MCPcopy Create free account

hub / github.com/NJU-PCALab/STAR / functions

Functions1,973 in github.com/NJU-PCALab/STAR

⨍ Functions 1,973◇ Types & classes 452↳ Endpoints 3
↓ 2 callersMethod__init__
( self, input_size=(1, 32, 32), in_channels=4, patch_size=(1, 2, 2), h
utils_data/opensora/models/pixart/pixart.py:114
↓ 2 callersMethod__init__
(self)
utils_data/opensora/models/vsr/fdie_arch.py:99
↓ 2 callersMethod__init__
skip_frms_num: ignore the first and the last xx frames, avoiding transitions.
cogvideox-based/sat/data_video.py:361
↓ 2 callersMethod__init__
(self, urls, seed, nshards=sys.maxsize, deterministic=True)
cogvideox-based/sat/sgm/webds.py:56
↓ 2 callersMethod__init__
(self, block_scale=None, block_size=None, min_snr_value=None, fixed_frames=0, **kwargs)
cogvideox-based/sat/sgm/modules/diffusionmodules/loss.py:197
↓ 2 callersMethod__init__
(self, sigma_min=0.002, sigma_max=80.0, rho=7.0)
cogvideox-based/sat/sgm/modules/diffusionmodules/discretizer.py:33
↓ 2 callersMethod__init__
(self)
cogvideox-based/sat/sgm/modules/encoders/modules.py:30
↓ 2 callersFunction_all_to_all
( input_: torch.Tensor, world_size: int, group: dist.ProcessGroup, scatter_dim: int, gathe
utils_data/opensora/acceleration/communications.py:8
↓ 2 callersMethod_apply_random_compression
(self, imgs)
utils_data/opensora/datasets/high_order/degrade_video.py:36
↓ 2 callersFunction_create_pad
(h, max_len)
video_to_video/video_to_video_model.py:184
↓ 2 callersFunction_drop_from_previous_rank
(input_, dim, kernel_size)
cogvideox-based/sat/vae_modules/cp_enc_dec.py:291
↓ 2 callersFunction_logsnr_cosine_shifted
(n, logsnr_min=-15, logsnr_max=15, scale=2)
video_to_video/diffusion/schedules_sdedit.py:36
↓ 2 callersMethod_predict_xstart_from_eps
(self, x_t, t, eps)
utils_data/opensora/schedulers/iddpm/gaussian_diffusion.py:323
↓ 2 callersMethod_t_to_sigma
(self, t)
video_to_video/diffusion/diffusion_sdedit.py:435
↓ 2 callersMethod_validation_step
(self, batch: dict, batch_idx: int, postfix: str = "")
cogvideox-based/sat/sgm/models/autoencoder.py:302
↓ 2 callersMethod_validation_step
(self, batch: dict, batch_idx: int, postfix: str = "")
cogvideox-based/sat/vae_modules/autoencoder.py:317
↓ 2 callersFunction_warmup_beta
(beta_start, beta_end, num_diffusion_timesteps, warmup_frac)
utils_data/opensora/schedulers/iddpm/gaussian_diffusion.py:64
↓ 2 callersFunction_warmup_beta
(beta_start, beta_end, num_diffusion_timesteps, warmup_frac)
utils_data/opensora/schedulers/dpms/dpm_solver.py:30
↓ 2 callersMethodancestral_euler_step
(self, x, denoised, sigma, sigma_down)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:169
↓ 2 callersMethodancestral_step
(self, x, sigma, next_sigma, sigma_up)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:175
↓ 2 callersMethodapply_ckpt
(self, ckpt: Union[None, str, dict])
cogvideox-based/sat/sgm/models/autoencoder.py:61
↓ 2 callersMethodapply_ckpt
(self, ckpt: Union[None, str, dict])
cogvideox-based/sat/vae_modules/autoencoder.py:70
↓ 2 callersFunctionapprox_standard_normal_cdf
A fast approximation of the cumulative distribution function of the standard normal.
utils_data/opensora/schedulers/iddpm/diffusion_utils.py:38
↓ 2 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
cogvideox-based/sat/sgm/modules/diffusionmodules/util.py:268
↓ 2 callersMethodbits_to_codes
(self, bits)
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:138
↓ 2 callersFunctioncalc_mean_std
Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to th
utils_data/opensora/datasets/wavelet_color_fix.py:44
↓ 2 callersFunctioncalc_mean_std
Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to th
cogvideox-based/sat/color_fix.py:48
↓ 2 callersFunctioncalc_mean_std
Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to th
video_super_resolution/color_fix.py:47
↓ 2 callersFunctioncalculate_weights_indices
Calculate weights and indices, used for imresize function. Args: in_length (int): Input length. out_length (int): Output length
utils_data/opensora/datasets/high_order/matlab_functions.py:16
↓ 2 callersFunctioncenter_crop
(clip, crop_size)
utils_data/opensora/datasets/video_transforms.py:118
↓ 2 callersFunctionclean_caption
(caption)
utils_data/opensora/models/text_encoder/t5.py:210
↓ 2 callersFunctionclean_caption
(caption)
video_to_video/modules/t5.py:210
↓ 2 callersMethodcondition_score
Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See con
utils_data/opensora/schedulers/iddpm/gaussian_diffusion.py:347
↓ 2 callersFunctionconvert_prompt
Convert a prompt to a format that can be used by the model for inference
cogvideox-based/inference/convert_demo.py:33
↓ 2 callersFunctioncount_flops_attn
A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr
cogvideox-based/sat/sgm/modules/diffusionmodules/openaimodel.py:401
↓ 2 callersFunctioncubic
cubic function used for calculate_weights_indices.
