Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None`

Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None`

Helper function for creating a resnet_v1 bottleneck block. Args: scope: The scope of the block. base_depth: The depth of the bottleneck lay

Helper function for creating a resnet_v2 bottleneck block. Args: scope: The scope of the block. base_depth: The depth of the bottleneck lay

A shallow and thin ResNet v1 for faster tests.

Name scope to create the clone. Args: clone_index: Int, representing the clone_index. Returns: A name_scope suitable for `tf.nam

统计tf_records图像的个数(example)个数 :param tf_records_filenames: tf_records文件路径 :return:

解析record文件:源文件的图像数据是RGB,uint8,[0,255],一般作为训练数据时,需要归一化到[0,1] :param filename: :param resize_height: :param resize_width: :param ty

A shallow and thin ResNet v2 for faster tests.

Device used to create the clone and all the ops inside the clone. Args: clone_index: Int, representing the clone_index. Returns:

:param images:图像 :param labels:标签 :param batch_size: :param labels_nums:标签个数 :param one_hot:是否将labels转为one_hot的形式 :param shuf

Device to use with the optimizer. Returns: A value suitable for `tf.device()`.

Device to use to build the inputs. Returns: A value suitable for `tf.device()`.

Returns the device to use for variables created inside the clone. Returns: A value suitable for `tf.device()`.

Wrapper for inserting bytes features into Example proto.

Returns the device to use for caching variables. Variables are cached on the worker CPU when using replicas. Returns: A device string

Wrapper for inserting int64 features into Example proto.

Find ops of a given type in graphdef or a graph. Args: optype: operation type (e.g. Conv2D) Returns: List of operations.

Pads the input along the spatial dimensions independently of input size. Pads the input such that if it was used in a convolution with 'VALID' padd

Wrapper for inserting float features into Example proto.

Generator for v1 ResNet models. This function generates a family of ResNet v1 models. See the resnet_v1_*() methods for specific model instantiat

Generator for v2 (preactivation) ResNet models. This function generates a family of ResNet v2 models. See the resnet_v2_*() methods for specific

Constructs a NASNet image model.

Check that generator can take small and non-square inputs.

Update hparams for given is_training option.

Returns a TF-Feature of int64s. Args: values: A scalar or list of values. Returns: A TF-Feature.

读取图片数据,默认返回的是uint8,[0,255] :param filename: :param resize_height: :param resize_width: :param normalization:是否归一化到[0.,1.0] :r

Returns `slim.arg_scope` with all None arguments removed. Arguments: funcs: Functions to pass to `arg_scope`. **kwargs: Arguments to pass t

Loads data from the binary MNIST files and writes files to a TFRecord. Args: data_filename: The filename of the MNIST images. labels_filena

Loads data from the cifar10 pickle files and writes files to a TFRecord. Args: filename: The filename of the cifar10 pickle file. tfrecord_

Applies the predicted conv operation to net.

Resize images preserving the original aspect ratio. Args: image: A 3-D image `Tensor`. smallest_side: A python integer or scalar `Tensor` i

Constructs a PNASNet image model.

Converts the given filenames to a TFRecord dataset. Args: split_name: The name of the dataset, either 'train' or 'validation'. filenames: A

Crops the given image using the provided offsets and sizes. Note that the method doesn't assume we know the input image size but it does assume w

Pads the input along the spatial dimensions independently of input size. Pads the input such that if it was used in a convolution with 'VALID' padd

Gather the loss for a single clone. Args: clone: A Clone namedtuple. num_clones: The number of clones being deployed. regularization_lo

Creates the output filename. Args: dataset_dir: The directory where the temporary files are stored. split_name: The name of the train/test

Creates the output filename. Args: dataset_dir: The dataset directory where the dataset is stored. split_name: The name of the train/test s

Subtracts the given means from each image channel. For example: means = [123.68, 116.779, 103.939] image = _mean_image_subtraction(image, m

Process a complete data set and save it as a TFRecord. Args: name: string, unique identifier specifying the data set. directory: string, ro

Returns the default blocks, scaled down to make test run faster.

Define kernel size which is automatically reduced for small input. If the shape of the input images is unknown at graph construction time this fu

Sets arg scope defaults for all items present in defaults. Args: defaults: dictionary/list of pairs, containing a mapping from function to

Evenly splits num, num_ways so each piece is a multiple of divisible_by.

Computes func(x, sel), with sel sampled from [0...num_cases-1]. Args: x: input Tensor. func: Python function to apply. num_cases: Pytho

Returns a TF-Feature of bytes. Args: values: A string. Returns: A TF-Feature.

实现将图像原始数据,label,长,宽等信息保存为record文件 注意:读取的图像数据默认是uint8,再转为tf的字符串型BytesList保存,解析请需要根据需要转换类型 :param image_dir:原始图像的目录 :param file:输入保存图片信

Reduces the shape of net without information loss due to striding.

实现遍历dir目录下,所有文件(包含子文件夹的文件) :param dir:指定文件夹目录 :return:包含所有文件的列表->list

显示图片 :param title: 图像标题 :param image: 图像的数据 :return:

Creates a split convolution. Split convolution splits the input and output into 'num_blocks' blocks of approximately the same size each, and on

保存txt数据 :param content:需要保存的数据,type->list :param filename:文件名 :param mode:读写模式:'w' or 'a' :return: void

Process a single XML file containing a bounding box.

Add histogram summaries to gradients. Note: The summaries are also added to the SUMMARIES collection. Args: grads_and_vars: A list of gradie

Adds output nodes. Adjust according to specified implementations. Adds the following nodes for output tensors: * classes: A float32

Apply drop_path regularization. Args: net: the Tensor that gets drop_path regularization applied. current_step: a float32 Tensor with

Auxiliary head used for all models across all datasets.

Build a lookup from image file to bounding boxes. Args: bounding_box_file: string, path to file with bounding boxes annotations. Assumes

Build the desired graph.

Build lookup for synset to human-readable label. Args: imagenet_metadata_file: string, path to file containing mapping from synset to hum

Runs the beginning of the conv cell before the predicted ops are run.

Performs central crops of the given image list. Args: image_list: a list of image tensors of the same dimension but possibly varying chan

Stem used for models trained on Cifar.

Removes temporary files used to create the dataset. Args: dataset_dir: The directory where the temporary files are stored.

Removes temporary files used to create the dataset. Args: dataset_dir: The directory where the temporary files are stored.

Removes temporary files used to create the dataset. Args: dataset_dir: The directory where the temporary files are stored.

Concatenate the unused hidden states of the cell.

Configures the learning rate. Args: num_samples_per_epoch: The number of samples in each epoch of training. global_step: The global_step te

Configures the optimizer used for training. Args: learning_rate: A scalar or `Tensor` learning rate. Returns: An instance of an optimize

Build an Example proto for an example. Args: filename: string, path to an image file, e.g., '/path/to/example.JPG' image_buffer: string, JP

Returns the default generator block definitions. Returns: A list of generator blocks.

Downloads MNIST locally. Args: dataset_dir: The directory where the temporary files are stored.