Functions — github.com/DreamEditBenchTeam/DreamEdit

hub / github.com/DreamEditBenchTeam/DreamEdit / functions

Functions598 in github.com/DreamEditBenchTeam/DreamEdit

⨍ Functions 598◇ Types & classes 104

↓ 78 callersFunctionexpand_dims

Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:1174

↓ 38 callersMethodregister_buffer

(self, name, attr)

src/ldm/models/diffusion/ddim.py:19

↓ 21 callersMethodmarginal_lambda

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:150

↓ 21 callersMethodmodel_fn

Convert the model to the noise prediction model or the data prediction model.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:401

↓ 18 callersMethodmarginal_std

Compute sigma_t of a given continuous-time label t in [0, T].

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:144

↓ 16 callersFunctionexists

(val)

src/ldm/modules/x_transformer.py:54

↓ 16 callersMethodmarginal_log_mean_coeff

Compute log(alpha_t) of a given continuous-time label t in [0, T].

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:125

↓ 15 callersMethod__init__

(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks, attn_resolutions, dropout=0.0, resam

src/ldm/modules/diffusionmodules/model.py:217

↓ 15 callersFunctionconv_nd

Create a 1D, 2D, or 3D convolution module.

src/ldm/modules/diffusionmodules/util.py:218

↓ 15 callersFunctionextract_into_tensor

(a, t, x_shape)

src/ldm/modules/diffusionmodules/util.py:96

↓ 14 callersFunctioninstantiate_from_config

(config)

src/ldm/util.py:78

↓ 13 callersMethoddecode

(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None,

src/ldm/models/diffusion/ddim.py:223

↓ 13 callersMethodregister_buffer

(self, name, attr)

src/ldm/models/diffusion/plms.py:18

↓ 12 callersMethod__init__

(self, value, fn)

src/ldm/modules/x_transformer.py:118

↓ 12 callersMethodq_sample

(self, x_start, t, noise=None)

src/ldm/models/diffusion/ddpm.py:274

↓ 11 callersMethodapply_model

(self, x_noisy, t, cond, return_ids=False)

src/ldm/models/diffusion/ddpm.py:891

↓ 11 callersMethodget_time_steps

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We suppor

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:410

↓ 10 callersFunctionmerge_masks

param: masks in size [N, H, W] return: mask in size []

src/utils/mask_helper.py:9

↓ 10 callersFunctionnonlinearity

(x)

src/ldm/modules/diffusionmodules/model.py:33

↓ 9 callersFunctionNormalize

(in_channels, num_groups=32)

src/ldm/modules/diffusionmodules/model.py:38

↓ 9 callersMethod__init__

(self, channels, use_conv, dims=2, out_channels=None, padding=1)

src/ldm/modules/diffusionmodules/openaimodel.py:100

↓ 9 callersFunctionsave_pil_image

param: image as PIL Image dest_folder filename return: ---

src/utils/visual_helper.py:23

↓ 8 callersMethod__init__

(self, n_embed, n_layer, vocab_size=30522, max_seq_len=77, device="cuda",use_tokenizer=True,

src/ldm/modules/encoders/modules.py:82

↓ 8 callersMethoddecode_first_stage

(self, z, predict_cids=False, force_not_quantize=False)

src/ldm/models/diffusion/ddpm.py:706

↓ 8 callersFunctionnormalization

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

src/ldm/modules/diffusionmodules/util.py:199

↓ 7 callersMethodema_scope

(self, context=None)

src/ldm/models/diffusion/ddpm.py:172

↓ 7 callersMethodget_learned_conditioning

(self, c)

src/ldm/models/diffusion/ddpm.py:551

↓ 7 callersFunctionmake_attn

(in_channels, attn_type="vanilla")

src/ldm/modules/diffusionmodules/model.py:205

↓ 7 callersMethodsample

(self)

src/ldm/modules/distributions/distributions.py:17

↓ 6 callersMethod__init__

(self, dim_in, dim_out)

src/ldm/modules/attention.py:38

↓ 6 callersMethod__init__

(self, txt_file, data_root, size=None, int

src/ldm/data/lsun.py:10

↓ 6 callersFunctionadd_JPEG_noise

(img)