utils_data/opensora/datasets/high_order/matlab_functions.py:6
↓ 2 callersMethoddata_prediction_fn
Return the data prediction model (with corrector).
utils_data/opensora/schedulers/dpms/dpm_solver.py:555
↓ 2 callersMethoddecode
(self, z: torch.Tensor, **kwargs)
cogvideox-based/sat/vae_modules/autoencoder.py:232
↓ 2 callersMethoddecode_first_stage
(self, z)
cogvideox-based/sat/diffusion_video.py:170
↓ 2 callersFunctiondefault
(*args)
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:23
↓ 2 callersMethoddiffuse
(self, x0, t, noise=None)
video_to_video/diffusion/diffusion_sdedit.py:26
↓ 2 callersFunctiondownload_url
(input_path)
utils_data/opensora/datasets/utils.py:49
↓ 2 callersMethodema_scope
(self, context=None)
cogvideox-based/sat/sgm/models/autoencoder.py:82
↓ 2 callersMethodema_scope
(self, context=None)
cogvideox-based/sat/vae_modules/autoencoder.py:98
↓ 2 callersMethodencode
(self, text)
video_to_video/modules/t5.py:189
↓ 2 callersFunctionentropy
(prob)
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:55
↓ 2 callersMethodeuler_step
(self, x, d, dt)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:81
↓ 2 callersFunctionexpand_dims_like
(x, y)
cogvideox-based/sat/sgm/util.py:227
↓ 2 callersFunctionextract_frequencies
Extract high-frequency and low-frequency components of a video using Fourier transform. Args: video (torch.Tensor): Input video tensor o
cogvideox-based/sat/sgm/modules/diffusionmodules/loss.py:177
↓ 2 callersFunctionextract_frequencies
Extract high-frequency and low-frequency components of a video using Fourier transform. Args: video (torch.Tensor): Input video tensor o
video_super_resolution/scripts/train_sr.py:617
↓ 2 callersMethodfind_in_interval
(self, n)
cogvideox-based/sat/sgm/lr_scheduler.py:62
↓ 2 callersMethodforward
(self, x)
utils_data/opensora/utils/wavelet.py:55
↓ 2 callersFunctiongenerate_gaussian_noise_pt
Add Gaussian noise (PyTorch version). Args: img (Tensor): Shape (b, c, h, w), range[0, 1], float32. scale (float | Tensor): Noi
utils_data/opensora/datasets/high_order/utils_noise.py:55
↓ 2 callersFunctiongenerate_poisson_noise_pt
Generate a batch of poisson noise (PyTorch version) Args: img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32.
utils_data/opensora/datasets/high_order/utils_noise.py:126
↓ 2 callersFunctiongenerate_roughly_equally_spaced_steps
(num_substeps: int, max_step: int)
cogvideox-based/sat/sgm/modules/diffusionmodules/discretizer.py:11
↓ 2 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
cogvideox-based/sat/dit_video_concat.py:148
↓ 2 callersFunctionget_ancestral_step
(sigma_from, sigma_to, eta=1.0)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling_utils.py:135
↓ 2 callersMethodget_autoencoder_params
(self)
cogvideox-based/sat/sgm/models/autoencoder.py:182
↓ 2 callersMethodget_autoencoder_params
(self)
cogvideox-based/sat/vae_modules/autoencoder.py:198
↓ 2 callersFunctionget_ckpt_path
(name, root, check=False)
cogvideox-based/sat/sgm/modules/autoencoding/lpips/util.py:34
↓ 2 callersFunctionget_data_parallel_group
()
utils_data/opensora/acceleration/parallel_states.py:10
↓ 2 callersMethodget_input
(self, batch)
cogvideox-based/sat/diffusion_video.py:166
↓ 2 callersMethodget_last_layer
(self)
cogvideox-based/sat/sgm/models/autoencoder.py:199
↓ 2 callersMethodget_last_layer
(self)
cogvideox-based/sat/vae_modules/autoencoder.py:215
↓ 2 callersMethodget_loss
(self, model_output, target, w, video_data=None, timesteps=None, decode_first_stage=None)
cogvideox-based/sat/sgm/modules/diffusionmodules/loss.py:247
↓ 2 callersFunctionget_model_input_time
Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. For discrete-time DPMs, we convert `t_continuou
utils_data/opensora/schedulers/dpms/dpm_solver.py:394
↓ 2 callersMethodget_param_groups
( self, parameter_names: List[List[str]], optimizer_args: List[dict] )
cogvideox-based/sat/sgm/models/autoencoder.py:340
↓ 2 callersMethodget_param_groups
( self, parameter_names: List[List[str]], optimizer_args: List[dict] )
