Python nets.inception.inception_v3_arg_scope() Examples

The following are 30 code examples of nets.inception.inception_v3_arg_scope(). 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 nets.inception , or try the search function .
Example #1
Source File: inception_v3_test.py    From nasnet-tensorflow with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #2
Source File: inception_v3_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #3
Source File: inception_v3_test.py    From Translation-Invariant-Attacks with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #4
Source File: inception_v3_test.py    From Action_Recognition_Zoo with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #5
Source File: inception_v3_test.py    From ECO-pytorch with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #6
Source File: inception_v3_test.py    From Machine-Learning-with-TensorFlow-1.x with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #7
Source File: inception_v3_test.py    From hands-detection with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #8
Source File: inception_v3_test.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #9
Source File: inception_v3_test.py    From MBMD with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #10
Source File: inception_v3_test.py    From Optical-Flow-Guided-Feature with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #11
Source File: inception_v3_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #12
Source File: inception_v3_test.py    From SENet-tensorflow-slim with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #13
Source File: inception_v3_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #14
Source File: inception_v3_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
def testNoBatchNormScaleByDefault(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3(inputs, num_classes, is_training=False)

    self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
Example #15
Source File: inception_v3_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
def testBatchNormScale(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(
        inception.inception_v3_arg_scope(batch_norm_scale=True)):
      inception.inception_v3(inputs, num_classes, is_training=False)

    gamma_names = set(
        v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
    self.assertGreater(len(gamma_names), 0)
    for v in tf.global_variables('.*/BatchNorm/moving_mean:0$'):
      self.assertIn(v.op.name[:-len('moving_mean')] + 'gamma', gamma_names)
Example #16
Source File: inception_v3_test.py    From tf_classification with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #17
Source File: inception_v3_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #18
Source File: body_feature_extractor_common.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def build_network(batch_size, is_training):
    # input
    tf_raw_image_data = tf.placeholder(tf.string, shape=(batch_size,))
    tf_body_bbox = tf.placeholder(tf.int32, shape=(batch_size, 4))
    tf_labels = tf.placeholder(tf.int32, shape=(batch_size,))

    # pre-processing pipeline
    crops = []
    for i in range(batch_size):
        image = tf.image.decode_jpeg(tf_raw_image_data[i], channels=3)
        body_crop = tf.image.crop_to_bounding_box(image, tf_body_bbox[i, 1], tf_body_bbox[i, 0], tf_body_bbox[i, 3],
                                                  tf_body_bbox[i, 2])
        processed_crop = inception_preprocessing.preprocess_image(body_crop, image_size, image_size,
                                                                  is_training=is_training)
        crops.append(processed_crop)
    processed_images = tf.stack(crops)

    # training pipeline
    with slim.arg_scope(inception.inception_v3_arg_scope()):
        _, endpoints = inception.inception_v3(processed_images, num_classes=num_identity, is_training=is_training)

    # load model parameters
    init_fn = slim.assign_from_checkpoint_fn(os.path.join(checkpoints_dir, checkpoint_name),
                                             slim.get_model_variables(original_variable_namescope))

    net_before_pool = tf.reshape(endpoints['Mixed_7c'], shape=(batch_size, -1))
    net_before_pool_frozen = tf.stop_gradient(net_before_pool)
    tf_features = slim.fully_connected(net_before_pool_frozen, feature_length, activation_fn=None)
    tf_features_normalized = tf.nn.l2_normalize(tf_features, dim=1)
    tf_loss = coco_loss_layer(tf_features_normalized, tf_labels, batch_size)

    # optimizer
    tf_lr = tf.placeholder(dtype=tf.float32, shape=(), name='learning_rate')
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
    train = optimizer.minimize(tf_loss)

    # summary
    tf.summary.scalar('coco_loss', tf_loss)
    summary_op = tf.summary.merge_all()

    return (tf_raw_image_data, tf_body_bbox, tf_labels), (init_fn, tf_loss, tf_lr, train, summary_op), tf_features
Example #19
Source File: head_feature_extractor_common.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def build_network(batch_size, is_training):
    # input
    tf_raw_image_data = tf.placeholder(tf.string, shape=(batch_size,))
    tf_body_bbox = tf.placeholder(tf.int32, shape=(batch_size, 4))
    tf_labels = tf.placeholder(tf.int32, shape=(batch_size,))

    # pre-processing pipeline
    crops = []
    for i in range(batch_size):
        image = tf.image.decode_jpeg(tf_raw_image_data[i], channels=3)
        body_crop = tf.image.crop_to_bounding_box(image, tf_body_bbox[i, 1], tf_body_bbox[i, 0], tf_body_bbox[i, 3],
                                                  tf_body_bbox[i, 2])
        processed_crop = inception_preprocessing.preprocess_image(body_crop, image_size, image_size,
                                                                  is_training=is_training)
        crops.append(processed_crop)
    processed_images = tf.stack(crops)

    # training pipeline
    with slim.arg_scope(inception.inception_v3_arg_scope()):
        _, endpoints = inception.inception_v3(processed_images, num_classes=num_identity, is_training=is_training)

