An intermediate representation for TensorFlow operations.

Input data specifications for an ImageNet model.

Prescale batch normalization parameters. Concatenate gamma (scale) and beta (bias) terms if set.

The original batch normalization paper includes two learned parameters: a scaling factor \gamma and a bias \beta. Caffe's implementation

Associates parameters loaded from a .caffemodel file with their corresponding nodes.

Constructs a model graph from a Caffe protocol buffer definition.

Renames nodes in the graph using a given unary function that accepts a node and returns its new name.

Convert layer data arrays to a dictionary mapping parameter names to their values.

Fuses rectified linear units with their parent nodes.

Loads and processes batches of images in parallel.

An abstract helper for merging a single-child with its single-parent.