cogvideox-based/sat/vae_modules/autoencoder.py:355
↓ 2 callersMethodget_sigmas
(self, n, device)
cogvideox-based/sat/sgm/modules/diffusionmodules/discretizer.py:28
↓ 2 callersMethodget_single_embedding
( self, embedder, batch, output, cond_or_not: Optional[np.ndarray] = N
cogvideox-based/sat/sgm/modules/encoders/modules.py:133
↓ 2 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/pixart/pixart.py:251
↓ 2 callersFunctionget_state_dict
(saved_dict: Dict[str, Any])
cogvideox-based/tools/convert_weight_sat2hf.py:144
↓ 2 callersMethodget_trainable_autoencoder_parameters
(self)
cogvideox-based/sat/sgm/modules/autoencoding/losses/discriminator_loss.py:84
↓ 2 callersMethodget_trainable_parameters
(self)
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/base.py:17
↓ 2 callersMethodget_trainable_parameters
(self)
cogvideox-based/sat/vae_modules/regularizers.py:68
↓ 2 callersFunctionget_transforms_image
(name="center", image_size=(256, 256))
utils_data/opensora/datasets/utils.py:152
↓ 2 callersMethodget_unconditional_conditioning
(self, batch_c, batch_uc=None, force_uc_zero_embeddings=None)
cogvideox-based/sat/sgm/modules/encoders/modules.py:211
↓ 2 callersFunctiongrad_layer_wrt_loss
(loss: Tensor, layer: nn.Parameter)
cogvideox-based/sat/sgm/modules/autoencoding/losses/video_loss.py:47
↓ 2 callersFunctionhinge_discr_loss
(fake, real)
cogvideox-based/sat/sgm/modules/autoencoding/magvit2_pytorch.py:139
↓ 2 callersFunctionhinge_gen_loss
(fake)
cogvideox-based/sat/sgm/modules/autoencoding/magvit2_pytorch.py:143
↓ 2 callersMethodidx_to_sigma
(self, idx)
cogvideox-based/sat/sgm/modules/diffusionmodules/sigma_sampling.py:39
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
cogvideox-based/sat/sgm/models/autoencoder.py:539
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
cogvideox-based/sat/vae_modules/autoencoder.py:564
↓ 2 callersMethodinitialize
(self, input)
cogvideox-based/sat/sgm/modules/autoencoding/lpips/util.py:56
↓ 2 callersMethodinstantiate_optimizer_from_config
(self, params, lr, cfg)
cogvideox-based/sat/sgm/models/autoencoder.py:104
↓ 2 callersMethodinstantiate_optimizer_from_config
(self, params, lr, cfg)
cogvideox-based/sat/vae_modules/autoencoder.py:120
↓ 2 callersFunctioninterpolate_fn
A piecewise linear function y = f(x), using xp and yp as keypoints. We implement f(x) in a differentiable way (i.e. applicable for autograd).
utils_data/opensora/schedulers/dpms/dpm_solver.py:1480
↓ 2 callersFunctionis_master
(group=None)
video_to_video/utils/logger.py:89
↓ 2 callersFunctionis_odd
(n)
cogvideox-based/sat/sgm/modules/cp_enc_dec.py:36
↓ 2 callersFunctionis_odd
(n)
cogvideox-based/sat/sgm/modules/autoencoding/vqvae/movq_enc_3d.py:21
↓ 2 callersFunctionis_odd
(n)
cogvideox-based/sat/vae_modules/cp_enc_dec.py:34
↓ 2 callersFunctionmake_beta_schedule
( schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, )
cogvideox-based/sat/sgm/modules/diffusionmodules/util.py:20
↓ 2 callersFunctionmd5_hash
(path)
cogvideox-based/sat/sgm/modules/autoencoding/lpips/util.py:28
↓ 2 callersMethodmultistep_dpm_solver_update
Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The init
utils_data/opensora/schedulers/dpms/dpm_solver.py:1097
↓ 2 callersMethodnoise_prediction_fn
Return the noise prediction model.
utils_data/opensora/schedulers/dpms/dpm_solver.py:549
↓ 2 callersFunctionnoise_schedule
(schedule='logsnr_cosine_interp', n=1000, zero_terminal_snr=False,
video_to_video/diffusion/schedules_sdedit.py:72
↓ 2 callersFunctionnorm_cdf
(x)
utils_data/opensora/models/layers/timm_uvit.py:11
↓ 2 callersFunctionnormal_kl
Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among other
utils_data/opensora/schedulers/iddpm/diffusion_utils.py:18
↓ 2 callersFunctionnormalize_tensor
(x, eps=1e-10)
cogvideox-based/sat/sgm/modules/autoencoding/lpips/loss/lpips.py:126
↓ 2 callersFunctionpad_last_frame
(tensor, num_frames)
cogvideox-based/sat/data_video.py:150
← previousnext →201–300 of 1,973, ranked by callers