    # load model parameters
    init_fn = slim.assign_from_checkpoint_fn(os.path.join(checkpoints_dir, checkpoint_name),
                                             slim.get_model_variables(original_variable_namescope))

    net_before_pool = tf.reshape(endpoints['Mixed_7c'], shape=(batch_size, -1))
    net_before_pool_frozen = tf.stop_gradient(net_before_pool)
    tf_features = slim.fully_connected(net_before_pool_frozen, feature_length, activation_fn=None)
    tf_features_normalized = tf.nn.l2_normalize(tf_features, dim=1)
    tf_loss = coco_loss_layer(tf_features_normalized, tf_labels, batch_size)

    # optimizer
    tf_lr = tf.placeholder(dtype=tf.float32, shape=(), name='learning_rate')
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
    train = optimizer.minimize(tf_loss)

    # summary
    tf.summary.scalar('coco_loss', tf_loss)
    summary_op = tf.summary.merge_all()

    return (tf_raw_image_data, tf_body_bbox, tf_labels), (init_fn, tf_loss, tf_lr, train, summary_op), tf_features
Example #20
Source File: upper_body_feature_extractor_common.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def build_network(batch_size, is_training):
    # input
    tf_raw_image_data = tf.placeholder(tf.string, shape=(batch_size,))
    tf_body_bbox = tf.placeholder(tf.int32, shape=(batch_size, 4))
    tf_labels = tf.placeholder(tf.int32, shape=(batch_size,))

    # pre-processing pipeline
    crops = []
    for i in range(batch_size):
        image = tf.image.decode_jpeg(tf_raw_image_data[i], channels=3)
        body_crop = tf.image.crop_to_bounding_box(image, tf_body_bbox[i, 1], tf_body_bbox[i, 0], tf_body_bbox[i, 3],
                                                  tf_body_bbox[i, 2])
        processed_crop = inception_preprocessing.preprocess_image(body_crop, image_size, image_size,
                                                                  is_training=is_training)
        crops.append(processed_crop)
    processed_images = tf.stack(crops)

    # training pipeline
    with slim.arg_scope(inception.inception_v3_arg_scope()):
        _, endpoints = inception.inception_v3(processed_images, num_classes=num_identity, is_training=is_training)

    # load model parameters
    init_fn = slim.assign_from_checkpoint_fn(os.path.join(checkpoints_dir, checkpoint_name),
                                             slim.get_model_variables(original_variable_namescope))

    net_before_pool = tf.reshape(endpoints['Mixed_7c'], shape=(batch_size, -1))
    net_before_pool_frozen = tf.stop_gradient(net_before_pool)
    tf_features = slim.fully_connected(net_before_pool_frozen, feature_length, activation_fn=None)
    tf_features_normalized = tf.nn.l2_normalize(tf_features, dim=1)
    tf_loss = coco_loss_layer(tf_features_normalized, tf_labels, batch_size)

    # optimizer
    tf_lr = tf.placeholder(dtype=tf.float32, shape=(), name='learning_rate')
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
    train = optimizer.minimize(tf_loss)

    # summary
    tf.summary.scalar('coco_loss', tf_loss)
    summary_op = tf.summary.merge_all()

    return (tf_raw_image_data, tf_body_bbox, tf_labels), (init_fn, tf_loss, tf_lr, train, summary_op), tf_features
Example #21
Source File: inception_v3_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #22
Source File: inception_v3_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def testNoBatchNormScaleByDefault(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3(inputs, num_classes, is_training=False)

    self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
Example #23
Source File: inception_v3_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def testBatchNormScale(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(
        inception.inception_v3_arg_scope(batch_norm_scale=True)):
      inception.inception_v3(inputs, num_classes, is_training=False)

    gamma_names = set(
        v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
    self.assertGreater(len(gamma_names), 0)
    for v in tf.global_variables('.*/BatchNorm/moving_mean:0$'):
      self.assertIn(v.op.name[:-len('moving_mean')] + 'gamma', gamma_names)
Example #24
Source File: inception_v3_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random.uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #25
Source File: inception_v3_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def testNoBatchNormScaleByDefault(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3(inputs, num_classes, is_training=False)

    self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
Example #26
Source File: inception_v3_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def testBatchNormScale(self):
    height, width = 299, 299
    num_classes = 1000
    inputs = tf.placeholder(tf.float32, (1, height, width, 3))
    with slim.arg_scope(
        inception.inception_v3_arg_scope(batch_norm_scale=True)):
      inception.inception_v3(inputs, num_classes, is_training=False)

    gamma_names = set(
        v.op.name
        for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
    self.assertGreater(len(gamma_names), 0)
    for v in tf.global_variables('.*/BatchNorm/moving_mean:0$'):
      self.assertIn(v.op.name[:-len('moving_mean')] + 'gamma', gamma_names)
Example #27
Source File: inception_v3_test.py    From Non-Targeted-Adversarial-Attacks with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #28
Source File: inception_v3_test.py    From motion-rcnn with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #29
Source File: inception_v3_test.py    From mtl-ssl with Apache License 2.0 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)
Example #30
Source File: inception_v3_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      inception.inception_v3_base(inputs)
    total_params, _ = slim.model_analyzer.analyze_vars(
        slim.get_model_variables())
    self.assertAlmostEqual(21802784, total_params)