Defines the default MobilenetV1 arg scope. Args: is_training: Whether or not we're training the model. If this is set to None, the parame

Defines the default arg scope for the NASNet-A Cifar model. Args: weight_decay: The weight decay to use for regularizing the model. batch_n

Defines the default arg scope for the NASNet-A Large ImageNet model. Args: weight_decay: The weight decay to use for regularizing the model.

Defines the default arg scope for the NASNet-A Mobile ImageNet model. Args: weight_decay: The weight decay to use for regularizing the model.

Contains the model definition for the OverFeat network. The definition for the network was obtained from: OverFeat: Integrated Recognition, Loc

Returns a default argument scope for isola_net. Returns: An arg scope.

Creates the Image2Image Translation Discriminator. Args: net: A `Tensor` of size [batch_size, height, width, channels] representing the i

Defines the network architecture. Args: net: A `Tensor` of size [batch, height, width, channels]. Note that the generator currently requi

Default arg scope for the PNASNet Large ImageNet model.

Default arg scope for the PNASNet Mobile ImageNet model.

Pre-process one image for training or evaluation. Args: image: 3-D Tensor [height, width, channels] with the image. If dtype is tf.float3

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

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

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

Reads the labels file and returns a mapping from ID to class name. Args: dataset_dir: The directory in which the labels file is found. file

Defines the default ResNet arg scope. TODO(gpapan): The batch-normalization related default values above are appropriate for use in conjunction

ResNet-101 model of [1]. See resnet_v1() for arg and return description.

ResNet-152 model of [1]. See resnet_v1() for arg and return description.

ResNet-200 model of [2]. See resnet_v1() for arg and return description.

ResNet-50 model of [1]. See resnet_v1() for arg and return description.

ResNet-101 model of [1]. See resnet_v2() for arg and return description.

ResNet-152 model of [1]. See resnet_v2() for arg and return description.

ResNet-200 model of [2]. See resnet_v2() for arg and return description.

ResNet-50 model of [1]. See resnet_v2() for arg and return description.

Runs the download and conversion operation. Args: dataset_dir: The dataset directory where the dataset is stored.

Runs the download and conversion operation. Args: dataset_dir: The dataset directory where the dataset is stored.

Runs the download and conversion operation. Args: dataset_dir: The dataset directory where the dataset is stored.

Separable mobilenet V1 style convolution. Depthwise convolution, with default non-linearity, followed by 1x1 depthwise convolution. This is simi

Stacks ResNet `Blocks` and controls output feature density. First, this function creates scopes for the ResNet in the form of 'block_name/unit_1'

Verify dense feature extraction with atrous convolution.

Verify dense feature extraction with atrous convolution.

Verify the values of dense feature extraction by atrous convolution. Make sure that dense feature extraction by stack_blocks_dense() followed by

Verify the values of dense feature extraction by atrous convolution. Make sure that dense feature extraction by stack_blocks_dense() followed by