MCPcopy Create free account

hub / github.com/LuChengTHU/dpm-solver / functions

Functions1,626 in github.com/LuChengTHU/dpm-solver

⨍ Functions 1,626◇ Types & classes 286
↓ 1 callersFunctionget_ddpm_loss_fn
Legacy code to reproduce previous results on DDPM. Not recommended for new work.
examples/score_sde_pytorch/losses.py:128
↓ 1 callersFunctionget_ddpm_loss_fn
Legacy code to reproduce previous results on DDPM. Not recommended for new work.
examples/score_sde_jax/losses.py:152
↓ 1 callersMethodget_dir
(self)
examples/ddpm_and_guided-diffusion/models/guided_diffusion/logger.py:388
↓ 1 callersFunctionget_div_fn
Create the divergence function of `fn` using the Hutchinson-Skilling trace estimator.
examples/score_sde_pytorch/likelihood.py:26
↓ 1 callersFunctionget_div_fn
Create the divergence function of `fn` using the Hutchinson-Skilling trace estimator.
examples/score_sde_jax/likelihood.py:28
↓ 1 callersFunctionget_dpm_solver_sampler
Create a Predictor-Corrector (PC) sampler. Args: sde: An `sde_lib.SDE` object representing the forward SDE. shape: A sequence of integers.
examples/score_sde_pytorch/sampling.py:505
↓ 1 callersFunctionget_dpm_solver_sampler
Create a Predictor-Corrector (PC) sampler. Args: sde: An `sde_lib.SDE` object representing the forward SDE. shape: A sequence of integers.
examples/score_sde_jax/sampling.py:539
↓ 1 callersMethodget_feature_vectors
Apply the model and return all of the intermediate tensors. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a
examples/ddpm_and_guided-diffusion/models/improved_ddpm/unet.py:494
↓ 1 callersFunctionget_image_paths
(dataroot)
examples/stable-diffusion/ldm/modules/image_degradation/utils_image.py:67
↓ 1 callersFunctionget_model
(name)
examples/score_sde_pytorch/models/utils.py:46
↓ 1 callersFunctionget_model
(name)
examples/score_sde_jax/models/utils.py:65
↓ 1 callersFunctionget_noise_fn
Wraps `noise_fn` so that the model output corresponds to a real time-dependent noise function. Args: sde: An `sde_lib.SDE` object that represen
examples/score_sde_pytorch/models/utils.py:129
↓ 1 callersFunctionget_noise_fn
Wraps `noise_fn` so that the model output corresponds to a real time-dependent noise function. Args: sde: An `sde_lib.SDE` object that represen
examples/score_sde_jax/models/utils.py:164
↓ 1 callersFunctionget_obj_from_str
(string, reload=False)
examples/stable-diffusion/ldm/util.py:88
↓ 1 callersFunctionget_ode_sampler
Probability flow ODE sampler with the black-box ODE solver. Args: sde: An `sde_lib.SDE` object that represents the forward SDE. shape: A se
examples/score_sde_pytorch/sampling.py:431
↓ 1 callersFunctionget_ode_sampler
Probability flow ODE sampler with the black-box ODE solver. Args: sde: An `sde_lib.SDE` object that represents the forward SDE. model: A `f
examples/score_sde_jax/sampling.py:459
↓ 1 callersFunctionget_optimizer
(config, parameters)
examples/ddpm_and_guided-diffusion/functions/__init__.py:4
↓ 1 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
dpm_solver_jax.py:437
↓ 1 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
dpm_solver_pytorch.py:482
↓ 1 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
examples/ddpm_and_guided-diffusion/dpm_solver/sampler.py:482
↓ 1 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
examples/score_sde_pytorch/dpm_solver.py:490
↓ 1 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
examples/stable-diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py:490
↓ 1 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
examples/score_sde_jax/dpm_solver.py:437
↓ 1 callersFunctionget_parser
(**parser_kwargs)
examples/stable-diffusion/main.py:24
↓ 1 callersFunctionget_parser
()
examples/stable-diffusion/scripts/sample_diffusion.py:162
↓ 1 callersFunctionget_pc_sampler
Create a Predictor-Corrector (PC) sampler. Args: sde: An `sde_lib.SDE` object representing the forward SDE. shape: A sequence of integers.
examples/score_sde_pytorch/sampling.py:372
↓ 1 callersFunctionget_pc_sampler
Create a Predictor-Corrector (PC) sampler. Args: sde: An `sde_lib.SDE` object representing the forward SDE. model: A `flax.linen.Module` ob
examples/score_sde_jax/sampling.py:391
↓ 1 callersFunctionget_predictor
(name)
examples/score_sde_pytorch/sampling.py:73
↓ 1 callersFunctionget_predictor
(name)
examples/score_sde_jax/sampling.py:77
↓ 1 callersFunctionget_rank_without_mpi_import
()
examples/ddpm_and_guided-diffusion/models/guided_diffusion/logger.py:403
↓ 1 callersFunctionget_sde_loss_fn
Create a loss function for training with arbirary SDEs. Args: sde: An `sde_lib.SDE` object that represents the forward SDE. train: `True` f
examples/score_sde_pytorch/losses.py:55
↓ 1 callersFunctionget_sde_loss_fn
Create a loss function for training with arbirary SDEs. Args: sde: An `sde_lib.SDE` object that represents the forward SDE. model: A `flax.
