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
↓ 1 callersMethodapply_center_update
(self)
dinov2/dinov2/loss/dino_clstoken_loss.py:90
↓ 1 callersFunctionapply_optim_scheduler
(optimizer, lr, wd, last_layer_lr)
dinov2/dinov2/train/train.py:114
↓ 1 callersFunctionapply_scaling_rules_to_cfg
(cfg)
dinov2/dinov2/utils/config.py:22
↓ 1 callersFunctionas_torch_dtype
(dtype: TypeSpec)
dinov2/dinov2/utils/dtype.py:32
↓ 1 callersMethodaug_data_mask
(self, image, mask)
datasets/base.py:33
↓ 1 callersFunctionaugment_img
Kai Zhang (github: https://github.com/cszn)
ldm/modules/image_degradation/utils_image.py:380
↓ 1 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
ldm/modules/diffusionmodules/util.py:241
↓ 1 callersMethodbackbone_forward
(self, image, coord_features=None)
iseg/coarse_mask_refine_util.py:258
↓ 1 callersMethodbackprop_loss
(self, loss)
dinov2/dinov2/train/ssl_meta_arch.py:129
↓ 1 callersFunctionbgr2ycbcr
bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]
ldm/modules/image_degradation/utils_image.py:573
↓ 1 callersFunctionbuild_model
(args, only_teacher=False, img_size=224)
dinov2/dinov2/models/__init__.py:15
↓ 1 callersFunctionbuild_model_for_eval
(config, pretrained_weights)
dinov2/dinov2/eval/setup.py:63
↓ 1 callersFunctionbuild_optimizer
(cfg, params_groups)
dinov2/dinov2/train/train.py:62
↓ 1 callersFunctionbuild_schedulers
(cfg)
dinov2/dinov2/train/train.py:66
↓ 1 callersFunctionbuild_topk_imagenet_real_accuracy_metric
(num_classes: int, ks: tuple = (1, 5))
dinov2/dinov2/eval/metrics.py:67
↓ 1 callersMethodcheck_connect
(self, mask)
datasets/mose.py:90
↓ 1 callersMethodcheck_connect
(self, mask)
datasets/vipseg.py:92
↓ 1 callersMethodcheck_frequency
(self, check_idx)
cldm/logger.py:71
↓ 1 callersMethodcompute
(self)
dinov2/dinov2/eval/metrics.py:112
↓ 1 callersFunctioncompute_iou
(seg, gt)
datasets/data_utils.py:263
↓ 1 callersMethodcompute_neighbors
(self, features_rank)
dinov2/dinov2/eval/knn.py:162
↓ 1 callersFunctioncond_grad_fn
Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).
ldm/models/diffusion/dpm_solver/dpm_solver.py:280
↓ 1 callersFunctioncreate_class_indices_mapping
(labels)
dinov2/dinov2/eval/knn.py:234
↓ 1 callersFunctioncreate_module_dict
(*, module, n_per_class_list, n_tries, nb_knn, train_features, train_labels)
dinov2/dinov2/eval/knn.py:198
↓ 1 callersFunctioncrop_back
( pred, tar_image, extra_sizes, tar_box_yyxx_crop)
predict.py:117
↓ 1 callersFunctioncrop_back
( pred, tar_image, extra_sizes, tar_box_yyxx_crop)
run_inference.py:126
↓ 1 callersFunctioncrop_back
( pred, tar_image, extra_sizes, tar_box_yyxx_crop)
run_gradio_demo.py:52
↓ 1 callersMethodddim_sampling
(self, cond, shape, x_T=None, ddim_use_original_steps=False, callb
ldm/models/diffusion/ddim.py:123
↓ 1 callersMethodddim_sampling
(self, cond, shape, x_T=None, ddim_use_original_steps=False, callb
cldm/ddim_hacked.py:123
↓ 1 callersFunctiondefault_setup
(args)
dinov2/dinov2/utils/config.py:50
↓ 1 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.
ldm/models/diffusion/dpm_solver/dpm_solver.py:463
↓ 1 callersFunctiondo_train
(cfg, model, resume=False)
dinov2/dinov2/train/train.py:135
↓ 1 callersFunctiondownload
(url, dest)
predict.py:24
↓ 1 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`.
