Functions — github.com/JaydenLyh/Reward-Forcing

hub / github.com/JaydenLyh/Reward-Forcing / functions

Functions579 in github.com/JaydenLyh/Reward-Forcing

⨍ Functions 579◇ Types & classes 123

Functionget_peft_state_maybe_zero_3

(named_params, bias)

videoalign/utils.py:103

Functiongreen_mark

(x)

demo_utils/utils.py:394

Functiongroup_files_by_folder

(all_files)

demo_utils/utils.py:574

Methodhacked_get_attr

(self, name: str)

demo_utils/memory.py:19

Methodinference

Perform inference on the given noise and text prompts. Inputs: noise (torch.Tensor): The input noise tensor of shape

pipeline/bidirectional_diffusion_inference.py:34

Methodinference

Perform inference on the given noise and text prompts. Inputs: noise (torch.Tensor): The input noise tensor of shape

pipeline/causal_diffusion_inference.py:49

Methodinference

Perform inference on the given noise and text prompts. Inputs: noise (torch.Tensor): The input noise tensor of shape

pipeline/bidirectional_inference.py:33

Methodinference_with_trajectory

( self, noise: torch.Tensor, initial_latent: Optional[torch.Tensor] = None

pipeline/reward_forcing_training.py:61

Methodinit_weight

(self, conv)

wan/modules/vae.py:162

Methodinit_weight

(self, conv)

demo_utils/vae_block3.py:106

Methodinit_weight

(self, conv)

demo_utils/vae.py:127

Methodinit_weight2

(self, conv)

wan/modules/vae.py:174

Methodinit_weight2

(self, conv)

demo_utils/vae_block3.py:118

Methodinit_weight2

(self, conv)

demo_utils/vae.py:139

Functioninit_weights

(m)

wan/modules/t5.py:27

Functioninterpolate_numbers

(a, b, n, round_to_int=False, gamma=1.0)

demo_utils/utils.py:239

Functionjust_crop

(image, w, h)

demo_utils/utils.py:94

Functionlazy_positional_encoding

(t, repeats=None)

demo_utils/utils.py:513

Functionload_model_as_complete

(model, target_device, unload=True)

demo_utils/memory.py:127

Functionmin_resize

(x, m)

demo_utils/utils.py:19

Functionmove_optimizer_to_device

(optimizer, device)

demo_utils/utils.py:612

Methodnoop_no_sync

()

wan/image2video.py:249

Methodnoop_no_sync

()

wan/text2video.py:194

Functionnumpy2pytorch

(imgs)

demo_utils/utils.py:422

Functionoffload_model_from_device_for_memory_preservation

(model, target_device, preserved_memory_gb=0)

demo_utils/memory.py:101

Methodon_step_end

(self, args, state, control, **kwargs)

videoalign/trainer.py:233

Methodon_train_begin

(self, args, state, control, **kwargs)

videoalign/trainer.py:229

Methodparam_groups

(self)

wan/modules/clip.py:418

Methodprediction_step

( self, model, inputs, prediction_loss_only, ignore_keys = None, )

videoalign/trainer.py:501

Functionprint_free_mem

()

demo_utils/utils.py:323

Functionprint_gpu_parameters

(device, state_dict, log_count=1)

demo_utils/utils.py:333

Functionprint_tensor_list_size

(tensors)

demo_utils/utils.py:159

Functionprocess_vision_info

( conversations: list[dict] | list[list[dict]], )

wan/utils/qwen_vl_utils.py:344

Functionpytorch2numpy

(imgs)

demo_utils/utils.py:411

Methodqkv_fn

(x)

wan/modules/causal_model.py:134

Methodqkv_fn

(x)

wan/modules/model.py:138

MethodreadCalibrationCache

(self)

demo_utils/vae_torch2trt.py:209

Functionread_from_json

(file_path)

demo_utils/utils.py:116

Functionrepeat_to_batch_size

(tensor: torch.Tensor, batch_size: int)

