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
↓ 4 callersFunctiontransform
(sample)
dinov2/dinov2/data/loaders.py:34
↓ 3 callersMethod__init__
(self, start_index=1)
ldm/modules/midas/midas/vit.py:10
↓ 3 callersMethod_get_entries_path
(self, root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net_22k.py:125
↓ 3 callersMethod_get_entries_path
(self, split: "ImageNet.Split", root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:103
↓ 3 callersMethod_load_extra
(self, extra_path: str)
dinov2/dinov2/data/datasets/image_net_22k.py:187
↓ 3 callersFunction_make_encoder
(backbone, features, use_pretrained, groups=1, expand=False, exportable=True, hooks=None, use_vit_only=False,
ldm/modules/midas/midas/blocks.py:11
↓ 3 callersFunction_run
(command)
dinov2/dinov2/utils/utils.py:50
↓ 3 callersMethod_save_extra
(self, extra_array: np.ndarray, extra_path: str)
dinov2/dinov2/data/datasets/image_net.py:97
↓ 3 callersFunctionadd_blur
(img, sf=4)
ldm/modules/image_degradation/bsrgan_light.py:324
↓ 3 callersFunctionall_gather_and_flatten
(tensor_rank)
dinov2/dinov2/eval/utils.py:87
↓ 3 callersMethodbackward
(ctx, *output_grads)
ldm/modules/diffusionmodules/util.py:133
↓ 3 callersFunctionbuild_metric
(metric_type: MetricType, *, num_classes: int, ks: Optional[tuple] = None)
dinov2/dinov2/eval/metrics.py:44
↓ 3 callersFunctioncount_params
(model, verbose=False)
ldm/util.py:67
↓ 3 callersMethoddecode
(self, z)
ldm/models/autoencoder.py:88
↓ 3 callersMethoddpm_solver_first_update
DPM-Solver-1 (equivalent to DDIM) 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:469
↓ 3 callersFunctionenable_sliced_attention
()
cldm/hack.py:17
↓ 3 callersMethodencode_first_stage
(self, x)
ldm/models/diffusion/ddpm.py:833
↓ 3 callersFunctionevaluate
( model: nn.Module, data_loader, postprocessors: Dict[str, nn.Module], metrics: Dict[str, Metr
dinov2/dinov2/eval/utils.py:49
↓ 3 callersFunctionevaluate_linear_classifiers
( feature_model, linear_classifiers, data_loader, metric_type, metrics_file_path, trai
dinov2/dinov2/eval/linear.py:260
↓ 3 callersMethodforward_features
(self, x, masks=None)
dinov2/dinov2/models/vision_transformer.py:221
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
ldm/modules/image_degradation/bsrgan_light.py:209
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
ldm/modules/image_degradation/bsrgan.py:210
↓ 3 callersFunctionget_cluster_type
(cluster_type: Optional[ClusterType] = None)
dinov2/dinov2/utils/cluster.py:32
↓ 3 callersMethodget_first_stage_encoding
(self, encoder_posterior)
ldm/models/diffusion/ddpm.py:655
↓ 3 callersFunctionget_fsdp_modules
(x)
dinov2/dinov2/fsdp/__init__.py:73
↓ 3 callersMethodget_input
(self, batch, k)
ldm/models/autoencoder.py:102
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
ldm/models/diffusion/ddpm.py:367
↓ 3 callersMethodget_unconditional_conditioning
(self, batch_size, null_label=None)
ldm/models/diffusion/ddpm.py:1136
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
ldm/models/diffusion/ddpm.py:700
↓ 3 callersFunctionisimage
(x)
ldm/util.py:43
↓ 3 callersFunctionismap
(x)
ldm/util.py:37
↓ 3 callersMethodlog_images
(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)
ldm/models/diffusion/ddpm.py:477
↓ 3 callersFunctionmake_classification_eval_transform
( *, resize_size: int = 256, interpolation=transforms.InterpolationMode.BICUBIC, crop_size: in
dinov2/dinov2/data/transforms.py:78
↓ 3 callersFunctionmake_ddim_sampling_parameters
(alphacums, ddim_timesteps, eta, verbose=True)
ldm/modules/diffusionmodules/util.py:63
↓ 3 callersFunctionmake_ddim_timesteps
(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True)
ldm/modules/diffusionmodules/util.py:46
↓ 3 callersFunctionmake_normalize_transform
( mean: Sequence[float] = IMAGENET_DEFAULT_MEAN, std: Sequence[float] = IMAGENET_DEFAULT_STD, )
dinov2/dinov2/data/transforms.py:47
↓ 3 callersMethodmarginal_alpha
Compute alpha_t of a given continuous-time label t in [0, T].
ldm/models/diffusion/dpm_solver/dpm_solver.py:120
↓ 3 callersFunctionremove_ddp_wrapper
(m: nn.Module)
dinov2/dinov2/eval/linear.py:159
↓ 3 callersFunctionsetup
Create configs and perform basic setups.
