Functions — github.com/DreamEditBenchTeam/DreamEdit

hub / github.com/DreamEditBenchTeam/DreamEdit / functions

Functions598 in github.com/DreamEditBenchTeam/DreamEdit

⨍ Functions 598◇ Types & classes 104

# modified version of https://github.com/assafshocher/BlindSR_dataset_generator # Kai Zhang # min_var = 0.175 * sf # variance of the gau

src/ldm/modules/image_degradation/bsrgan.py:145

Methodget_BLIP_Model

(self)

src/pipelines/extract_object_pipeline.py:42

Methodget_base

(self)

src/ldm/data/imagenet.py:390

Methodget_embeddings_intermediate

We use `n_last_block=4` when evaluating ViT-Small

src/metrics/dino_vit.py:24

Functionget_file_path

search file across whole repo and return abspath

src/utils/path_finder.py:3

Methodget_langSAM

(self)

src/pipelines/extract_object_pipeline.py:39

Methodget_last_layer

(self)

src/ldm/modules/diffusionmodules/model.py:364

Functionget_mask_new

the map value will be clamped to map.mean() * clamp_rate, then values will be scaled into 0~1, then term into binary(split at 0.5). so if

src/generate_new.py:150

Methodget_model_output

(x, t)

src/ldm/models/diffusion/plms.py:178

Methodget_x_prev_and_pred_x0

(e_t, index)

src/ldm/models/diffusion/plms.py:199

Functiongroup_by_key_prefix

(prefix, d)

src/ldm/modules/x_transformer.py:106

Functionhinge_d_loss_with_exemplar_weights

(logits_real, logits_fake, weights)

src/ldm/modules/losses/vqperceptual.py:11

Functionimresize

(img, scale, antialiasing=True)

src/ldm/modules/image_degradation/utils_image.py:766

Functionimresize_np

(img, scale, antialiasing=True)

src/ldm/modules/image_degradation/utils_image.py:839

Functionimsave

(img, img_path)

src/ldm/modules/image_degradation/utils_image.py:203

Functionimshow

(x, title=None, cbar=False, figsize=None)

src/ldm/modules/image_degradation/utils_image.py:37

Functionimwrite

(img, img_path)

src/ldm/modules/image_degradation/utils_image.py:209

Functioninit_

(tensor)

src/ldm/modules/attention.py:29

Functioninner

(*args, **kwargs)

src/ldm/modules/x_transformer.py:65

Functionl1

(x, y)

src/ldm/modules/losses/vqperceptual.py:35

Functionl2

(x, y)

src/ldm/modules/losses/vqperceptual.py:39

Functionload_model_from_pretrain

(config, ckpt, verbose=False)

src/generate_new.py:66

Methodlog_images

(self, batch, only_inputs=False, plot_ema=False, **kwargs)

src/ldm/models/autoencoder.py:233

Methodlog_images

(self, batch, only_inputs=False, **kwargs)

src/ldm/models/autoencoder.py:401

Methodlog_images

(self, batch, N=8, *args, **kwargs)

src/ldm/models/diffusion/classifier.py:238

Methodlog_images

(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None, qua

src/ldm/models/diffusion/ddpm.py:1251

Methodlog_images

(self, batch, N=8, *args, **kwargs)

src/ldm/models/diffusion/ddpm.py:1430

Functionlog_result

(result)

src/clip_img_ret.py:46

Functionmax_neg_value

(t)

src/ldm/modules/attention.py:25

Functionmean_flat

https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/nn.py#L86 Take the mean over all no

src/ldm/util.py:63

Functionmkdir_and_rename

(path)

src/ldm/modules/image_degradation/utils_image.py:166

Functionmkdirs

(paths)

src/ldm/modules/image_degradation/utils_image.py:158

Functionmodcrop

(img_in, scale)

src/ldm/modules/image_degradation/utils_image.py:494

Functionmodcrop_np

Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image

src/ldm/modules/image_degradation/bsrgan_light.py:29

Functionmodcrop_np

Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image

src/ldm/modules/image_degradation/bsrgan.py:29

Methodmode

(self)

src/ldm/modules/distributions/distributions.py:9

Methodmode

(self)

src/ldm/modules/distributions/distributions.py:61

Functionmodel_fn

The noise predicition model function that is used for DPM-Solver.

src/ldm/models/diffusion/dpm_solver/dpm_solver.py:321

Functionmse

(img1, img2)

src/utils/losses.py:3

Methodnll

(self, sample, dims=[1,2,3])

src/ldm/modules/distributions/distributions.py:53

Methodon_train_batch_end

(self, *args, **kwargs)

src/ldm/models/autoencoder.py:92

Methodon_train_batch_end

(self, *args, **kwargs)

src/ldm/models/diffusion/ddpm.py:366

Methodon_train_batch_start

(self, batch, batch_idx, dataloader_idx)

src/ldm/models/diffusion/ddpm.py:478

Methodon_train_epoch_start

(self)

src/ldm/models/diffusion/classifier.py:157

Methodon_validation_start

(self)

src/ldm/models/diffusion/classifier.py:206

Functionparallel_data_prefetch

( func: callable, data, n_proc, target_data_type="ndarray", cpu_intensive=True, use_worker_id=False )

src/ldm/util.py:108

Functionpick_and_pop

(keys, d)

src/ldm/modules/x_transformer.py:88

Functionread_img

(path)

