Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/NVlabs/stylegan2-ada-pytorch
/ functions
Functions
277 in github.com/NVlabs/stylegan2-ada-pytorch
⨍
Functions
277
◇
Types & classes
40
↳
Endpoints
5
Function
filter2d
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
Method
find_class
(self, module, name)
legacy.py:68
Function
fma
(a, b, c)
torch_utils/ops/fma.py:15
Function
folder_write_bytes
(fname: str, data: Union[bytes, str])
dataset_tool.py:294
Function
format_time
Convert the seconds to human readable string with days, hours, minutes and seconds.
dnnlib/util.py:139
Method
forward
(ctx, input, grid)
torch_utils/ops/grid_sample_gradfix.py:46
Method
forward
(ctx, grad_output, input, grid)
torch_utils/ops/grid_sample_gradfix.py:63
Method
forward
(ctx, x, b)
torch_utils/ops/bias_act.py:147
Method
forward
(ctx, dy, x, b, y)
torch_utils/ops/bias_act.py:180
Method
forward
(ctx, x, f)
torch_utils/ops/upfirdn2d.py:230
Method
forward
(ctx, a, b, c)
torch_utils/ops/fma.py:22
Method
forward
(ctx, input, weight, bias)
torch_utils/ops/conv2d_gradfix.py:109
Method
forward
(ctx, grad_output, input)
torch_utils/ops/conv2d_gradfix.py:142
Method
forward
(self, c)
metrics/perceptual_path_length.py:49
Method
forward
(self, x)
training/networks.py:105
Method
forward
(self, x, gain=1)
training/networks.py:160
Method
forward
(self, z, c, truncation_psi=1, truncation_cutoff=None, skip_w_avg_update=False)
training/networks.py:214
Method
forward
(self, x, w, noise_mode='random', fused_modconv=True, gain=1)
training/networks.py:286
Method
forward
(self, x, w, fused_modconv=True)
training/networks.py:320
Method
forward
(self, x, img, ws, force_fp32=False, fused_modconv=None, **layer_kwargs)
training/networks.py:379
Method
forward
(self, ws, **block_kwargs)
training/networks.py:457
Method
forward
(self, z, c, truncation_psi=1, truncation_cutoff=None, **synthesis_kwargs)
training/networks.py:497
Method
forward
(self, x, img, force_fp32=False)
training/networks.py:556
Method
forward
(self, x)
training/networks.py:595
Method
forward
(self, x, img, cmap, force_fp32=False)
training/networks.py:642
Method
forward
(self, img, c, **block_kwargs)
training/networks.py:717
Method
forward
(self, images, debug_percentile=None)
training/augment.py:181
Function
get_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
Function
get_module_dir_by_obj_name
Get the directory path of the module containing the given object name.
dnnlib/util.py:292
Function
get_plugin
(module_name, sources, **build_kwargs)
torch_utils/custom_ops.py:46
Function
get_top_level_function_name
Return the fully-qualified name of a top-level function.
dnnlib/util.py:303
Function
grid_sample
(input, grid)
torch_utils/ops/grid_sample_gradfix.py:27
Method
has_labels
(self)
training/dataset.py:145
Method
has_onehot_labels
(self)
training/dataset.py:149
Method
image_shape
(self)
training/dataset.py:115
Function
import_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
Method
init_args
(self)
torch_utils/persistence.py:111
Method
init_kwargs
(self)
torch_utils/persistence.py:115
Function
init_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
Function
is50k
(opts)
metrics/metric_main.py:106
Function
is_pickleable
(obj: Any)
dnnlib/util.py:210
Function
kid50k
(opts)
metrics/metric_main.py:121
Function
kid50k_full
(opts)
metrics/metric_main.py:89
Method
label_dim
(self)
training/dataset.py:140
Method
label_shape
(self)
training/dataset.py:130
Function
list_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
Function
list_valid_metrics
()
metrics/metric_main.py:34
Method
name
(self)
training/dataset.py:111
Function
no_weight_gradients
()
torch_utils/ops/conv2d_gradfix.py:26
Method
num_channels
(self)
training/dataset.py:119
Function
num_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
Function
num_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
Function
open_url
Download the given URL and return a binary-mode file object to access the data.
dnnlib/util.py:382
Function
params_and_buffers
(module)
torch_utils/misc.py:145
Function
post_hook
(mod, _inputs, outputs)
torch_utils/misc.py:202
Function
ppl2_wend
(opts)
metrics/metric_main.py:101
Function
ppl_wend
(opts)
metrics/metric_main.py:148
Function
ppl_wfull
(opts)
metrics/metric_main.py:138
Function
ppl_zend
(opts)
metrics/metric_main.py:143
Function
ppl_zfull
(opts)
metrics/metric_main.py:133
Function
pr50k3
(opts)
metrics/metric_main.py:127
Function
pr50k3_full
(opts)
metrics/metric_main.py:95
Function
pre_hook
(_mod, _inputs)
torch_utils/misc.py:200
Function
print_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
torch_utils/misc.py:192
Function
profiled_function
(fn)
torch_utils/misc.py:98
Function
register_metric
(fn)
metrics/metric_main.py:26
Function
report0
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
Function
report_metric
(result_dict, run_dir=None, snapshot_pkl=None)
metrics/metric_main.py:67
Method
resolution
(self)
training/dataset.py:124
Function
scale
(width, height, img)
dataset_tool.py:206
Function
set_cache_dir
(path: str)
dnnlib/util.py:120
Function
setup_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
Method
trainable_gen
()
training/networks.py:534
Function
training_loop
( run_dir = '.', # Output directory. training_set_kwargs = {}, # Option
training/training_loop.py:88
Function
tuple_product
Calculate the product of the tuple elements.
dnnlib/util.py:163
Function
upsample2d
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
Function
zip_write_bytes
(fname: str, data: Union[bytes, str])
dataset_tool.py:279
← previous
201–277 of 277, ranked by callers