Performs central crops of the given image list. Args: image: a 3-D image tensor crop_height: the height of the image following the crop.

Crops the given image to a random part of the image, and randomly flips. Args: image: a 3-D image tensor crop_height: the new height. c

Bottleneck block variant for residual networks with BN before convolutions. Args: inputs: A tensor of size [batch, channels, height_in, width_i

Standard building block for residual networks with BN before convolutions. Args: inputs: A tensor of size [batch, channels, height_in, width_in

DESCRIPTION: function which selects images for manual annotation based on their entropy. The higher the entropy o

Compute the mean and std value of dataset.

Our model_fn for ResNet to be used with our Estimator.

Our model_fn for ResNet to be used with our Estimator.

Init layer parameters.

Input function which provides batches for train or eval. Args: is_training: A boolean denoting whether the input is for training. data_dir:

Input function which provides batches for train or eval. Args: is_training: A boolean denoting whether the input is for training. data_dir:

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

Checks if a file is an allowed image extension. Args: filename (string): path to a file Returns: bool: True if the filename en

select nb_idx indices among im_list_idx and return them in im_selection (list) : the minimal distance between two selected images is maximi

Get a learning rate that decays step-wise as training progresses. Args: batch_size: the number of examples processed in each training batch.

PARAMETERS: dataset_dir - directory which contains dataset related information al_budget - int which gives the ac

Parses a record containing a training example of an image. The input record is parsed into a label and image, and the image is passed through pre

Parses a record containing a training example of an image. The input record is parsed into a label and image, and the image is passed through pre

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

Given a Dataset with raw records, parse each record into images and labels, and return an iterator over the records. Args: dataset: A Da

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-152 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Shared functionality for different resnet model_fns. Initializes the ResnetModel representing the model layers and uses that model to build the n