MCPcopy Create free account

hub / github.com/NVlabs/stylegan / types & classes

Types & classes20 in github.com/NVlabs/stylegan

↓ 27 callersClassEasyDict
Convenience class that behaves like a dict but allows access with the attribute syntax.
dnnlib/util.py:36
↓ 10 callersClassTFRecordExporter
dataset_tool.py:33
↓ 1 callersClassExceptionInfo
dataset_tool.py:106
↓ 1 callersClassNetwork
Generic network abstraction. Acts as a convenience wrapper for a parameterized network construction function, providing several utility metho
dnnlib/tflib/network.py:36
↓ 1 callersClassWorkerThread
dataset_tool.py:113
ClassDummyMetric
metrics/metric_base.py:137
ClassFID
metrics/frechet_inception_distance.py:21
ClassLS
metrics/linear_separability.py:104
ClassLogger
Redirect stderr to stdout, optionally print stdout to a file, and optionally force flushing on both stdout and the file.
dnnlib/util.py:52
ClassMetricBase
metrics/metric_base.py:36
ClassMetricGroup
metrics/metric_base.py:119
ClassOptimizer
A Wrapper for tf.train.Optimizer. Automatically takes care of: - Gradient averaging for multi-GPU training. - Dynamic loss scaling and ty
dnnlib/tflib/optimizer.py:29
ClassPPL
metrics/perceptual_path_length.py:35
ClassPathType
Determines in which format should a path be formatted. WINDOWS: Format with Windows style. LINUX: Format with Linux/Posix style. AUTO: Us
dnnlib/submission/submit.py:38
ClassRunContext
Helper class for managing the run/training loop. The context will hide the implementation details of a basic run/training loop. It will set t
dnnlib/submission/run_context.py:22
ClassSubmitConfig
Strongly typed config dict needed to submit runs. Attributes: run_dir_root: Path to the run dir root. Can be optionally templated with ta
dnnlib/submission/submit.py:53
ClassSubmitTarget
The target where the function should be run. LOCAL: Run it locally.
dnnlib/submission/submit.py:30
ClassSyntheticDataset
training/dataset.py:171
ClassTFRecordDataset
training/dataset.py:37
ClassThreadPool
dataset_tool.py:131