Python tensorflow.contrib方法代码示例

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def __depthwise_conv2d_p(name, x, w=None, kernel_size=(3, 3), padding='SAME', stride=(1, 1),
                         initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0):
    with tf.variable_scope(name):
        stride = [1, stride[0], stride[1], 1]
        kernel_shape = [kernel_size[0], kernel_size[1], x.shape[-1], 1]

        with tf.name_scope('layer_weights'):
            if w is None:
                w = __variable_with_weight_decay(kernel_shape, initializer, l2_strength)
            __variable_summaries(w)
        with tf.name_scope('layer_biases'):
            if isinstance(bias, float):
                bias = tf.get_variable('biases', [x.shape[-1]], initializer=tf.constant_initializer(bias))
            __variable_summaries(bias)
        with tf.name_scope('layer_conv2d'):
            conv = tf.nn.depthwise_conv2d(x, w, stride, padding)
            out = tf.nn.bias_add(conv, bias)

    return out 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def depthwise_conv2d(name, x, w=None, kernel_size=(3, 3), padding='SAME', stride=(1, 1),
                     initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0, activation=None,
                     batchnorm_enabled=False, is_training=True):
    """Implementation of depthwise 2D convolution wrapper"""
    with tf.variable_scope(name) as scope:
        conv_o_b = __depthwise_conv2d_p(name=scope, x=x, w=w, kernel_size=kernel_size, padding=padding,
                                        stride=stride, initializer=initializer, l2_strength=l2_strength, bias=bias)

        if batchnorm_enabled:
            conv_o_bn = tf.layers.batch_normalization(conv_o_b, training=is_training)
            if not activation:
                conv_a = conv_o_bn
            else:
                conv_a = activation(conv_o_bn)
        else:
            if not activation:
                conv_a = conv_o_b
            else:
                conv_a = activation(conv_o_b)
    return conv_a 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def depthwise_separable_conv2d(name, x, w_depthwise=None, w_pointwise=None, width_multiplier=1.0, num_filters=16,
                               kernel_size=(3, 3),
                               padding='SAME', stride=(1, 1),
                               initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, biases=(0.0, 0.0),
                               activation=None, batchnorm_enabled=True,
                               is_training=True):
    """Implementation of depthwise separable 2D convolution operator as in MobileNet paper"""
    total_num_filters = int(round(num_filters * width_multiplier))
    with tf.variable_scope(name) as scope:
        conv_a = depthwise_conv2d('depthwise', x=x, w=w_depthwise, kernel_size=kernel_size, padding=padding,
                                  stride=stride,
                                  initializer=initializer, l2_strength=l2_strength, bias=biases[0],
                                  activation=activation,
                                  batchnorm_enabled=batchnorm_enabled, is_training=is_training)

        conv_o = conv2d('pointwise', x=conv_a, w=w_pointwise, num_filters=total_num_filters, kernel_size=(1, 1),
                        initializer=initializer, l2_strength=l2_strength, bias=biases[1], activation=activation,
                        batchnorm_enabled=batchnorm_enabled, is_training=is_training)

    return conv_a, conv_o


############################################################################################################
# Fully Connected layer Methods 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def dense_p(name, x, w=None, output_dim=128, initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0,
            bias=0.0):
    """
    Fully connected layer
    :param name: (string) The name scope provided by the upper tf.name_scope('name') as scope.
    :param x: (tf.tensor) The input to the layer (N, D).
    :param output_dim: (integer) It specifies H, the output second dimension of the fully connected layer [ie:(N, H)]
    :param initializer: (tf.contrib initializer) The initialization scheme, He et al. normal or Xavier normal are recommended.
    :param l2_strength:(weight decay) (float) L2 regularization parameter.
    :param bias: (float) Amount of bias. (if not float, it means pretrained bias)
    :return out: The output of the layer. (N, H)
    """
    n_in = x.get_shape()[-1].value
    with tf.variable_scope(name):
        if w == None:
            w = variable_with_weight_decay([n_in, output_dim], initializer, l2_strength)
        variable_summaries(w)
        if isinstance(bias, float):
            bias = tf.get_variable("layer_biases", [output_dim], tf.float32, tf.constant_initializer(bias))
        variable_summaries(bias)
        output = tf.nn.bias_add(tf.matmul(x, w), bias)
        return output 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def __depthwise_conv2d_atrous_p(name, x, w=None, kernel_size=(3, 3), padding='SAME', stride=(1, 1),
                         initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0,
                         dilation_factor= 1):
    with tf.variable_scope(name):
        stride = [1, stride[0], stride[1], 1]
        kernel_shape = [kernel_size[0], kernel_size[1], x.shape[-1], 1]

