Extract the images into a numpy array. Args: filename: The path to an MNIST images file. num_images: The number of images in the file. R

Extract the labels into a vector of int64 label IDs. Args: filename: The path to an MNIST labels file. num_labels: The number of labels in

Build a list of human-readable labels. Args: synsets: list of strings; each string is a unique WordNet ID. synset_to_human: dict of synset

Find the bounding boxes for a given image file. Args: filenames: list of strings; each string is a path to an image file. image_to_bboxes:

Build a list of all images files and labels in the data set. Args: data_dir: string, path to the root directory of images. Assumes that

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

Returns a list of filenames and inferred class names. Args: dataset_dir: A directory containing a set of subdirectories representing clas

Returns a function run by the chief worker to warm-start the training. Note that the init_fn is only run when initializing the model during the ver

Returns a list of variables to train. Returns: A list of variables to train by the optimizer.

Stem used for models trained on ImageNet.

Determine if file contains a CMYK JPEG format image. Args: filename: string, path of the image file. Returns: boolean indicating if the

Determine if a file contains a PNG format image. Args: filename: string, path of the image file. Returns: boolean indicating if the imag

Takes in operation name and returns meta information. An example would be 'separable_3x3_4' -> (3, 4). Args: operation: String that correspo

Parses the pooling operation string to return its type and shape.

Takes in the operation string and returns the pooling kernel shape.

Takes in the operation string and returns the pooling type.

Compute losses and gradients for a single clone. Args: optimizer: A tf.Optimizer object. clone: A Clone namedtuple. num_clones: The nu

Parses operation and performs the correct pooling operation on net.

Process a single image file. Args: filename: string, path to an image file e.g., '/path/to/example.JPG'. coder: instance of ImageCoder to p

Process and save list of images as TFRecord of Example protos. Args: name: string, unique identifier specifying the data set filenames: lis

Crops the given list of images. The function applies the same crop to each image in the list. This can be effectively applied when there are mult

Matches dimension of prev_layer to the curr_layer.

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

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

A plain ResNet without extra layers before or after the ResNet blocks.

A plain ResNet without extra layers before or after the ResNet blocks.

Computes new shape with the smallest side equal to `smallest_side`. Computes new shape with the smallest side equal to `smallest_side` while pres

A simplified ResNet Block stacker without output stride control.

A simplified ResNet Block stacker without output stride control.

Takes in an operations and parses it to the correct sep operation.

Calculate the sum gradient for each shared variable across all clones. This function assumes that the clone_grads has been scaled appropriately by

:param record_file: record文件路径 :param resize_height: :param resize_width: :return: :PS:image_batch, label_batch一般作为网络的输入

Builds the 8x8 resnet block.

Builds Inception-A block for Inception v4 network.

Builds Inception-B block for Inception v4 network.

Builds Inception-C block for Inception v4 network.

Builds Reduction-A block for Inception v4 network.

Builds Reduction-B block for Inception v4 network.

Build the mobilenet_v1 model for evaluation. Returns: g: graph with rewrites after insertion of quantization ops and batch norm folding.

Builds graph for model to train with rewrites for quantization. Returns: g: Graph with fake quantization ops and batch norm folding suitable fo

Creates multiple clones according to config using a `model_fn`. The returned values of `model_fn(*args, **kwargs)` are collected along with the s

Create a dict mapping label id to human readable string. Returns: labels_to_names: dictionary where keys are integers from to 1000 and

Distort the color of a Tensor image. Each color distortion is non-commutative and thus ordering of the color ops matters. Ideally we would random

Generates cropped_image using a one of the bboxes randomly distorted. See `tf.image.sample_distorted_bounding_box` for more documentation. Args:

Drops out a whole example hiddenstate with the specified probability.

Evaluates mobilenet_v1.

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

:param pb_path:pb文件的路径 :param image_path:测试图片的路径 :return:

Converts all variables in a graph and checkpoint into constants.

Returns the checkpoint init_fn if the checkpoint is provided.

Applies avg pool to produce 1x1 output. NOTE: This function is funcitonally equivalenet to reduce_mean, but it has baked in average pool which ha

Data reader for imagenet. Reads in imagenet data and performs pre-processing on the images. Args: is_training: bool specifying if train or

Data reader for imagenet. Reads in imagenet data and performs pre-processing on the images. Args: is_training: bool specifying if train or

Inception model from http://arxiv.org/abs/1602.07261. Constructs an Inception Resnet v2 network from inputs to the given final endpoint. This me

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

Inception v2 (6a2). Constructs an Inception v2 network from inputs to the given final endpoint. This method can construct the network up to the l

Inception model from http://arxiv.org/abs/1512.00567. Constructs an Inception v3 network from inputs to the given final endpoint. This method can

Creates the Inception V4 network up to the given final endpoint. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. final_e

Large ImageNet configuration based on PNASNet-5.

载图txt文件，文件中每行为一个图片信息，且以空格隔开：图像路径 标签1 标签2，如：test_image/1.jpg 0 2 :param filename: :param labels_num :labels个数 :param shuffle :是否打乱顺序

Specify the metrics for eval. Args: logits: Logits output from the graph. labels: Ground truth labels for inputs. Returns: Eval Op

Mobile ImageNet configuration based on PNASNet-5.

Creates mobilenet V2 network. Inference mode is created by default. To create training use training_scope below. with tf.contrib.slim.arg_scop

Mobilenet base network. Constructs a network from inputs to the given final endpoint. By default the network is constructed in inference mode. To

Mobilenet v1. Constructs a Mobilenet v1 network from inputs to the given final endpoint. Args: inputs: a tensor of shape [batch_size, height

Compute clone losses and gradients for the given list of `Clones`. Note: The regularization_losses are added to the first clone losses. Args:

Prepare one image for evaluation. If height and width are specified it would output an image with that size by applying resize_bilinear. If ce

Preprocesses the given image for evaluation. Args: image: A `Tensor` representing an image of arbitrary size. output_height: The height of

Preprocesses the given image for evaluation. Args: image: A `Tensor` representing an image of arbitrary size. output_height: The height of

Distort one image for training a network. Distorting images provides a useful technique for augmenting the data set during training in order to m

Preprocesses the given image for training. Note that the actual resizing scale is sampled from [`resize_size_min`, `resize_size_max`]. Args:

Preprocesses the given image for training. Note that the actual resizing scale is sampled from [`resize_size_min`, `resize_size_max`]. Args:

Replaces variable values in the checkpoint with their moving averages. If the current checkpoint has shadow variables maintaining moving averages

循环迭代训练过程 :param train_op: 训练op :param loss: loss函数 :param accuracy: 准确率函数 :param train_images_batch: 训练images数据 :param tr

循环迭代训练过程 :param train_op: 训练op :param loss: loss函数 :param accuracy: 准确率函数 :param train_images_batch: 训练images数据 :param tr

循环迭代训练过程 :param train_op: 训练op :param loss: loss函数 :param accuracy: 准确率函数 :param train_images_batch: 训练images数据 :param tr

循环迭代训练过程 :param train_op: 训练op :param loss: loss函数 :param accuracy: 准确率函数 :param train_images_batch: 训练images数据 :param tr