MCPcopy Create free account

hub / github.com/ali-vilab/AnyDoor / functions

Functions1,053 in github.com/ali-vilab/AnyDoor

⨍ Functions 1,053◇ Types & classes 180
↓ 2 callersMethodget_v
(self, x, noise, t)
ldm/models/diffusion/ddpm.py:361
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/ddpm.py:210
↓ 2 callersFunctioninterpolate_fn
A piecewise linear function y = f(x), using xp and yp as keypoints. We implement f(x) in a differentiable way (i.e. applicable for autograd).
ldm/models/diffusion/dpm_solver/dpm_solver.py:1104
↓ 2 callersFunctionload_config
(config_name: str)
dinov2/dinov2/configs/__init__.py:12
↓ 2 callersFunctionmake_2tuple
(x)
dinov2/dinov2/layers/patch_embed.py:17
↓ 2 callersFunctionmake_beta_schedule
(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)
ldm/modules/diffusionmodules/util.py:21
↓ 2 callersFunctionmake_eval_data_loader
(test_dataset_str, batch_size, num_workers, metric_type)
dinov2/dinov2/eval/linear.py:411
↓ 2 callersFunctionmkdir
(path)
ldm/modules/image_degradation/utils_image.py:153
↓ 2 callersMethodmode
(self)
ldm/modules/distributions/distributions.py:20
↓ 2 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 initi
ldm/models/diffusion/dpm_solver/dpm_solver.py:855
↓ 2 callersMethodnoise_prediction_fn
Return the noise prediction model.
ldm/models/diffusion/dpm_solver/dpm_solver.py:346
↓ 2 callersMethodp_sample
(self, x, c, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=False, quantize_
ldm/models/diffusion/ddpm.py:966
↓ 2 callersMethodp_sample_ddim
(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/ddim.py:181
↓ 2 callersMethodp_sample_ddim
(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
cldm/ddim_hacked.py:182
↓ 2 callersMethodpredict_eps_from_z_and_v
(self, x_t, t, v)
ldm/models/diffusion/ddpm.py:298
↓ 2 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
ldm/models/diffusion/ddpm.py:284
↓ 2 callersMethodpredict_start_from_z_and_v
(self, x_t, t, v)
ldm/models/diffusion/ddpm.py:290
↓ 2 callersMethodprogressive_denoising
(self, cond, shape, verbose=True, callback=None, quantize_denoised=False, img_ca
ldm/models/diffusion/ddpm.py:997
↓ 2 callersMethodq_posterior
(self, x_start, x_t, t)
ldm/models/diffusion/ddpm.py:304
↓ 2 callersFunctionq_x
Adding noise for and given image.
datasets/data_utils.py:321
↓ 2 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
ldm/modules/image_degradation/bsrgan.py:427
↓ 2 callersMethodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000, linear_start=1e-4,
ldm/models/diffusion/ddpm.py:138
↓ 2 callersMethodreset_num_updates
(self)
ldm/modules/ema.py:25
↓ 2 callersMethodrestore
Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the
ldm/modules/ema.py:68
↓ 2 callersMethodsample_log
(self, cond, batch_size, ddim, ddim_steps, **kwargs)
cldm/cldm.py:415
↓ 2 callersFunctionshift_pixel
shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir
ldm/modules/image_degradation/bsrgan_light.py:98
↓ 2 callersFunctionshift_pixel
shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir
ldm/modules/image_degradation/bsrgan.py:99
↓ 2 callersMethodsinglestep_dpm_solver_third_update
Singlestep solver DPM-Solver-3 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.
ldm/models/diffusion/dpm_solver/dpm_solver.py:599
↓ 2 callersMethodsinkhorn_knopp_teacher
(self, teacher_output, teacher_temp, n_iterations=3)
dinov2/dinov2/loss/dino_clstoken_loss.py:36
↓ 2 callersMethodsoftmax_center_teacher
(self, teacher_output, teacher_temp)
dinov2/dinov2/loss/dino_clstoken_loss.py:30
↓ 2 callersMethodstore
Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be
ldm/modules/ema.py:59
↓ 2 callersMethodsynchronize_between_processes
(self)
dinov2/dinov2/logging/helpers.py:47
↓ 2 callersMethodtrain
(self)
dinov2/dinov2/train/ssl_meta_arch.py:370
↓ 2 callersFunctiontrain_for_C
(*, C, max_iter, train_features, train_labels, dtype=torch.float64, device=_CPU_DEVICE)
dinov2/dinov2/eval/log_regression.py:153
↓ 2 callersMethodupdate
(self, value, num=1)
dinov2/dinov2/logging/helpers.py:147
↓ 2 callersMethodupdate_center
(self, teacher_output)
dinov2/dinov2/loss/dino_clstoken_loss.py:78
↓ 2 callersFunctionzero_module
Zero out the parameters of a module and return it.
