Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Vchitect/Latte
/ functions
Functions
555 in github.com/Vchitect/Latte
⨍
Functions
555
◇
Types & classes
88
Function
list_valid_metrics
()
tools/metrics/metric_main.py:35
Function
load_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ffs_datasets.py:68
Function
load_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ucf101_image_datasets.py:71
Function
load_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ucf101_datasets.py:70
Function
load_annotations
(ann_file, num_class, num_samples_per_cls)
datasets/ffs_image_datasets.py:72
Function
mean_flat
Take the mean over all non-batch dimensions.
models/utils.py:115
Method
name
(self)
tools/utils/dataset.py:131
Function
no_weight_gradients
()
tools/torch_utils/ops/conv2d_gradfix.py:26
Function
noise_like
(shape, device, repeat=False)
models/utils.py:187
Function
normalization
Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.
models/utils.py:122
Method
num_channels
(self)
tools/utils/dataset.py:139
Function
numpy2tensor
(x)
datasets/ffs_datasets.py:37
Function
numpy2tensor
(x)
datasets/ffs_image_datasets.py:39
Method
on_save_checkpoint
(self, checkpoint)
train_with_img_pl.py:128
Method
on_save_checkpoint
(self, checkpoint)
train_pl.py:118
Method
on_train_batch_end
(self, *args, **kwargs)
train_with_img_pl.py:125
Method
on_train_batch_end
(self, *args, **kwargs)
train_pl.py:115
Function
open_url
Download the given URL and return a binary-mode file object to access the data.
tools/dnnlib/util.py:385
Method
p_mean_variance
( self, model, *args, **kwargs )
diffusion/respace.py:89
Function
params_and_buffers
(module)
tools/torch_utils/misc.py:146
Function
post_hook
(mod, module_inputs, outputs)
tools/torch_utils/misc.py:203
Function
pre_hook
(_mod, _inputs)
tools/torch_utils/misc.py:201
Function
print_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
tools/torch_utils/misc.py:193
Method
process
(text: str)
sample/pipeline_latte.py:373
Method
process_xstart
(x)
diffusion/gaussian_diffusion.py:314
Function
profiled_function
(fn)
tools/torch_utils/misc.py:99
Function
register_metric
(fn)
tools/metrics/metric_main.py:27
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
tools/torch_utils/training_stats.py:103
Function
report_metric
(result_dict, run_dir=None, snapshot_pkl=None)
tools/metrics/metric_main.py:81
Function
resized_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
Method
resolution
(self)
tools/utils/dataset.py:144
Function
rewrite_opts_for_gen_dataset
Updates dataset arguments in the opts to enable the second dataset stats computation
tools/metrics/metric_utils.py:325
Function
save_video_grid
(video, nrow=None)
utils.py:255
Function
scale_module
Scale the parameters of a module and return it.
models/utils.py:106
Function
set_cache_dir
(path: str)
tools/dnnlib/util.py:123
Method
set_chunk_feed_forward
(self, chunk_size: Optional[int], dim: int)
models/latte_t2v.py:267
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
tools/torch_utils/ops/upfirdn2d.py:72
Function
task_proxy
I do not know, how to pass several arguments to a pool job...
tools/convert_videos_to_frames.py:40
Function
temporal_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
Function
temporal_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
Function
temporal_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
Function
temporal_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
Function
text_preprocessing
(text, clean_caption=False)
utils.py:318
Function
timestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may
models/utils.py:74
Method
to_dict
(self)
tools/dnnlib/util.py:55
Method
training_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
Method
training_step
(self, batch, batch_idx)
train_with_img_pl.py:80
Method
training_step
(self, batch, batch_idx)
train_pl.py:80
Function
tuple_product
Calculate the product of the tuple elements.
tools/dnnlib/util.py:166
Method
update_with_all_losses
(self, ts, losses)
diffusion/timestep_sampler.py:139
Method
update_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
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.
tools/torch_utils/ops/upfirdn2d.py:308
Method
weights
(self)
diffusion/timestep_sampler.py:67
Method
weights
(self)
diffusion/timestep_sampler.py:130
Function
zero_module
Zero out the parameters of a module and return it.
models/utils.py:97
← previous
501–555 of 555, ranked by callers