Returns a progress function that can wrap iterators to print progress messages, if verbose is True. If verbose is False or if iftop i

* Read all URL parameters into a map. * @returns {Map} the url parameters as a key-value store (ES6 map)

Returns a dict of all currently retained features.

* Every time data has changed, update is called and * triggers wrangling and re-rendering * @param {Object} data data object * @return

When within a progress loop, post_progress(k=str) will display the given k=str status on the right-hand-side of the progress status bar.

Returns top k data items and indexes in each dimension, with channels in the first dimension and k in the last dimension.

Returns a multilabel segmentation for the given batch of (RGB [-1...1]) images. Each pixel of the result is a torch.long indicating

Used to evaluate an arbitrary command-line constructor specifying a class, with automatic import of global module names.

Generate a standard set of random Z as a (size, z_dimension) tensor. With the same random seed, it always returns the same z (e.g., the first one

Sets default verbosity level. Set to True to see progress bars.

3x3 convolution with padding

3x3 convolution with padding

Returns a (end-start) sets of sample_size grid points within the shape given. If the shape dimensions are a multiple of 'grid', then sam

Creates an instrumented model out of a namespace of arguments that correspond to ArgumentParser command-line args: model: a string to e

Pass a fully-qualified layer name (E.g., module.submodule.conv3) to hook that layer and modify its output each time the model is run.