ldm/modules/attention.py:79
↓ 1 callersMethod__init__
( self, head, features=256, backbone="vitb_rn50_384", readout="project
ldm/modules/midas/midas/dpt_depth.py:27
↓ 1 callersMethod__init__
(self, ddconfig, lossconfig, embed_dim, ck
ldm/models/autoencoder.py:14
↓ 1 callersMethod__init__
( self, image_size, in_channels, model_channels, h
cldm/cldm.py:48
↓ 1 callersMethod__init__
(self, model)
dinov2/dinov2/eval/utils.py:23
↓ 1 callersMethod__init__
(self, train_features, train_labels, nb_knn, T, device, num_classes=1000)
dinov2/dinov2/eval/knn.py:109
↓ 1 callersMethod__init__
( self, in_features: int, hidden_features: Optional[int] = None, out_features:
dinov2/dinov2/layers/swiglu_ffn.py:14
↓ 1 callersFunction_augment
(img)
ldm/modules/image_degradation/utils_image.py:475
↓ 1 callersFunction_build_mlp
(nlayers, in_dim, bottleneck_dim, hidden_dim=None, use_bn=False, bias=True)
dinov2/dinov2/layers/dino_head.py:45
↓ 1 callersFunction_collect_env_vars
()
dinov2/dinov2/distributed/__init__.py:121
↓ 1 callersFunction_configure_logger
Configure a logger. Adapted from Detectron2. Args: name: The name of the logger to configure. level: The logging level
dinov2/dinov2/logging/__init__.py:19
↓ 1 callersMethod_dump_class_ids
(self, *args, **kwargs)
dinov2/dinov2/data/datasets/image_net_22k.py:282
↓ 1 callersMethod_dump_class_ids_and_names
(self, split: "ImageNet.Split", root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:212
↓ 1 callersMethod_dump_entries
(self, *args, **kwargs)
dinov2/dinov2/data/datasets/image_net_22k.py:244
↓ 1 callersMethod_dump_entries
(self, split: "ImageNet.Split", root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:163
↓ 1 callersMethod_dump_extra
(self, *args, **kwargs)
dinov2/dinov2/data/datasets/image_net_22k.py:299
↓ 1 callersMethod_find_class_ids
(self, path: str)
dinov2/dinov2/data/datasets/image_net_22k.py:131
↓ 1 callersMethod_gather_all_knn_for_rank
(self, topk_sims, neighbors_labels, target_rank)
dinov2/dinov2/eval/knn.py:144
↓ 1 callersFunction_generate_randperm_indices
Generate the indices of a random permutation.
