Functions — github.com/One-2-3-45/One-2-3-45

hub / github.com/One-2-3-45/One-2-3-45 / functions

Functions1,158 in github.com/One-2-3-45/One-2-3-45

⨍ Functions 1,158◇ Types & classes 214

Method__init__

(self, *args, vq_interface=False, **kwargs)

ldm/models/autoencoder.py:427

Method__init__

(self, model, schedule="linear", **kwargs)

ldm/models/diffusion/ddim.py:14

Method__init__

(self, diffusion_path, num_classes, ckpt_path=None,

ldm/models/diffusion/classifier.py:30

Method__init__

(self, first_stage_config, cond_stage_config, num_timesteps

ldm/models/diffusion/ddpm.py:485

Method__init__

(self, diff_model_config, conditioning_key)

ldm/models/diffusion/ddpm.py:1442

Method__init__

(self, *args, low_scale_config, low_scale_key="LR", **kwargs)

ldm/models/diffusion/ddpm.py:1478

Method__init__

(self, finetune_keys=("model.diffusion_model.input_blocks.0.0.weight",

ldm/models/diffusion/ddpm.py:1619

Method__init__

(self, cond_stage_key, *args, **kwargs)

ldm/models/diffusion/ddpm.py:1785

Method__init__

(self, *args, low_scale_key="LR", **kwargs)

ldm/models/diffusion/ddpm.py:1808

Method__init__

(self, *args, low_scale_key="LR", **kwargs)

ldm/models/diffusion/ddpm.py:1900

Method__init__

(self, model, schedule="linear", **kwargs)

ldm/models/diffusion/plms.py:13

Method__init__

(self, input_size, num_layers, mode='ir', drop_ratio=0.4, affine=True)

ldm/thirdp/psp/model_irse.py:12

Method__init__

(self, in_channel, depth, stride)

ldm/thirdp/psp/helpers.py:78

Method__init__

(self, in_channel, depth, stride)

ldm/thirdp/psp/helpers.py:100

Method__init__

(self, model_path)

ldm/thirdp/psp/id_loss.py:8

ldm/modules/evaluate/adm_evaluator.py:485

reconstruction/data/One2345_eval_new_data.py:136

Method__len__

(self)

reconstruction/data/One2345_train.py:159

Method__len__

(self)

ldm/modules/evaluate/adm_evaluator.py:482

Method__len__

(self)

ldm/data/simple.py:62

Method__len__

(self)

ldm/data/simple.py:151

Method__len__

(self)

ldm/data/simple.py:245

Method__len__

(self)

ldm/data/simple.py:376

Method__len__

(self)

ldm/data/simple.py:444

Method__len__

(self)

ldm/data/simple.py:490

Method__len__

(self)

ldm/data/imagenet.py:39

Method__len__

(self)

ldm/data/imagenet.py:336

ldm/data/nerf_like.py:52

Method__len__

(self)

ldm/data/nerf_like.py:95

Method__len__

(self)

ldm/data/nerf_like.py:136

Method_filter_predicate

(self, x)

ldm/data/laion.py:67

Method_forward

(self, x, context=None)

ldm/modules/attention.py:214

Method_forward

(self, x, emb)

ldm/modules/diffusionmodules/openaimodel.py:256

Method_forward

(self, x)

ldm/modules/diffusionmodules/openaimodel.py:319

Method_predict_eps_from_xstart

(self, x_t, t, pred_xstart)

ldm/models/diffusion/ddpm.py:986

Method_prepare

(self)

ldm/data/imagenet.py:150

Method_prepare

(self)

ldm/data/imagenet.py:216

Method_prior_bpd

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

ldm/models/diffusion/ddpm.py:990

Method_punsafe_to_class

(self, punsafe)

ldm/data/laion.py:64

Method_rescale_annotations

(self, bboxes, crop_coordinates)

ldm/models/diffusion/ddpm.py:878

Functionabs_error_numpy

(depth_pred, depth_gt, mask)

reconstruction/utils/misc_utils.py:67

Functionabs_relative

Computes relative absolute distance. Takes preprocessed depths (no nans, infs and non-positive values) depth_pred: depth map prediction

reconstruction/loss/depth_metric.py:115

Functionacc_threshold

computes the percentage of pixels whose depth error is less than @threshold

reconstruction/utils/misc_utils.py:78

Functionadd_Poisson_noise

(img)

ldm/modules/image_degradation/bsrgan_light.py:408

Functionadd_resize

(img, sf=4)

ldm/modules/image_degradation/bsrgan_light.py:343

Functionadd_sharpening

USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho

ldm/modules/image_degradation/bsrgan_light.py:299

Functionadd_speckle_noise

(img, noise_level1=2, noise_level2=25)

ldm/modules/image_degradation/bsrgan_light.py:390

Functionanalytic_kernel

Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)

ldm/modules/image_degradation/bsrgan_light.py:49

Functionanalytic_kernel

Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)

ldm/modules/image_degradation/bsrgan.py:49

Functionaugment_img_np3

(img, mode=0)

ldm/modules/image_degradation/utils_image.py:441

Functionaugment_img_tensor

Kai Zhang (github: https://github.com/cszn)