src/ldm/modules/image_degradation/bsrgan.py:418

↓ 6 callersFunctionadd_blur

(img, sf=4)

src/ldm/modules/image_degradation/bsrgan.py:325

↓ 6 callersFunctiondefault

(val, d)

src/ldm/modules/x_transformer.py:58

↓ 6 callersMethodmeshgrid

(self, h, w)

src/ldm/models/diffusion/ddpm.py:564

↓ 6 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

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:885

↓ 5 callersFunctiondefault

(val, d)

src/ldm/util.py:57

↓ 5 callersMethodencode

(self, x)

src/ldm/models/autoencoder.py:96

↓ 5 callersMethodforward

(self, x)

src/ldm/modules/diffusionmodules/util.py:210

↓ 5 callersMethodget_input

(self, batch, k)

src/ldm/models/diffusion/ddpm.py:329

↓ 5 callersMethodinverse_lambda

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:158

↓ 5 callersFunctionlinear

Create a linear module.

src/ldm/modules/diffusionmodules/util.py:231

↓ 5 callersMethodquantize

(self, x, *args, **kwargs)

src/ldm/models/autoencoder.py:437

↓ 4 callersMethod__init__

Imagenet Superresolution Dataloader Performs following ops in order: 1. crops a crop of size s from image either as random o

src/ldm/data/imagenet.py:273

↓ 4 callersFunctionadd_Gaussian_noise

(img, noise_level1=2, noise_level2=25)

src/ldm/modules/image_degradation/bsrgan.py:369

↓ 4 callersFunctionadd_JPEG_noise

(img)

src/ldm/modules/image_degradation/bsrgan_light.py:422

↓ 4 callersFunctionadopt_weight

(weight, global_step, threshold=0, value=0.)

src/ldm/modules/losses/vqperceptual.py:20

↓ 4 callersFunctioncalculate_weights_indices

(in_length, out_length, scale, kernel, kernel_width, antialiasing)

src/ldm/modules/image_degradation/utils_image.py:708

↓ 4 callersMethodcompute_top_k

(self, logits, labels, k, reduction="mean")

src/ldm/models/diffusion/classifier.py:150

↓ 4 callersMethodencode_image

Take input in size [B, 3, H, W]

src/metrics/clip_vit.py:14

↓ 4 callersFunctionevaluate_clipi_score_list

(real_image, generated_image_list, device, clip_model)

src/metrics/evaluate_dino.py:39

↓ 4 callersFunctionevaluate_dino_score_list

(real_image, generated_image_list, device, fidelity)

src/metrics/evaluate_dino.py:17

↓ 4 callersFunctionget_concat_pil_images

param: images - list of pil images direction - h for horizonal return: pil - Image Object

src/utils/visual_helper.py:72

↓ 4 callersMethodget_fold_unfold

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

src/ldm/models/diffusion/ddpm.py:601

↓ 4 callersMethodget_last_layer

(self)

src/ldm/models/autoencoder.py:230

↓ 4 callersMethodget_last_layer

(self)

src/ldm/models/autoencoder.py:397

↓ 4 callersFunctionget_mask_pil_image

param: mask_tensor in size [H, W] return: mask in PIL image

src/utils/visual_helper.py:37

↓ 4 callersFunctionnoise_like

(shape, device, repeat=False)

src/ldm/modules/diffusionmodules/util.py:264

↓ 4 callersFunctionnoise_pred_fn

(x, t_continuous, cond=None)

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:289

↓ 4 callersMethodsample

(self, batch_size=16, return_intermediates=False)

src/ldm/models/diffusion/ddpm.py:268

↓ 4 callersMethodsample_log

(self,cond,batch_size,ddim, ddim_steps,**kwargs)

src/ldm/models/diffusion/ddpm.py:1235

↓ 4 callersMethodshared_step

(self, batch, t=None)

src/ldm/models/diffusion/classifier.py:179

↓ 4 callersFunctionzero_module

Zero out the parameters of a module and return it.

