MCPcopy Create free account

hub / github.com/NVlabs/stylegan2-ada-pytorch / functions

Functions277 in github.com/NVlabs/stylegan2-ada-pytorch

Functionfilter2d
r"""Filter a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape matches the input. User-spe
torch_utils/ops/upfirdn2d.py:272
Methodfind_class
(self, module, name)
legacy.py:68
Functionfma
(a, b, c)
torch_utils/ops/fma.py:15
Functionfolder_write_bytes
(fname: str, data: Union[bytes, str])
dataset_tool.py:294
Functionformat_time
Convert the seconds to human readable string with days, hours, minutes and seconds.
dnnlib/util.py:139
Methodforward
(ctx, input, grid)
torch_utils/ops/grid_sample_gradfix.py:46
Methodforward
(ctx, grad_output, input, grid)
torch_utils/ops/grid_sample_gradfix.py:63
Methodforward
(ctx, x, b)
torch_utils/ops/bias_act.py:147
Methodforward
(ctx, dy, x, b, y)
torch_utils/ops/bias_act.py:180
Methodforward
(ctx, x, f)
torch_utils/ops/upfirdn2d.py:230
Methodforward
(ctx, a, b, c)
torch_utils/ops/fma.py:22
Methodforward
(ctx, input, weight, bias)
torch_utils/ops/conv2d_gradfix.py:109
Methodforward
(ctx, grad_output, input)
torch_utils/ops/conv2d_gradfix.py:142
Methodforward
(self, c)
metrics/perceptual_path_length.py:49
Methodforward
(self, x)
training/networks.py:105
Methodforward
(self, x, gain=1)
training/networks.py:160
Methodforward
(self, z, c, truncation_psi=1, truncation_cutoff=None, skip_w_avg_update=False)
training/networks.py:214
Methodforward
(self, x, w, noise_mode='random', fused_modconv=True, gain=1)
training/networks.py:286
Methodforward
(self, x, w, fused_modconv=True)
training/networks.py:320
Methodforward
(self, x, img, ws, force_fp32=False, fused_modconv=None, **layer_kwargs)
training/networks.py:379
Methodforward
(self, ws, **block_kwargs)
training/networks.py:457
Methodforward
(self, z, c, truncation_psi=1, truncation_cutoff=None, **synthesis_kwargs)
training/networks.py:497
Methodforward
(self, x, img, force_fp32=False)
training/networks.py:556
Methodforward
(self, x)
training/networks.py:595
Methodforward
(self, x, img, cmap, force_fp32=False)
training/networks.py:642
Methodforward
(self, img, c, **block_kwargs)
training/networks.py:717
Methodforward
(self, images, debug_percentile=None)
training/augment.py:181
Functionget_dtype_and_ctype
Given a type name string (or an object having a __name__ attribute), return matching Numpy and ctypes types that have the same size in bytes.
dnnlib/util.py:187
Functionget_module_dir_by_obj_name
Get the directory path of the module containing the given object name.
dnnlib/util.py:292
Functionget_plugin
(module_name, sources, **build_kwargs)
torch_utils/custom_ops.py:46
Functionget_top_level_function_name
Return the fully-qualified name of a top-level function.
dnnlib/util.py:303
Functiongrid_sample
(input, grid)
torch_utils/ops/grid_sample_gradfix.py:27
Methodhas_labels
(self)
training/dataset.py:145
Methodhas_onehot_labels
(self)
training/dataset.py:149
Methodimage_shape
(self)
training/dataset.py:115
Functionimport_hook
r"""Register an import hook that is called whenever a persistent object is being unpickled. A typical use case is to patch the pickled source
torch_utils/persistence.py:147
Methodinit_args
(self)
torch_utils/persistence.py:111
Methodinit_kwargs
(self)
torch_utils/persistence.py:115
Functioninit_multiprocessing
r"""Initializes `torch_utils.training_stats` for collecting statistics across multiple processes. This function must be called after `tor
torch_utils/training_stats.py:34
Functionis50k
(opts)
metrics/metric_main.py:106
Functionis_pickleable
(obj: Any)
dnnlib/util.py:210
Functionkid50k
(opts)
metrics/metric_main.py:121
Functionkid50k_full
(opts)
metrics/metric_main.py:89
Methodlabel_dim
(self)
training/dataset.py:140
Methodlabel_shape
(self)
training/dataset.py:130
Functionlist_dir_recursively_with_ignore
List all files recursively in a given directory while ignoring given file and directory names. Returns list of tuples containing both absolute and
dnnlib/util.py:315
Functionlist_valid_metrics
()
metrics/metric_main.py:34
Methodname
(self)
training/dataset.py:111
Functionno_weight_gradients
()
torch_utils/ops/conv2d_gradfix.py:26
Methodnum_channels
(self)
training/dataset.py:119
Functionnum_range
Accept either a comma separated list of numbers 'a,b,c' or a range 'a-c' and return as a list of ints.
style_mixing.py:25
Functionnum_range
Accept either a comma separated list of numbers 'a,b,c' or a range 'a-c' and return as a list of ints.
generate.py:25
Functionopen_url
Download the given URL and return a binary-mode file object to access the data.
dnnlib/util.py:382
Functionparams_and_buffers
(module)
torch_utils/misc.py:145
Functionpost_hook
(mod, _inputs, outputs)
torch_utils/misc.py:202
Functionppl2_wend
(opts)
metrics/metric_main.py:101
Functionppl_wend
(opts)
metrics/metric_main.py:148
Functionppl_wfull
(opts)
metrics/metric_main.py:138
Functionppl_zend
(opts)
metrics/metric_main.py:143
Functionppl_zfull
(opts)
metrics/metric_main.py:133
Functionpr50k3
(opts)
metrics/metric_main.py:127
Functionpr50k3_full
(opts)
metrics/metric_main.py:95
Functionpre_hook
(_mod, _inputs)
torch_utils/misc.py:200
Functionprint_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
torch_utils/misc.py:192
Functionprofiled_function
(fn)
torch_utils/misc.py:98
Functionregister_metric
(fn)
metrics/metric_main.py:26
Functionreport0
r"""Broadcasts the given set of scalars by the first process (`rank = 0`), but ignores any scalars provided by the other processes. See `repor
torch_utils/training_stats.py:103
Functionreport_metric
(result_dict, run_dir=None, snapshot_pkl=None)
metrics/metric_main.py:67
Methodresolution
(self)
training/dataset.py:124
Functionscale
(width, height, img)
dataset_tool.py:206
Functionset_cache_dir
(path: str)
dnnlib/util.py:120
Functionsetup_filter
r"""Convenience function to setup 2D FIR filter for `upfirdn2d()`. Args: f: Torch tensor, numpy array, or python list of the sh
torch_utils/ops/upfirdn2d.py:72
Methodtrainable_gen
()
training/networks.py:534
Functiontraining_loop
( run_dir = '.', # Output directory. training_set_kwargs = {}, # Option
training/training_loop.py:88
Functiontuple_product
Calculate the product of the tuple elements.
dnnlib/util.py:163
Functionupsample2d
r"""Upsample a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape is a multiple of the input.
torch_utils/ops/upfirdn2d.py:308
Functionzip_write_bytes
(fname: str, data: Union[bytes, str])
dataset_tool.py:279
← previous201–277 of 277, ranked by callers