ldm/modules/image_degradation/utils_image.py:422

Functionaugment_img_tensor4

Kai Zhang (github: https://github.com/cszn)

ldm/modules/image_degradation/utils_image.py:401

Functionaugment_imgs

(img_list, hflip=True, rot=True)

ldm/modules/image_degradation/utils_image.py:469

Functionavg_log10

Computes average log_10 error (Liu, Neural Fields, 2015). Takes preprocessed depths (no nans, infs and non-positive values) depth1: one

reconstruction/loss/depth_metric.py:137

Functionback_project_dense_type

Unproject the image fetures to form a 3D (dense) feature volume :param coords: coordinates of voxels, dim: (batch, nviews, 3, X,Y,Z)

reconstruction/ops/back_project.py:133

Functionbetas_for_alpha_bar

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

ldm/modules/diffusionmodules/util.py:77

Functionblur

x: image, NxcxHxW k: kernel, Nx1xhxw

ldm/modules/image_degradation/bsrgan_light.py:128

Functionblur

x: image, NxcxHxW k: kernel, Nx1xhxw

ldm/modules/image_degradation/bsrgan.py:128

Functioncalculate_fvd

Returns a list of ops that compute metrics as funcs of activations. Args: real_activations: <float32>[num_samples, embedding_size] generate

ldm/modules/evaluate/frechet_video_distance.py:135

Functioncalculate_psnr

(img1, img2, border=0)

ldm/modules/image_degradation/utils_image.py:621

Functioncalculate_ssim

calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]

ldm/modules/image_degradation/utils_image.py:642

Functionchannel_convert

(in_c, tar_type, img_list)

ldm/modules/image_degradation/utils_image.py:597

Functionclassical_degradation

blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa

ldm/modules/image_degradation/bsrgan_light.py:284

Functionclassical_degradation

blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa

ldm/modules/image_degradation/bsrgan.py:284

Methodcoarse

(self, inputs)

reconstruction/models/fields.py:159

Functioncompute_depth_errors

Computes different distance measures between two depth maps. depth_pred: depth map prediction depth_gt: depth map

reconstruction/loss/depth_metric.py:204

Functioncompute_fvd

(ref_input, sample_input, bs=32, ref_stats=None, sample_stats=None,

ldm/modules/evaluate/torch_frechet_video_distance.py:155

Functioncompute_perceptual_similarity_from_list

(pred_imgs_list, tgt_imgs_list, take_every_other,

ldm/modules/evaluate/evaluate_perceptualsim.py:416

Functioncompute_perceptual_similarity_from_list_topk

(pred_imgs_list, tgt_imgs_list, take_every_other, resize=Fals

ldm/modules/evaluate/evaluate_perceptualsim.py:502

Functioncompute_supervision_coarse

(data, config)

elevation_estimate/loftr/utils/supervision.py:112

Functioncompute_supervision_fine

(data, config)

elevation_estimate/loftr/utils/supervision.py:146

Methodconfigure_optimizers

(self)

ldm/models/autoencoder.py:197

Methodconfigure_optimizers

(self)

ldm/models/autoencoder.py:386

Methodconfigure_optimizers

(self)

ldm/models/diffusion/classifier.py:220

Methodconfigure_optimizers

(self)

ldm/models/diffusion/ddpm.py:474

Methodconfigure_optimizers

(self)

ldm/models/diffusion/ddpm.py:1387

Functionconvert_module_to_f16

(x)

ldm/modules/diffusionmodules/openaimodel.py:25

Functionconvert_module_to_f32

(x)

ldm/modules/diffusionmodules/openaimodel.py:28

Methodconvert_to_fp16

Convert the torso of the model to float16.

ldm/modules/diffusionmodules/openaimodel.py:729

Methodconvert_to_fp16

Convert the torso of the model to float16.

ldm/modules/diffusionmodules/openaimodel.py:959

Methodconvert_to_fp32

Convert the torso of the model to float32.

ldm/modules/diffusionmodules/openaimodel.py:737

Methodconvert_to_fp32

Convert the torso of the model to float32.

ldm/modules/diffusionmodules/openaimodel.py:966

Methodcount_flops

(model, _x, y)

ldm/modules/diffusionmodules/openaimodel.py:376

Methodcount_flops

(model, _x, y)

ldm/modules/diffusionmodules/openaimodel.py:410

Functioncreate_id3_embedding

Embeds the given videos using the Inflated 3D Convolution ne twork. Downloads the graph of the I3D from tf.hub and adds it to the graph on the

ldm/modules/evaluate/frechet_video_distance.py:66

Methoddecode

(self, z)

ldm/modules/encoders/modules.py:532

Methoddecode

(self, h, force_not_quantize=False)

ldm/models/autoencoder.py:274

Methoddecode

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

ldm/models/autoencoder.py:434

Methoddecode_code

(self, code_b)

ldm/models/autoencoder.py:112

Functiondegradation_bsrgan

This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --

ldm/modules/image_degradation/bsrgan_light.py:442

Functiondegradation_bsrgan

This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --

ldm/modules/image_degradation/bsrgan.py:438

← previous next →701–800 of 1,158, ranked by callers