src/ldm/modules/diffusionmodules/util.py:174

↓ 3 callersMethod__init__

(self, ddconfig, lossconfig, n_embed, embe

src/ldm/models/autoencoder.py:15

↓ 3 callersMethod__init__

(self, unet_config, timesteps=1000, beta_schedule="linear",

src/ldm/models/diffusion/ddpm.py:46

↓ 3 callersFunctionadd_blur

(img, sf=4)

src/ldm/modules/image_degradation/bsrgan_light.py:325

↓ 3 callersFunctionbounding_box_merge

(bbox_tensor)

src/utils/mask_helper.py:151

↓ 3 callersFunctioncheckpoint

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

src/ldm/modules/diffusionmodules/util.py:102

↓ 3 callersFunctiondefault

(val, d)

src/ldm/modules/attention.py:19

↓ 3 callersMethoddenoise_to_zero_fn

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:498

↓ 3 callersMethoddpm_solver_adaptive

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:909

↓ 3 callersMethoddpm_solver_first_update

DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:504

↓ 3 callersMethodema_scope

(self, context=None)

src/ldm/models/autoencoder.py:64

↓ 3 callersMethodencode_first_stage

(self, x)

src/ldm/models/diffusion/ddpm.py:826

↓ 3 callersFunctionexists

(val)

src/ldm/modules/attention.py:11

↓ 3 callersFunctionfspecial

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

src/ldm/modules/image_degradation/bsrgan_light.py:210

↓ 3 callersFunctionfspecial

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

src/ldm/modules/image_degradation/bsrgan.py:210

↓ 3 callersMethodget_embeddings

(self, tensor_image)

src/metrics/dino_vit.py:20

↓ 3 callersMethodget_first_stage_encoding

(self, encoder_posterior)

src/ldm/models/diffusion/ddpm.py:542

↓ 3 callersMethodget_input

(self, batch, k)

src/ldm/models/autoencoder.py:124

↓ 3 callersMethodget_input

(self, batch, k)

src/ldm/models/autoencoder.py:344

↓ 3 callersMethodget_loss

(self, pred, target, mean=True)

src/ldm/models/diffusion/ddpm.py:279

↓ 3 callersFunctionget_mask_from_bbox

(bbox)

src/utils/mask_helper.py:165

↓ 3 callersMethodget_orders_and_timesteps_for_singlestep_solver

Get the order of each step for sampling by the singlestep DPM-Solver. We combine both DPM-Solver-1,2,3 to use all the function evalu

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:439

↓ 3 callersMethodget_transform

(self)

src/metrics/clip_vit.py:11

↓ 3 callersMethodget_weighting

(self, h, w, Ly, Lx, device)

src/ldm/models/diffusion/ddpm.py:585

↓ 3 callersFunctionlog_txt_as_img

(wh, xc, size=10)

src/ldm/util.py:17

↓ 3 callersMethodmarginal_alpha

Compute alpha_t of a given continuous-time label t in [0, T].

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:138

↓ 3 callersMethodmode

(self)

src/ldm/modules/distributions/distributions.py:20

↓ 3 callersFunctionmodel_wrapper

Create a wrapper function for the noise prediction model. DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discr

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:177

↓ 3 callersMethodpredict_one_image

(self, image)

src/pipelines/imagecaption_pipelines.py:14

↓ 3 callersFunctionrepeat_tensor

(x, n, dim=0)

src/generate_new.py:102

↓ 3 callersMethodsample

Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. =========================================

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:965

↓ 3 callersFunctionselect_inpainting_pipeline

(name: str, device="cuda")

src/pipelines/inpainting_pipelines.py:31

↓ 3 callersMethodshared_step

(self, batch)

src/ldm/models/diffusion/ddpm.py:337

↓ 3 callersMethodsinglestep_dpm_solver_second_update

Singlestep solver DPM-Solver-2 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:551

↓ 3 callersMethodsinglestep_dpm_solver_update

Singlestep DPM-Solver with the order `order` from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:859

↓ 3 callersFunctionssim

(img1, img2)

src/ldm/modules/image_degradation/utils_image.py:669

↓ 3 callersMethodto_rgb

(self, x)

src/ldm/models/autoencoder.py:255

↓ 3 callersMethodto_rgb

(self, x)

src/ldm/models/diffusion/ddpm.py:1386

next →1–100 of 598, ranked by callers