examples/score_sde_jax/losses.py:65
↓ 1 callersFunctionget_smld_loss_fn
Legacy code to reproduce previous results on SMLD(NCSN). Not recommended for new work.
examples/score_sde_pytorch/losses.py:104
↓ 1 callersFunctionget_smld_loss_fn
Legacy code to reproduce previous results on SMLD(NCSN). Not recommended for new work.
examples/score_sde_jax/losses.py:124
↓ 1 callersFunctionget_timestamp
()
examples/stable-diffusion/ldm/modules/image_degradation/utils_image.py:33
↓ 1 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
examples/ddpm_and_guided-diffusion/models/diffusion.py:6
↓ 1 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
examples/stable-diffusion/ldm/modules/diffusionmodules/model.py:12
↓ 1 callersFunctionget_weight
Get/create weight tensor for a convolution or fully-connected layer.
examples/score_sde_jax/models/up_or_down_sampling.py:31
↓ 1 callersMethodget_x_noisy
(self, x, t, noise=None)
examples/stable-diffusion/ldm/models/diffusion/classifier.py:110
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
examples/stable-diffusion/ldm/modules/image_degradation/bsrgan_light.py:86
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
examples/stable-diffusion/ldm/modules/image_degradation/bsrgan.py:86
↓ 1 callersFunctiongrad_fn
(data, ve_noise_scale, labels)
examples/score_sde_jax/models/utils.py:321
↓ 1 callersFunctionimread_uint
(path, n_channels=3)
examples/stable-diffusion/ldm/modules/image_degradation/utils_image.py:185
↓ 1 callersFunctionimssave
imgs: list, N images of size WxHxC
examples/stable-diffusion/ldm/modules/image_degradation/utils_image.py:112
↓ 1 callersMethodinit_
(self)
examples/stable-diffusion/ldm/modules/x_transformer.py:31
↓ 1 callersMethodinit_
(self)
examples/stable-diffusion/ldm/modules/x_transformer.py:595
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
examples/stable-diffusion/ldm/models/autoencoder.py:78
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
examples/stable-diffusion/ldm/models/autoencoder.py:313
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
examples/stable-diffusion/ldm/models/diffusion/classifier.py:70
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
examples/stable-diffusion/ldm/models/diffusion/ddpm.py:509
↓ 1 callersMethodinstantiate_first_stage
(self, config)
examples/stable-diffusion/ldm/models/diffusion/ddpm.py:502
↓ 1 callersMethodinstantiate_pretrained
(self, config)
examples/stable-diffusion/ldm/modules/diffusionmodules/model.py:807
↓ 1 callersMethodinverse
Inverse the sample `x` from time `t_start` to `t_end` by DPM-Solver. For discrete-time DPMs, we use `t_start=1/N`, where `N` is the t
examples/score_sde_pytorch/dpm_solver.py:1040
↓ 1 callersMethodinverse
Inverse the sample `x` from time `t_start` to `t_end` by DPM-Solver. For discrete-time DPMs, we use `t_start=1/N`, where `N` is the t
examples/stable-diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py:1040
↓ 1 callersFunctionis_image_file
(filename)
examples/stable-diffusion/ldm/modules/image_degradation/utils_image.py:29
↓ 1 callersFunctionisimage
(x)
examples/stable-diffusion/ldm/util.py:47
↓ 1 callersMethodkl
(self, other=None)
examples/stable-diffusion/ldm/modules/distributions/distributions.py:39
↓ 1 callersFunctionlikelihood_fn
Compute an unbiased estimate to the log-likelihood in bits/dim. Args: model: A score model. data: A PyTorch tensor. Returns:
examples/score_sde_pytorch/likelihood.py:69
↓ 1 callersFunctionlikelihood_fn
Compute an unbiased estimate to the log-likelihood in bits/dim. Args: prng: An array of random states. The list dimension equals the number
examples/score_sde_jax/likelihood.py:76
↓ 1 callersMethodload_classifier
(self, ckpt_path, pool)
examples/stable-diffusion/ldm/models/diffusion/classifier.py:95
↓ 1 callersFunctionload_data_for_worker
(base_samples, batch_size, cond_class)
examples/ddpm_and_guided-diffusion/runners/diffusion.py:31
↓ 1 callersMethodload_database
(self)
examples/stable-diffusion/scripts/knn2img.py:104
↓ 1 callersFunctionload_datapool
(dpath)
examples/stable-diffusion/scripts/train_searcher.py:28
↓ 1 callersMethodload_diffusion
(self)
examples/stable-diffusion/ldm/models/diffusion/classifier.py:88
↓ 1 callersFunctionload_img
(path)
examples/stable-diffusion/scripts/img2img.py:48
↓ 1 callersFunctionload_model
(config, ckpt, gpu, eval_mode)
examples/stable-diffusion/scripts/sample_diffusion.py:228
