Subsamples the input along the spatial dimensions. Args: inputs: A `Tensor` of size [batch, height_in, width_in, channels]. factor: The sub

:param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的t

:param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的t

:param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的t

:param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的t

:param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的t

Trains mobilenet_v1.

Writes frozen graph to disk. Args: frozen_graph_path: Path to write inference graph. frozen_graph_def: tf.GraphDef holding frozen

Writes the graph and the checkpoint into disk.

Writes SavedModel to disk. If checkpoint_path is not None bakes the weights into the graph thereby eliminating the need of checkpoint files d

Runs the conv cell.

Create a DeploymentConfig. The config describes how to deploy a model across multiple clones and replicas. The model will be replicated `num

Downloads cifar10 and uncompresses it locally. Args: dataset_dir: The directory where the temporary files are stored.

Returns input that accepts a batch of PNG or JPEG strings. Returns: A tuple of input placeholder and the output decoded images.

Returns input placeholder and a 4-D uint8 image tensor.

Processes and saves list of images as TFRecord in 1 thread. Args: coder: instance of ImageCoder to provide TensorFlow image coding utils. t

AlexNet version 2. Described in: http://arxiv.org/pdf/1404.5997v2.pdf Parameters from: github.com/akrizhevsky/cuda-convnet2/blob/master/layers/

Builds the 17x17 resnet block.

Builds the 35x35 resnet block.

Bottleneck residual unit variant with BN after convolutions. This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for its def

Bottleneck residual unit variant with BN before convolutions. This is the full preactivation residual unit variant proposed in [2]. See Fig. 1(b)

Build NASNet model for the Cifar Dataset.

Build NASNet Large model for the ImageNet Dataset.

Build NASNet Mobile model for the ImageNet Dataset.

Build PNASNet Large model for the ImageNet Dataset.

Build PNASNet Mobile model for the ImageNet Dataset.

Figure out what layers should have reductions.

Creates a variant of the CifarNet model. Note that since the output is a set of 'logits', the values fall in the interval of (-infinity, infinity

Defines the default cifarnet argument scope. Args: weight_decay: The weight decay to use for regularizing the model. Returns: An `arg_sc

Allows data parallelism by creating multiple clones of network_fn.

Strided 2-D convolution with 'SAME' padding. When stride > 1, then we do explicit zero-padding, followed by conv2d with 'VALID' padding. Note

Returns a default argument scope for all generators and discriminators. Args: instance_norm_center: Whether instance normalization applies cent

Defines the cyclegan resnet network architecture. As closely as possible following https://github.com/junyanz/CycleGAN/blob/master/models/archite

Upsamples the given inputs. Args: net: A Tensor of size [batch_size, height, width, filters]. num_outputs: The number of output filters.

Deploys a Slim-constructed model across multiple clones. The deployment options are specified by the config object and support deploying one or s

Discriminator network for DCGAN. Construct discriminator network from inputs to the final endpoint. Args: inputs: A tensor of size [batch_si

解析record文件，并显示show_nums张图片，主要用于验证生成record文件是否成功 :param tfrecord_file: record文件路径 :return:

Downloads the `tarball_url` and uncompresses it locally. Args: tarball_url: The URL of a tarball file. dataset_dir: The directory where the

Depthwise Convolution Block with expansion. Builds a composite convolution that has the following structure expansion (1x1) -> depthwise (kernel_

Exports inference graph for the desired graph. Args: input_type: Type of input for the graph. Can be one of ['image_tensor',

Returns a TF-Feature of floats. Args: values: A scalar of list of values. Returns: A TF-Feature.

:param input_checkpoint: :param output_graph: PB模型保存路径 :return:

Generator network for DCGAN. Construct generator network from inputs to the final endpoint. Args: inputs: A tensor with any size N. [batch_s

Given a dataset name and a split_name returns a Dataset. Args: name: String, the name of the dataset. split_name: A train/test split name.

Returns a network_fn such as `logits, end_points = network_fn(images)`. Args: name: The name of the network. num_classes: The number of cla

Returns preprocessing_fn(image, height, width, **kwargs). Args: name: The name of the preprocessing function. is_training: `True` if the mo

Gets a dataset tuple with instructions for reading ImageNet. Args: split_name: A train/test split name. dataset_dir: The base directory of

Gets a dataset tuple with instructions for reading cifar10. Args: split_name: A train/test split name. dataset_dir: The base directory of t

Gets a dataset tuple with instructions for reading flowers. Args: split_name: A train/validation split name. dataset_dir: The base director

Gets a dataset tuple with instructions for reading MNIST. Args: split_name: A train/test split name. dataset_dir: The base directory of the

Average pool away the height and width spatial dimensions of x.

Specifies whether or not the dataset directory contains a label map file. Args: dataset_dir: The directory in which the labels file is found.

Defines the default arg scope for inception models. Args: weight_decay: The weight decay to use for regularizing the model. use_batch_norm:

Creates the Inception Resnet V2 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. Dimension batch_size may be und

Returns the scope with the default parameters for inception_resnet_v2. Args: weight_decay: the weight decay for weights variables. batch_no

Defines the Inception V1 architecture. This architecture is defined in: Going deeper with convolutions Christian Szegedy, Wei Liu, Yangqin

Inception v2 model for classification. Constructs an Inception v2 network for classification as described in http://arxiv.org/abs/1502.03167.

Inception model from http://arxiv.org/abs/1512.00567. "Rethinking the Inception Architecture for Computer Vision" Christian Szegedy, Vincent Van

Creates the Inception V4 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. num_classes: number of predicted classes

Creates a variant of the LeNet model. Note that since the output is a set of 'logits', the values fall in the interval of (-infinity, infinity).

Defines the default lenet argument scope. Args: weight_decay: The weight decay to use for regularizing the model. Returns: An `arg_scope

Mobilenet model for classification, supports both V1 and V2. Note: default mode is inference, use mobilenet.training_scope to create training net

Creates base of the mobilenet (no pooling and no logits) .

Mobilenet v1 model for classification. Args: inputs: a tensor of shape [batch_size, height, width, channels]. num_classes: number of predic