Get parameter name by concatenating the prefix and the original name.

Gets the start end bytes of the given chars in the given text.

Constructs a python tensor flow model defined by model_spec. Args: input_pattern: File pattern of the data in tfrecords of Example. model_s

Return -1 or the smallest Unicode char greater than c for which the CharProperty holds. Expects c == -1 or HoldsFor(c).

Retrieves the next word from the input stream, treating words as simply being delimited by whitespace. Returns true if this is the end of a "sentence

Returns number of embedding spaces.

Reads up to the first empty line and returns false end of file is reached.

Rewinds the corpus reader.

Create a UnicodeText from a UTF-8 string or buffer. If do_copy is true, then a copy of the string is made. The copy is owned by the resulting Unicode

Create an empty workspace.

Adds an op capable of reading sentences and parsing them with a beam.

Returns a learning rate that decays by 0.96 every decay_steps. Args: initial_learning_rate: initial value of the learning rate decay_

Sort the hyps based on log probs and length. Args: hyps: A list of hypothesis. Returns: hyps: A list of sorted hypothesis in reve

Adds a sequence of beam parsing steps.

Extract text for a feature from td.Example. Args: ex: tf.Example. key: key of the feature to be extracted. Returns: feature

Returns the union of two lists. Python sets can have a non-deterministic iteration order. In some contexts, this could lead to TensorFlow produci

Returns the non-linearity function pointer for the given string code. For forwards compatibility, allows the full names for stand-alone non-l

Calculate the running average of losses.

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_

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

Wrapper for inserting a bytes Feature into a SequenceExample proto.

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

Creates a function that restores a model from checkpoint. Args: checkpoint_path: Checkpoint file or a directory containing a checkpoint

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

Compute 0 to t-th differential moments for Gaussian variable. E[(P(x+s)/P(x+s-1)-1)^t] = sum_{i=0}^t (t choose i) (-1)^{t-i} E[(P(x+s)/

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

This helper function declares a TF placeholder for the graph input data :return: TF placeholder for the graph input data

Wrapper for inserting an int64 Feature into a SequenceExample proto.

Loads image metadata from a JSON file and processes the captions. Args: captions_file: JSON file containing caption annotations. image_dir:

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

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

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

Computes the precision@k for the specified values of k

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 the list of available subsets.

Contruct batches of training or evaluation examples from the image dataset. Args: dataset: instance of Dataset class specifying the dataset.

Adds a Batch Normalization layer. Args: inputs: a tensor of size [batch_size, height, width, channels] or [batch_size, channels].

Runs beam search caption generation on a single image. Args: sess: TensorFlow Session object. encoded_image: An encoded image string.

Build a whole graph for the model.

Create input tfrecord tensors. Args: training: training or validation data. Returns: list of tensors corresponding to images, actions, an

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

In a sparse batch of ints, make 1.0 if it's 0 and 0.0 else.

Build convolutional lstm video predictor using STP, CDNA, or DNA. Args: images: tensor of ground truth image sequences actions: tensor of a

Returns/sets the feature function descriptor.

Creates and initializes the embedding tensors.

Extracts all elements from the TopN. This is a destructive operation. The only method that can be called immediately after extract() is reset().

Extract the images into a 4D tensor [image index, y, x, channels]. Values are rescaled from [0, 255] down to [-0.5, 0.5].

Extract the labels into a vector of int64 label IDs.

Returns/sets the feature extractor this function belongs to.

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

Build the CNN model. Args: images: Images returned from distorted_inputs() or inputs(). dropout: Boolean controling whether to use dropout o

Build a deeper CNN model. Args: images: Images returned from distorted_inputs() or inputs(). dropout: Boolean controling whether to use drop