↓ 1 callersFunctionload_model_from_config
(config, ckpt)
examples/stable-diffusion/notebook_helpers.py:40
↓ 1 callersFunctionload_model_from_config
(config, sd)
examples/stable-diffusion/scripts/sample_diffusion.py:220
↓ 1 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
examples/stable-diffusion/scripts/img2img.py:28
↓ 1 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
examples/stable-diffusion/scripts/txt2img.py:49
↓ 1 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
examples/stable-diffusion/scripts/knn2img.py:41
↓ 1 callersFunctionload_replacement
(x)
examples/stable-diffusion/scripts/txt2img.py:77
↓ 1 callersMethodload_retriever
(self, version='ViT-L/14', )
examples/stable-diffusion/scripts/knn2img.py:123
↓ 1 callersMethodload_searcher
(self)
examples/stable-diffusion/scripts/knn2img.py:130
↓ 1 callersFunctionload_single_file
(saved_embeddings)
examples/stable-diffusion/scripts/train_searcher.py:31
↓ 1 callersMethodload_single_file
(self, saved_embeddings)
examples/stable-diffusion/scripts/knn2img.py:91
↓ 1 callersMethodlog_images
(self, batch, only_inputs=False, plot_ema=False, **kwargs)
examples/stable-diffusion/ldm/models/autoencoder.py:233
↓ 1 callersMethodlog_images
(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)
examples/stable-diffusion/ldm/models/diffusion/ddpm.py:378
↓ 1 callersMethodlog_local
(self, save_dir, split, images, global_step, current_epoch, batch_idx)
examples/stable-diffusion/main.py:321
↓ 1 callersFunctionlogit_fn
Give the logits of the classifier. Args: data: A JAX array of the input. ve_noise_scale: time conditioning variables in the form of V
examples/score_sde_jax/models/utils.py:301
↓ 1 callersFunctionlogit_transform
(image, lam=1e-6)
examples/ddpm_and_guided-diffusion/datasets/__init__.py:184
↓ 1 callersFunctionlogkv
Log a value of some diagnostic Call this once for each diagnostic quantity, each iteration If called many times, last value will be used.
examples/ddpm_and_guided-diffusion/models/guided_diffusion/logger.py:212
↓ 1 callersMethodlogkv
(self, key, val)
examples/ddpm_and_guided-diffusion/models/guided_diffusion/logger.py:347
↓ 1 callersFunctionloss_fn
Compute the loss function. Args: rng: A JAX random state. params: A dictionary that contains trainable parameters of the score-based
examples/score_sde_jax/losses.py:84
↓ 1 callersFunctionmain
()
examples/ddpm_and_guided-diffusion/main.py:243
↓ 1 callersFunctionmain
()
examples/stable-diffusion/scripts/img2img.py:60
↓ 1 callersFunctionmain
()
examples/stable-diffusion/scripts/txt2img.py:98
↓ 1 callersFunctionmake_batch
(image, mask, device)
examples/stable-diffusion/scripts/inpaint.py:11
↓ 1 callersFunctionmake_beta_schedule
(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)
examples/stable-diffusion/ldm/modules/diffusionmodules/util.py:21
↓ 1 callersMethodmake_cond_schedule
(self, )
examples/stable-diffusion/ldm/models/diffusion/ddpm.py:471
↓ 1 callersFunctionmake_convolutional_sample
(batch, model, mode="vanilla", custom_steps=None, eta=1.0, swap_mode=False, masked=False,
examples/stable-diffusion/notebook_helpers.py:208
↓ 1 callersFunctionmake_convolutional_sample
(model, batch_size, vanilla=False, custom_steps=None, eta=1.0,)
examples/stable-diffusion/scripts/sample_diffusion.py:79
↓ 1 callersFunctionmake_output_format
(format, ev_dir, log_suffix="")
examples/ddpm_and_guided-diffusion/models/guided_diffusion/logger.py:191
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
examples/stable-diffusion/ldm/models/diffusion/plms.py:24
↓ 1 callersFunctionmaster_params_to_model_params
Copy the master parameter data back into the model parameters.
examples/ddpm_and_guided-diffusion/models/guided_diffusion/fp16_util.py:65
↓ 1 callersFunctionmaster_params_to_state_dict
( model, param_groups_and_shapes, master_params, use_fp16 )
examples/ddpm_and_guided-diffusion/models/guided_diffusion/fp16_util.py:95
↓ 1 callersFunctionmax_neg_value
(tensor)
examples/stable-diffusion/ldm/modules/x_transformer.py:82
↓ 1 callersFunctionmean_flat
Take the mean over all non-batch dimensions.
examples/stable-diffusion/ldm/modules/diffusionmodules/util.py:192
↓ 1 callersFunctionmeasure_perplexity
(predicted_indices, n_embed)
examples/stable-diffusion/ldm/modules/losses/vqperceptual.py:26
↓ 1 callersFunctionmelk
(*args, **kwargs)
examples/stable-diffusion/main.py:697
← previousnext →501–600 of 1,626, ranked by callers