Name of the TensorFlow device that the weights of this network reside on. Determined by the current device at construction time.

Construct TensorFlow expression(s) for the output(s) of this network, given the input expression(s). The graph is placed on the current Tensor

Create a clone of this network with its own copy of the variables.

Run this network for the given NumPy array(s), and return the output(s) as NumPy array(s). Args: input_transform: A dict speci

Create a new autosummary. Args: name: Name to use in TensorBoard value: TensorFlow expression or python value to track

Construct training op to update the registered variables based on their gradients.

Flush, close possible files, and remove stdout/stderr mirroring.

Copy the values of all variables from the given network, including sub-networks.

Register the gradients of the given loss function with respect to the given variables. Intended to be called once per GPU.

Check that TensorFlow session has been initialized.

Traverses the object name and returns the last (rightmost) python object.

Print a summary table of the network structure.

Run the specified ops in the default session.

r"""Pad, upsample, FIR filter, and downsample a batch of 2D images. Accepts a batch of 2D images of the shape `[majorDim, inH, inW, minorDim]`

Write text to stdout (and a file) and optionally flush.

Sum gradients across devices using TensorFlow collective ops (slow fallback path).

Internal helper for creating autosummary accumulators.

Get internal state for the given TensorFlow device.

Forcefully enter the specified name scope, ignoring any surrounding scopes.

r"""Downsample a batch of 2D images with the given filter. Accepts a batch of 2D images of the shape `[N, C, H, W]` or `[N, H, W, C]` and dow

Evaluate if new feature vectors are in the estimated manifold.

Find variable by local or global name.

Flush written text to both stdout and a file, if open.

Get or create variable representing log2 of the current dynamic loss scaling factor.

Searches for the underlying module behind the name to some python object. Returns the module and the object name (original name with module part r

Check whether the input is a valid Tensorflow expression, i.e., Tensorflow Tensor, Variable, or Operation.

Evaluate pairwise distances between two batches of feature vectors.

Reset internal state of the underlying optimizer.