ldm/models/diffusion/dpm_solver/dpm_solver.py:878
↓ 1 callersFunctiondrop_path
(x, drop_prob: float = 0.0, training: bool = False)
dinov2/dinov2/layers/drop_path.py:15
↓ 1 callersMethoddump_in_output_file
(self, iteration, iter_time, data_time)
dinov2/dinov2/logging/helpers.py:54
↓ 1 callersMethodencode
(self, x)
ldm/models/autoencoder.py:82
↓ 1 callersMethodencode_with_transformer
(self, text)
ldm/modules/encoders/modules.py:192
↓ 1 callersFunctioneval_knn
( model, train_dataset, val_dataset, accuracy_averaging, nb_knn, temperature, batc
dinov2/dinov2/eval/knn.py:245
↓ 1 callersFunctioneval_knn_with_model
( model, output_dir, train_dataset_str="ImageNet:split=TRAIN", val_dataset_str="ImageNet:split
dinov2/dinov2/eval/knn.py:318
↓ 1 callersFunctioneval_linear
( *, feature_model, linear_classifiers, train_data_loader, val_data_loader, metrics_fi
dinov2/dinov2/eval/linear.py:313
↓ 1 callersFunctioneval_log_regression
Implements the "standard" process for log regression evaluation: The value of C is chosen by training on train_dataset and evaluating on
dinov2/dinov2/eval/log_regression.py:252
↓ 1 callersFunctioneval_log_regression_with_model
( model, train_dataset_str="ImageNet:split=TRAIN", val_dataset_str="ImageNet:split=VAL", finet
dinov2/dinov2/eval/log_regression.py:362
↓ 1 callersMethodexport
(self, *, overwrite: bool)
dinov2/dinov2/distributed/__init__.py:220
↓ 1 callersFunctionextract_features_with_dataloader
(model, data_loader, sample_count, gather_on_cpu=False)
dinov2/dinov2/eval/utils.py:114
↓ 1 callersFunctionfilter_train
(mapping, n_per_class, seed)
dinov2/dinov2/eval/knn.py:225
↓ 1 callersMethodforward
(self, x)
ldm/modules/diffusionmodules/util.py:213
↓ 1 callersMethodforward
(self, x, t=None, context=None)
ldm/modules/diffusionmodules/model.py:400
↓ 1 callersMethodforward
(self, x)
ldm/modules/midas/midas/dpt_depth.py:67
↓ 1 callersMethodforward
(self, x: Tensor)
dinov2/dinov2/layers/block.py:82
↓ 1 callersMethodforward
(self, x: Tensor)
dinov2/dinov2/layers/attention.py:49
↓ 1 callersMethodforward_backward
(self, images, teacher_temp)
dinov2/dinov2/train/ssl_meta_arch.py:135
↓ 1 callersMethodforward_features_list
(self, x_list, masks_list)
dinov2/dinov2/models/vision_transformer.py:202
↓ 1 callersMethodforward_masked
( self, student_patch_tokens_masked, teacher_patch_tokens_masked, student_mask
dinov2/dinov2/loss/ibot_patch_loss.py:106
↓ 1 callersMethodforward_nested
x_list contains a list of tensors to nest together and run
dinov2/dinov2/layers/block.py:205
↓ 1 callersFunctionforward_vit
(pretrained, x)
ldm/modules/midas/midas/vit.py:56
↓ 1 callersFunctionfree_if_fsdp
(x)
dinov2/dinov2/fsdp/__init__.py:66
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:88
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:130
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:182
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:253
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:296
↓ 1 callersMethodfsdp_synchronize_streams
(self)
dinov2/dinov2/train/ssl_meta_arch.py:351
↓ 1 callersFunctionfspecial_gaussian
(hsize, sigma)
ldm/modules/image_degradation/bsrgan_light.py:186
↓ 1 callersFunctionfspecial_gaussian
(hsize, sigma)
ldm/modules/image_degradation/bsrgan.py:187
↓ 1 callersFunctionfspecial_laplacian
(alpha)