        with tf.name_scope('layer_weights'):
            if w == None:
                w = variable_with_weight_decay(kernel_shape, initializer, l2_strength)
            variable_summaries(w)
        with tf.name_scope('layer_biases'):
            if isinstance(bias, float):
                bias = tf.get_variable('biases', [x.shape[-1]], initializer=tf.constant_initializer(bias))
            variable_summaries(bias)
        with tf.name_scope('layer_conv2d'):
            conv = tf.nn.depthwise_conv2d(x, w, stride, padding, [dilation_factor, dilation_factor])
            out = tf.nn.bias_add(conv, bias)

    return out 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def depthwise_conv2d(name, x, w=None, kernel_size=(3, 3), padding='SAME', stride=(1, 1),dilation_factor=1,
                     initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0, activation=None,
                     batchnorm_enabled=False, is_training=True):
    with tf.variable_scope(name) as scope:
        if dilation_factor>1:
             conv_o_b = __depthwise_conv2d_atrous_p(name=scope, x=x, w=w, kernel_size=kernel_size, padding=padding,
                                        stride=stride, initializer=initializer, l2_strength=l2_strength, bias=bias,
                                        dilation_factor= dilation_factor)
        else:
            conv_o_b = __depthwise_conv2d_p(name=scope, x=x, w=w, kernel_size=kernel_size, padding=padding,
                                        stride=stride, initializer=initializer, l2_strength=l2_strength, bias=bias)

        if batchnorm_enabled:
            conv_o_bn = tf.layers.batch_normalization(conv_o_b, training=is_training)
            if not activation:
                conv_a = conv_o_bn
            else:
                conv_a = activation(conv_o_bn)
        else:
            if not activation:
                conv_a = conv_o_b
            else:
                conv_a = activation(conv_o_b)
    return conv_a 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def depthwise_separable_conv2d(name, x, w_depthwise=None, w_pointwise=None, width_multiplier=1.0, num_filters=16,
                               kernel_size=(3, 3),
                               padding='SAME', stride=(1, 1),
                               initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, biases=(0.0, 0.0),
                               activation=None, batchnorm_enabled=True,
                               is_training=True):
    total_num_filters = int(round(num_filters * width_multiplier))
    with tf.variable_scope(name) as scope:
        conv_a = depthwise_conv2d('depthwise', x=x, w=w_depthwise, kernel_size=kernel_size, padding=padding,
                                  stride=stride,
                                  initializer=initializer, l2_strength=l2_strength, bias=biases[0],
                                  activation=activation,
                                  batchnorm_enabled=batchnorm_enabled, is_training=is_training)

        conv_o = conv2d('pointwise', x=conv_a, w=w_pointwise, num_filters=total_num_filters, kernel_size=(1, 1),
                        initializer=initializer, l2_strength=l2_strength, bias=biases[1], activation=activation,
                        batchnorm_enabled=batchnorm_enabled, is_training=is_training)

    return conv_o 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def depthwise_conv2d(name, x, w=None, kernel_size=(3, 3), padding='SAME', stride=(1, 1),
                     initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0, activation=None,
                     batchnorm_enabled=False, is_training=True):
    with tf.variable_scope(name) as scope:
        conv_o_b = __depthwise_conv2d_p(name='conv', x=x, w=w, kernel_size=kernel_size, padding=padding,
                                        stride=stride, initializer=initializer, l2_strength=l2_strength, bias=bias)

        if batchnorm_enabled:
            conv_o_bn = tf.layers.batch_normalization(conv_o_b, training=is_training, epsilon=1e-5)
            if not activation:
                conv_a = conv_o_bn
            else:
                conv_a = activation(conv_o_bn)
        else:
            if not activation:
                conv_a = conv_o_b
            else:
                conv_a = activation(conv_o_b)
    return conv_a


############################################################################################################
# ShuffleNet unit methods 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def inception_score(images, num_batches=None):
  """IS function from tf.contrib

