Builds a SequenceExample proto for an image-caption pair. Args: image: An ImageMetadata object. decoder: An ImageDecoder object. vocab:

Calculate the total loss on a single tower running the ImageNet model. We perform 'batch splitting'. This means that we cut up a batch across mul

Computes the precision@k for the specified values of k

Add two numbers represented as lower-endian digit lists.

Sets the learning rate to the initial LR decayed by 10 every 30 epochs

Create animation for the given data (hacky matplotlib use).

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.

Builds the inference graph from a configuration object. Args: model_config: Object containing configuration for building the model. c

Builds the image model subgraph and generates image embeddings. Inputs: self.images Outputs: self.image_embeddings

Input prefetching, preprocessing and batching. Outputs: self.images self.input_seqs self.target_seqs (training and eval only)

Builds the model. Inputs: self.image_embeddings self.seq_embeddings self.target_seqs (training and eval only) self.input_

Builds the model for inference. Args: model_config: Object containing configuration for building the model. Returns: model: The

Builds the input sequence embeddings. Inputs: self.input_seqs Outputs: self.seq_embeddings

Apply convolutional dynamic neural advection to previous image. Args: prev_image: previous image to be transformed. cdna_input: hidden lyae

Create log and model folder

Compute the co-occurrence statistics from the text. This generates a temporary file for each shard that contains the intermediate counts from the

returns ~ Pr[outcome != winner]. Args: counts: a list of scores noise_eps: privacy parameter for noisy_max Returns: q: the probabilit

Convolutional GRU.

Reads submatrix shards from disk.

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 directory if doesn't exist :param dest_directory: :return: True if everything went well

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

Reads text lines and generates a vocabulary.

Decode a JPEG string into one 3-D float image Tensor. Args: image_buffer: scalar string Tensor. scope: Optional scope for op_scope. Retur

Return the topK results and new decoder states.

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

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

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

Perform random distortions on an image. Args: image: A float32 Tensor of shape [height, width, 3] with values in [0, 1). thread_id: Preproc

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

Apply dynamic neural advection to previous image. Args: prev_image: previous image to be transformed. dna_input: hidden lyaer to be used fo

Prints a download message for the Dataset.

Return the top states from encoder for decoder. Args: sess: tensorflow session. enc_inputs: encoder inputs of shape [batch_size, enc_

Given a dataset, a number of teachers, and some input data, this helper function queries each teacher for predictions on the data and returns a

Prepare one image for evaluation. Args: image: 3-D float Tensor height: integer width: integer scope: Optional scope for op_scope.

Eval loop.

Evaluate an existing model.

Computes perplexity-per-word over the evaluation dataset. Summaries and perplexity-per-word are written out to the eval directory. Args: ses

Extracts the CIFAR-10 dataset and return numpy arrays with the different sets :param local_url: where the tar.gz archive is located locally :pa

Read batches of input.

Gets the list of variables, filtered by scope and/or suffix. Args: scope: an optional scope for filtering the variables to return. suffix:

Checks whether a func has been decorated with @add_arg_scope or not. Args: func: function to check. Returns: a boolean.

Returns the word string of an integer word id.

Decode and preprocess one image for evaluation or training. Args: image_buffer: JPEG encoded string Tensor bbox: 3-D float Tensor of boundi

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