ldm/modules/image_degradation/bsrgan_light.py:200
↓ 1 callersFunctionfspecial_laplacian
(alpha)
ldm/modules/image_degradation/bsrgan.py:201
↓ 1 callersFunctionfuse_params_groups
(all_params_groups, keys=("lr_multiplier", "wd_multiplier", "is_last_layer"))
dinov2/dinov2/utils/param_groups.py:83
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = [], add_he
dinov2/dinov2/eval/linear.py:34
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = [], add_he
dinov2/dinov2/eval/log_regression.py:39
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = [], add_he
dinov2/dinov2/eval/knn.py:30
↓ 1 callersFunctionget_args_parser
(add_help: bool = True)
dinov2/dinov2/train/train.py:31
↓ 1 callersFunctionget_autocast_dtype
(config)
dinov2/dinov2/eval/setup.py:53
↓ 1 callersFunctionget_branges_scales
(x, sample_drop_ratio=0.0)
dinov2/dinov2/layers/block.py:134
↓ 1 callersFunctionget_cfg_from_args
(args)
dinov2/dinov2/utils/config.py:41
↓ 1 callersFunctionget_checkpoint_path
(cluster_type: Optional[ClusterType] = None)
dinov2/dinov2/utils/cluster.py:39
↓ 1 callersMethodget_class_id
(self, index: int)
dinov2/dinov2/data/datasets/image_net.py:136
↓ 1 callersFunctionget_image_paths
(dataroot)
ldm/modules/image_degradation/utils_image.py:67
↓ 1 callersMethodget_image_relpath
(self, actual_index: int, class_id: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:37
↓ 1 callersMethodget_input
(self, batch, k, cond_key=None, bs=None, log_mode=False)
ldm/models/diffusion/ddpm.py:1383
↓ 1 callersMethodget_input
(self, batch, k, bs=None, *args, **kwargs)
cldm/cldm.py:317
↓ 1 callersMethodget_maybe_fused_params_for_submodel
(self, m)
dinov2/dinov2/train/ssl_meta_arch.py:374
↓ 1 callersFunctionget_node_name
(name, parent_name)
tool_add_control_sd21.py:18
↓ 1 callersFunctionget_obj_from_str
(string, reload=False)
ldm/util.py:84
↓ 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 evalua
ldm/models/diffusion/dpm_solver/dpm_solver.py:405
↓ 1 callersFunctionget_package_version
()
dinov2/setup.py:43
↓ 1 callersMethodget_params_groups
(self)
dinov2/dinov2/train/ssl_meta_arch.py:387
↓ 1 callersFunctionget_params_groups_with_decay
(model, lr_decay_rate=1.0, patch_embed_lr_mult=1.0)
dinov2/dinov2/utils/param_groups.py:42
↓ 1 callersMethodget_sample
(self, idx)
datasets/uvo_val.py:53
↓ 1 callersMethodget_sample
(self, idx)
datasets/dreambooth.py:55
↓ 1 callersMethodget_sample
(self, idx)
datasets/base.py:70
↓ 1 callersMethodget_shape
(self)
dinov2/dinov2/data/masking.py:47
↓ 1 callersFunctionget_shared_folder
()
dinov2/dinov2/run/submit.py:83
↓ 1 callersMethodget_size
(self, width, height)
ldm/modules/midas/midas/transforms.py:105
↓ 1 callersFunctionget_slurm_executor_parameters
( nodes: int, num_gpus_per_node: int, cluster_type: Optional[ClusterType] = None, **kwargs )
dinov2/dinov2/utils/cluster.py:75
↓ 1 callersMethodget_targets
(self)
dinov2/dinov2/data/datasets/image_net.py:133
↓ 1 callersFunctionget_timestamp
()
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
ldm/modules/diffusionmodules/model.py:20
↓ 1 callersMethodget_unconditional_conditioning
(self, N)
cldm/cldm.py:343
↓ 1 callersFunctionget_user_checkpoint_path
(cluster_type: Optional[ClusterType] = None)
dinov2/dinov2/utils/cluster.py:52
← previousnext →301–400 of 1,053, ranked by callers