50/ |
| resnet50_test.py | 104 tf.train.get_or_create_global_step()
110 optimizer = tf.train.GradientDescentOptimizer(0.1)
121 optimizer = tf.train.GradientDescentOptimizer(0.1)
219 optimizer = tf.train.GradientDescentOptimizer(0.1)
|
| /external/tensorflow/tensorflow/contrib/eager/python/examples/rnn_colorbot/ |
| rnn_colorbot_test.py | 54 optimizer = tf.train.AdamOptimizer(learning_rate=.01)
|