demo_utils/utils.py:451

Methodreset_parameters

(self)

wan/modules/model.py:493

Functionresize_and_center_crop

(image, target_width, target_height)

demo_utils/utils.py:48

Functionresize_and_center_crop_pytorch

(image, target_width, target_height)

demo_utils/utils.py:66

Functionresize_without_crop

(image, target_width, target_height)

demo_utils/utils.py:85

Methodreward

Inputs: video_paths: List[str], B paths of the videos. prompts: List[str], B prompts for the videos. eval

videoalign/inference.py:242

Functionsave_bchw_as_png

(x, output_filename)

demo_utils/utils.py:295

Functionsave_bcthw_as_mp4

(x, output_filename, fps=10, crf=0)

demo_utils/utils.py:269

Functionsave_bcthw_as_png

(x, output_filename)

demo_utils/utils.py:286

Functionsave_video

(tensor, path)

videoalign/utils.py:155

Methodscale_model_input

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Ar

wan/utils/fm_solvers.py:800

Methodscale_model_input

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

wan/utils/fm_solvers_unipc.py:741

Functionseparate_lora_AB

(parameters, B_patterns=None)

demo_utils/utils.py:135

Functionset_attr_recursive

(obj, attr, value)

demo_utils/utils.py:151

Methodset_begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index

wan/utils/fm_solvers.py:216

Methodset_begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

wan/utils/fm_solvers_unipc.py:149

Methodset_timesteps

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):

wan/utils/fm_solvers_unipc.py:160

Functionshard_model

( model, device_id, param_dtype=torch.bfloat16, reduce_dtype=torch.float32, buffer_dtype=t

wan/distributed/fsdp.py:10

Functionsoft_append_bcthw

(history, current, overlap=0)

demo_utils/utils.py:255

Functionstate_dict_offset_merge

(A, B, C=None)

demo_utils/utils.py:530

Functionstate_dict_weighted_merge

(state_dicts, weights)

demo_utils/utils.py:547

Methodstep_index

The index counter for current timestep. It will increase 1 after each scheduler step.

wan/utils/fm_solvers.py:202

Methodstep_index

The index counter for current timestep. It will increase 1 after each scheduler step.

wan/utils/fm_solvers_unipc.py:135

Functionstr2bool

Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: 'no', 'false', 'f', 'n', '0'

wan/utils/utils.py:94

Functionsupress_lower_channels

(m, k, alpha=0.01)

demo_utils/utils.py:203

Functiontorch_safe_save

(content, path)

demo_utils/utils.py:606

Methodtrain

(self)

trainer/distillation.py:324

Methodtrain

(self)

trainer/diffusion.py:248

trainer/rewarded_distillation.py:328

Functionuniform_random_by_intervals

(inclusive, exclusive, n, round_to_int=False)

demo_utils/utils.py:246

Methoduninstall_model

(model: torch.nn.Module)

demo_utils/memory.py:55

Functionusp_attn_forward

(self, x, seq_lens, grid_sizes,

wan/distributed/xdit_context_parallel.py:149

Functionusp_dit_forward

x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s

wan/distributed/xdit_context_parallel.py:66

Functionvisualize_txt_as_img

(width, height, text, font_path='font/DejaVuSans.ttf', size=18)

demo_utils/utils.py:348

Functionweighted_mse

(a, b, weight)

demo_utils/utils.py:436

MethodwriteCalibrationCache

(self, cache)

demo_utils/vae_torch2trt.py:216

Functionwrite_PIL_image_with_png_info

(image, metadata, path)

demo_utils/utils.py:595

Functionwrite_to_json

(data, file_path)

demo_utils/utils.py:108

Functionxlm_roberta_large

XLMRobertaLarge adapted from Huggingface.

wan/modules/xlm_roberta.py:146

Functionzero_module

(module)

demo_utils/utils.py:196

← previous501–579 of 579, ranked by callers