  Args:
      images: must be 4-D tensor, ranges from [0, 255]
      num_batches: Number of batches to split `generated_images` in to in
        order to efficiently run them through the classifier network.
  """
  batches = images.shape[0]
  if not num_batches:
    num_batches = (batches + _INCEPTION_BATCH - 1) // _INCEPTION_BATCH
  graph = _TFGAN.get_graph_def_from_url_tarball(
    'http://download.tensorflow.org/models/frozen_inception_v1_2015_12_05.tar.gz',
    'inceptionv1_for_inception_score.pb',
    '/tmp/frozen_inception_v1_2015_12_05.tar.gz')
  return _TFGAN.classifier_score(
    images=images,
    classifier_fn=partial(_run_inception,
                          layer_name='logits:0',
                          inception_graph=graph),
    num_batches=num_batches) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def __conv2d_p(name, x, w=None, num_filters=16, kernel_size=(3, 3), padding='SAME', stride=(1, 1),
               initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0):
    """
    Convolution 2D Wrapper
    :param name: (string) The name scope provided by the upper tf.name_scope('name') as scope.
    :param x: (tf.tensor) The input to the layer (N, H, W, C).
    :param w: (tf.tensor) pretrained weights (if None, it means no pretrained weights)
    :param num_filters: (integer) No. of filters (This is the output depth)
    :param kernel_size: (integer tuple) The size of the convolving kernel.
    :param padding: (string) The amount of padding required.
    :param stride: (integer tuple) The stride required.
    :param initializer: (tf.contrib initializer) The initialization scheme, He et al. normal or Xavier normal are recommended.
    :param l2_strength:(weight decay) (float) L2 regularization parameter.
    :param bias: (float) Amount of bias. (if not float, it means pretrained bias)
    :return out: The output of the layer. (N, H', W', num_filters)
    """
    with tf.variable_scope(name):
        stride = [1, stride[0], stride[1], 1]
        kernel_shape = [kernel_size[0], kernel_size[1], x.shape[-1], num_filters]

        with tf.name_scope('layer_weights'):
            if w == None:
                w = __variable_with_weight_decay(kernel_shape, initializer, l2_strength)
            __variable_summaries(w)
        with tf.name_scope('layer_biases'):
            if isinstance(bias, float):
                bias = tf.get_variable('biases', [num_filters], initializer=tf.constant_initializer(bias))
            __variable_summaries(bias)
        with tf.name_scope('layer_conv2d'):
            conv = tf.nn.conv2d(x, w, stride, padding)
            out = tf.nn.bias_add(conv, bias)

    return out 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def test_forward_inception_v1():
    '''test inception V1 model'''
    with tf.Graph().as_default():
        graph_def = nnvm.testing.tf.get_workload("InceptionV1/classify_image_graph_def-with_shapes.pb")
        # Call the utility to import the graph definition into default graph.
        graph_def = nnvm.testing.tf.ProcessGraphDefParam(graph_def)

        # Build an image from random data.
        from PIL import Image
        from tvm.contrib import util

        img_array = np.random.uniform(size=(1, 600, 600, 3)).astype("uint8")
        img = Image.frombuffer('RGB', (600, 600), img_array.tostring(), 'raw', 'RGB', 0, 1)
        temp = util.tempdir()
        img_path = temp.relpath("tf-test.jpg")
        img.save(img_path);

        import os.path
        if not tf.gfile.Exists(os.path.join(img_path)):
            tf.logging.fatal('File does not exist %s', image)
        data = tf.gfile.FastGFile(os.path.join(img_path), 'rb').read()

        temp.remove()

        # Extract tensorflow decoded image frame for tvm input
        with tf.Session() as sess:
            tvm_data = run_tf_graph(sess, data, 'DecodeJpeg/contents:0', 'DecodeJpeg:0')

        with tf.Session() as sess:
            tf_output = run_tf_graph(sess, data, 'DecodeJpeg/contents:0', 'softmax:0')
            tvm_output = run_tvm_graph(graph_def, tvm_data, 'DecodeJpeg/contents')
            np.testing.assert_allclose(tf_output, tvm_output, rtol=1e-5, atol=1e-5)

#######################################################################
# Mobilenet
# --------- 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def testContrib(self):
    # pylint: disable=g-import-not-at-top
    import tensorflow as tf
    _ = tf.contrib.layers  # `tf.contrib` is loaded lazily on first use.
    assert inspect.ismodule(tf.contrib) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def testLayers(self):
    # pylint: disable=g-import-not-at-top
    import tensorflow as tf
    assert inspect.ismodule(tf.contrib.layers) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def testLinearOptimizer(self):
    # pylint: disable=g-import-not-at-top
    import tensorflow as tf
    assert inspect.ismodule(tf.contrib.linear_optimizer) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import contrib [as 别名]
def serve(self, config, model_path, gpuid=0):
        v1_export_dir = os.path.join(model_path, _V1_SAVED_MODEL_DIR)
        if os.path.exists(v1_export_dir):
            raise ValueError('SavedModel exported with OpenNMT-tf 1.x are no longer supported. '
                             'They include ops from tf.contrib which is not included in '
                             'TensorFlow 2.x binaries. To upgrade automatically, you can release '
                             'or serve from a OpenNMT-tf 1.x training checkpoint.')
        export_dir = os.path.join(model_path, _SAVED_MODEL_DIR)
        translate_fn = tf.saved_model.load(export_dir).signatures['serving_default']
        return None, translate_fn