dinov2/dinov2/data/samplers.py:64
↓ 1 callersFunction_get_available_port
()
dinov2/dinov2/distributed/__init__.py:102
↓ 1 callersMethod_get_intermediate_layers_chunked
(self, x, n=1)
dinov2/dinov2/models/vision_transformer.py:250
↓ 1 callersMethod_get_intermediate_layers_not_chunked
(self, x, n=1)
dinov2/dinov2/models/vision_transformer.py:238
↓ 1 callersFunction_get_master_port
(seed: int = 0)
dinov2/dinov2/distributed/__init__.py:91
↓ 1 callersFunction_get_numpy_dtype
(size: int)
dinov2/dinov2/data/samplers.py:56
↓ 1 callersFunction_get_paths_from_images
(path)
ldm/modules/image_degradation/utils_image.py:74
↓ 1 callersFunction_get_tarball_path
(class_id: str)
dinov2/dinov2/data/datasets/image_net_22k.py:57
↓ 1 callersFunction_guess_cluster_type
()
dinov2/dinov2/utils/cluster.py:19
↓ 1 callersFunction_is_slurm_job_process
()
dinov2/dinov2/distributed/__init__.py:125
↓ 1 callersMethod_iterator
(self)
dinov2/dinov2/data/samplers.py:105
↓ 1 callersMethod_iterator
(self)
dinov2/dinov2/data/samplers.py:202
↓ 1 callersMethod_load_entries_class_ids
(self, root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net_22k.py:143
↓ 1 callersMethod_load_labels
(self, root: str)
dinov2/dinov2/data/datasets/image_net.py:148
↓ 1 callersFunction_make_dinov2_linear_head
( *, model_name: str = "dinov2_vitl14", embed_dim: int = 1024, layers: int = 4, pretrained
dinov2/hubconf.py:80
↓ 1 callersFunction_make_efficientnet_backbone
(effnet)
ldm/modules/midas/midas/blocks.py:88
↓ 1 callersFunction_make_mmap_tarball
(tarballs_root: str, mmap_cache_size: int)
dinov2/dinov2/data/datasets/image_net_22k.py:61
↓ 1 callersFunction_make_pretrained_efficientnet_lite3
(use_pretrained, exportable=False)
ldm/modules/midas/midas/blocks.py:78
↓ 1 callersFunction_make_pretrained_resnext101_wsl
(use_pretrained)
ldm/modules/midas/midas/blocks.py:114
↓ 1 callersFunction_make_pretrained_vitb16_384
(pretrained, use_readout="ignore", hooks=None)
ldm/modules/midas/midas/vit.py:310
↓ 1 callersFunction_make_pretrained_vitb_rn50_384
( pretrained, use_readout="ignore", hooks=None, use_vit_only=False )
ldm/modules/midas/midas/vit.py:478
↓ 1 callersFunction_make_pretrained_vitl16_384
(pretrained, use_readout="ignore", hooks=None)
ldm/modules/midas/midas/vit.py:297
↓ 1 callersFunction_make_resnet_backbone
(resnet)
ldm/modules/midas/midas/blocks.py:101
↓ 1 callersFunction_make_sampler
( *, dataset, type: Optional[SamplerType] = None, shuffle: bool = False, seed: int = 0,
dinov2/dinov2/data/loaders.py:101
↓ 1 callersFunction_make_seed
(seed: int, start: int, iter_count: int)
dinov2/dinov2/data/samplers.py:161
↓ 1 callersFunction_make_vit_b_rn50_backbone
( model, features=[256, 512, 768, 768], size=[384, 384], hooks=[0, 1, 8, 11], vit_features
ldm/modules/midas/midas/vit.py:343
↓ 1 callersMethod_mask
(self, mask, max_mask_patches)
dinov2/dinov2/data/masking.py:50
↓ 1 callersFunction_parse_dataset_str
(dataset_str: str)
dinov2/dinov2/data/loaders.py:45
↓ 1 callersFunction_parse_slurm_node_list
(s: str)
dinov2/dinov2/distributed/__init__.py:129
↓ 1 callersFunction_restrict_print_to_main_process
This function disables printing when not in the main process
dinov2/dinov2/distributed/__init__.py:75
↓ 1 callersMethod_set_from_local
(self)
dinov2/dinov2/distributed/__init__.py:211
↓ 1 callersMethod_set_from_preset_env
(self)
dinov2/dinov2/distributed/__init__.py:199
↓ 1 callersMethod_set_from_slurm_env
(self)
dinov2/dinov2/distributed/__init__.py:182
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/linear.py:36
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/log_regression.py:36
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/knn.py:36
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/train/train.py:36
↓ 1 callersMethod_shuffled_iterator
(self)
dinov2/dinov2/data/samplers.py:112
↓ 1 callersMethod_shuffled_iterator
(self)
dinov2/dinov2/data/samplers.py:209
↓ 1 callersMethod_similarity_for_rank
(self, features_rank, source_rank)
dinov2/dinov2/eval/knn.py:129
↓ 1 callersFunctionadd_residual
(x, brange, residual, residual_scale_factor, scaling_vector=None)
dinov2/dinov2/layers/block.py:142
↓ 1 callersFunctionadd_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.py:299
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1
ldm/modules/image_degradation/bsrgan_light.py:64
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1
ldm/modules/image_degradation/bsrgan.py:65
↓ 1 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi
ldm/models/diffusion/sampling_util.py:5
↓ 1 callersMethodapply_center_update
(self)
dinov2/dinov2/loss/ibot_patch_loss.py:142
← previousnext →201–300 of 1,053, ranked by callers