MCPcopy Create free account

hub / github.com/Vchitect/Latte / functions

Functions555 in github.com/Vchitect/Latte

Functionlist_valid_metrics
()
tools/metrics/metric_main.py:35
Functionload_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ffs_datasets.py:68
Functionload_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ucf101_image_datasets.py:71
Functionload_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ucf101_datasets.py:70
Functionload_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ffs_image_datasets.py:72
Functionmean_flat
Take the mean over all non-batch dimensions.
models/utils.py:115
Methodname
(self)
tools/utils/dataset.py:131
Functionno_weight_gradients
()
tools/torch_utils/ops/conv2d_gradfix.py:26
Functionnoise_like
(shape, device, repeat=False)
models/utils.py:187
Functionnormalization
Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.
models/utils.py:122
Methodnum_channels
(self)
tools/utils/dataset.py:139
Functionnumpy2tensor
(x)
datasets/ffs_datasets.py:37
Functionnumpy2tensor
(x)
datasets/ffs_image_datasets.py:39
Methodon_save_checkpoint
(self, checkpoint)
train_with_img_pl.py:128
Methodon_save_checkpoint
(self, checkpoint)
train_pl.py:118
Methodon_train_batch_end
(self, *args, **kwargs)
train_with_img_pl.py:125
Methodon_train_batch_end
(self, *args, **kwargs)
train_pl.py:115
Functionopen_url
Download the given URL and return a binary-mode file object to access the data.
tools/dnnlib/util.py:385
Methodp_mean_variance
( self, model, *args, **kwargs )
diffusion/respace.py:89
Functionparams_and_buffers
(module)
tools/torch_utils/misc.py:146
Functionpost_hook
(mod, module_inputs, outputs)
tools/torch_utils/misc.py:203
Functionpre_hook
(_mod, _inputs)
tools/torch_utils/misc.py:201
Functionprint_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
tools/torch_utils/misc.py:193
Methodprocess
(text: str)
sample/pipeline_latte.py:373
Methodprocess_xstart
(x)
diffusion/gaussian_diffusion.py:314
Functionprofiled_function
(fn)
tools/torch_utils/misc.py:99
Functionregister_metric
(fn)
tools/metrics/metric_main.py:27
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
tools/torch_utils/training_stats.py:103
Functionreport_metric
(result_dict, run_dir=None, snapshot_pkl=None)
tools/metrics/metric_main.py:81
Functionresized_crop
Do spatial cropping and resizing to the video clip Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
datasets/video_transforms.py:60
Methodresolution
(self)
tools/utils/dataset.py:144
Functionrewrite_opts_for_gen_dataset
Updates dataset arguments in the opts to enable the second dataset stats computation
tools/metrics/metric_utils.py:325
Functionsave_video_grid
(video, nrow=None)
utils.py:255
Functionscale_module
Scale the parameters of a module and return it.
models/utils.py:106
Functionset_cache_dir
(path: str)
tools/dnnlib/util.py:123
Methodset_chunk_feed_forward
(self, chunk_size: Optional[int], dim: int)
models/latte_t2v.py:267
Functionsetup_filter
r"""Convenience function to setup 2D FIR filter for `upfirdn2d()`. Args: f: Torch tensor, numpy array, or python list of the sh
tools/torch_utils/ops/upfirdn2d.py:72
Functiontask_proxy
I do not know, how to pass several arguments to a pool job...
tools/convert_videos_to_frames.py:40
Functiontemporal_sampling
Given the start and end frame index, sample num_samples frames between the start and end with equal interval. Args: frames (t
datasets/ffs_datasets.py:17
Functiontemporal_sampling
Given the start and end frame index, sample num_samples frames between the start and end with equal interval. Args: frames (tenso
datasets/ucf101_image_datasets.py:24
Functiontemporal_sampling
Given the start and end frame index, sample num_samples frames between the start and end with equal interval. Args: frames (t
datasets/ucf101_datasets.py:21
Functiontemporal_sampling
Given the start and end frame index, sample num_samples frames between the start and end with equal interval. Args: frames (tenso
datasets/ffs_image_datasets.py:19
Functiontext_preprocessing
(text, clean_caption=False)
utils.py:318
Functiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may
models/utils.py:74
Methodto_dict
(self)
tools/dnnlib/util.py:55
Methodtraining_losses
Compute training losses for a single timestep. :param model: the model to evaluate loss on. :param x_start: the [N x C x .
diffusion/gaussian_diffusion.py:719
Methodtraining_step
(self, batch, batch_idx)
train_with_img_pl.py:80
Methodtraining_step
(self, batch, batch_idx)
train_pl.py:80
Functiontuple_product
Calculate the product of the tuple elements.
tools/dnnlib/util.py:166
Methodupdate_with_all_losses
(self, ts, losses)
diffusion/timestep_sampler.py:139
Methodupdate_with_local_losses
Update the reweighting using losses from a model. Call this method from each rank with a batch of timesteps and the corres
diffusion/timestep_sampler.py:72
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.
tools/torch_utils/ops/upfirdn2d.py:308
Methodweights
(self)
diffusion/timestep_sampler.py:67
Methodweights
(self)
diffusion/timestep_sampler.py:130
Functionzero_module
Zero out the parameters of a module and return it.
models/utils.py:97
← previous501–555 of 555, ranked by callers