src/ldm/modules/image_degradation/utils_image.py:220

Methodregister_schedule

(self, given_betas=None, beta_schedule="linear", timesteps=1000,

src/ldm/models/diffusion/ddpm.py:493

Methodrescale_bbox

(bbox)

src/ldm/models/diffusion/ddpm.py:882

Functionresize_box_from_bottom

(resize_ratio, sam_box)

src/utils/mask_helper.py:141

Functionresize_box_from_middle

(resize_ratio, sam_box)

src/utils/mask_helper.py:131

Functionrgb2ycbcr

same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

src/ldm/modules/image_degradation/utils_image.py:529

Functionsample

( self, x, steps=20, t_start=None, t_end=None, order=3,

src/generate_new.py:320

Methodsample

(self)

src/ldm/modules/distributions/distributions.py:6

Methodsample

(self)

src/ldm/modules/distributions/distributions.py:35

Methodsample

(self, S, batch_size, shape, conditioning=None,

src/ldm/models/diffusion/plms.py:58

Methodsample

(self, S, batch_size, shape, conditioning=None,

src/ldm/models/diffusion/dpm_solver/sampler.py:22

Functionsample_edit

( self, x, steps=20, t_start=None, t_end=None, order=3,

src/generate_new.py:185

Functionsave_tensor_image

param: image in size [B, 3, H, W] dest_folder filename return: ---

src/utils/visual_helper.py:9

Functionscale_module

Scale the parameters of a module and return it.

src/ldm/modules/diffusionmodules/util.py:183

Methodschedule

(self, n, **kwargs)

src/ldm/lr_scheduler.py:83

Methodshared_step

(self, batch, **kwargs)

src/ldm/models/diffusion/ddpm.py:865

Functionshave

(img_in, border=0)

src/ldm/modules/image_degradation/utils_image.py:510

Functionsingle2tensor3

(img)

src/ldm/modules/image_degradation/utils_image.py:302

Functionsingle2tensor4

(img)

src/ldm/modules/image_degradation/utils_image.py:307

Functionsingle2tensor5

(img)

src/ldm/modules/image_degradation/utils_image.py:329

Functionsingle2uint

(img)

src/ldm/modules/image_degradation/utils_image.py:254

Functionsingle2uint16

(img)

src/ldm/modules/image_degradation/utils_image.py:264

Functionsingle32tensor5

(img)

src/ldm/modules/image_degradation/utils_image.py:333

Functionsingle42tensor4

(img)

src/ldm/modules/image_degradation/utils_image.py:337

Functionsplit_imageset

split the large images from original_dataroot into small overlapped images with size (p_size)x(p_size), and save them into taget_dataroot; on

src/ldm/modules/image_degradation/utils_image.py:125

Functionsrmd_degradation

blur + bicubic downsampling Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam

src/ldm/modules/image_degradation/bsrgan_light.py:240

Functionsrmd_degradation

blur + bicubic downsampling Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam

src/ldm/modules/image_degradation/bsrgan.py:240

Methodstochastic_encode

(self, x0, t, use_original_steps=False, noise=None)

src/ldm/models/diffusion/ddim.py:207

Functionstring_begins_with

(prefix, str)

src/ldm/modules/x_transformer.py:102

Functionsurf

(Z, cmap='rainbow', figsize=None)

src/ldm/modules/image_degradation/utils_image.py:47

Functiontensor2img

Converts a torch Tensor into an image Numpy array of BGR channel order Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel

src/ldm/modules/image_degradation/utils_image.py:342

Functiontensor2single

(img)

src/ldm/modules/image_degradation/utils_image.py:312

Functiontensor2single3

(img)

src/ldm/modules/image_degradation/utils_image.py:320

Functiontensor2uint

(img)

src/ldm/modules/image_degradation/utils_image.py:289

Functionto_binary

(pix)

src/generate_new.py:137

Methodtraining_step

(self, batch, batch_idx, optimizer_idx)

src/ldm/models/autoencoder.py:142

Methodtraining_step

(self, batch, batch_idx, optimizer_idx)

src/ldm/models/autoencoder.py:351

Methodtraining_step

(self, batch, batch_idx)

src/ldm/models/diffusion/classifier.py:198

Methodtraining_step

(self, batch, batch_idx)

src/ldm/models/diffusion/ddpm.py:342

Functiontransform_box_mask

(labeled_box, sam_box, mask)

src/utils/mask_helper.py:102

Functionuint162single

(img)

src/ldm/modules/image_degradation/utils_image.py:259

Functionuint2single

(img)

src/ldm/modules/image_degradation/utils_image.py:249

Functionuint2tensor3

(img)

src/ldm/modules/image_degradation/utils_image.py:282

Functionuint2tensor4

(img)

src/ldm/modules/image_degradation/utils_image.py:275

Functionuniform_on_device

(r1, r2, shape, device)

src/ldm/models/diffusion/ddpm.py:40

Functionuniq

(arr)

src/ldm/modules/attention.py:15

Methodvalidation_step

(self, batch, batch_idx)

src/ldm/models/autoencoder.py:164

Methodvalidation_step

(self, batch, batch_idx)

src/ldm/models/autoencoder.py:372

Methodvalidation_step

(self, batch, batch_idx)

src/ldm/models/diffusion/classifier.py:210

Methodvalidation_step

(self, batch, batch_idx)

src/ldm/models/diffusion/ddpm.py:358

Functionycbcr2rgb

same as matlab ycbcr2rgb Input: uint8, [0, 255] float, [0, 1]

src/ldm/modules/image_degradation/utils_image.py:553

← previous501–598 of 598, ranked by callers