dinov2/dinov2/utils/config.py:64
↓ 3 callersFunctionsetup_and_build_model
(args)
dinov2/dinov2/eval/setup.py:71
↓ 3 callersMethodshared_step
(self, batch)
ldm/models/diffusion/ddpm.py:427
↓ 3 callersMethodsinglestep_dpm_solver_second_update
Singlestep solver DPM-Solver-2 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:515
↓ 3 callersFunctionssim
(img1, img2)
ldm/modules/image_degradation/utils_image.py:669
↓ 3 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
ldm/modules/diffusionmodules/util.py:154
↓ 3 callersMethodto_rgb
(self, x)
ldm/models/autoencoder.py:192
↓ 3 callersMethodto_rgb
(self, x)
ldm/models/diffusion/ddpm.py:1315
↓ 3 callersMethodupdate
(self, preds: Tensor, target: Tensor)
dinov2/dinov2/eval/metrics.py:88
↓ 2 callersFunctionNormalize
(in_channels)
ldm/modules/attention.py:88
↓ 2 callersMethod__init__
(self)
ldm/modules/diffusionmodules/upscaling.py:58
↓ 2 callersMethod__init__
(self, classifiers_dict)
dinov2/dinov2/eval/linear.py:205
↓ 2 callersFunction_check_env_variable
(key: str, new_value: str)
dinov2/dinov2/distributed/__init__.py:146
↓ 2 callersMethod_get_class_ids_path
(self, root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net_22k.py:128
↓ 2 callersMethod_get_class_ids_path
(self, split: "ImageNet.Split", root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:106
↓ 2 callersMethod_get_class_names_path
(self, split: "ImageNet.Split", root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:109
↓ 2 callersMethod_get_knn_sims_and_labels
(self, similarity, train_labels)
dinov2/dinov2/eval/knn.py:124
↓ 2 callersMethod_get_rows_from_list
(self, samples)
ldm/models/diffusion/ddpm.py:469
↓ 2 callersFunction_get_torch_dtype
(size: int)
dinov2/dinov2/data/samplers.py:60
↓ 2 callersFunction_make_dinov2_model_name
(arch_name: str, patch_size: int)
dinov2/hubconf.py:17
↓ 2 callersMethod_save_extra
(self, extra_array: np.ndarray, extra_path: str)
dinov2/dinov2/data/datasets/image_net_22k.py:192
↓ 2 callersMethod_validation_step
(self, batch, batch_idx, postfix="")
ldm/models/autoencoder.py:136
↓ 2 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
ldm/modules/image_degradation/bsrgan_light.py:372
↓ 2 callersFunctionadd_Poisson_noise
(img)
ldm/modules/image_degradation/bsrgan.py:404
↓ 2 callersFunctionadd_resize
(img, sf=4)
ldm/modules/image_degradation/bsrgan.py:339
↓ 2 callersFunctionadd_speckle_noise
(img, noise_level1=2, noise_level2=25)
ldm/modules/image_degradation/bsrgan.py:386
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
ldm/modules/image_degradation/bsrgan_light.py:227
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
ldm/modules/image_degradation/bsrgan.py:228
↓ 2 callersFunctionbuild_model_from_cfg
(cfg, only_teacher=False)
dinov2/dinov2/models/__init__.py:40
↓ 2 callersFunctionbuild_topk_accuracy_metric
(average_type: AccuracyAveraging, num_classes: int, ks: tuple = (1, 5))
dinov2/dinov2/eval/metrics.py:60
↓ 2 callersMethodcheck_mask_area
(self, mask)
datasets/base.py:94
↓ 2 callersMethodcheck_region_size
(self, image, yyxx, ratio, mode = 'max')
datasets/base.py:46
↓ 2 callersMethodcopy_to
(self, model)
ldm/modules/ema.py:50
↓ 2 callersFunctioncount_flops_attn
A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr
ldm/modules/diffusionmodules/openaimodel.py:326
↓ 2 callersFunctioncreate_linear_input
(x_tokens_list, use_n_blocks, use_avgpool)
dinov2/dinov2/eval/linear.py:171
↓ 2 callersFunctioncubic
(x)
ldm/modules/image_degradation/utils_image.py:700
↓ 2 callersMethoddata_prediction_fn
Return the data prediction model (with thresholding).
ldm/models/diffusion/dpm_solver/dpm_solver.py:352
↓ 2 callersMethoddelta_border
:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and
ldm/models/diffusion/ddpm.py:686
↓ 2 callersFunctiondo_test
(cfg, model, iteration)
dinov2/dinov2/train/train.py:123
↓ 2 callersFunctiondrop_add_residual_stochastic_depth
( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )
dinov2/dinov2/layers/block.py:110
↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list
( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =
dinov2/dinov2/layers/block.py:181
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/autoencoder.py:64
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/diffusion/ddpm.py:195
↓ 2 callersMethodencode
(self, x0, c, t_enc, use_original_steps=False, return_intermediates=None, unconditional_guidanc
ldm/models/diffusion/ddim.py:254
↓ 2 callersFunctionevaluate_model
(*, logreg_model, logreg_metric, test_data_loader, device)
dinov2/dinov2/eval/log_regression.py:147
↓ 2 callersMethodfit
(self, train_features, train_labels)
dinov2/dinov2/eval/log_regression.py:137
↓ 2 callersMethodget_alpha_mask
(self, mask_path)
datasets/mvimagenet.py:38
↓ 2 callersFunctionget_attn_bias_and_cat
this will perform the index select, cat the tensors, and provide the attn_bias from cache
dinov2/dinov2/layers/block.py:157
↓ 2 callersMethodget_dirname
(self, class_id: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net.py:34
↓ 2 callersFunctionget_fsdp_wrapper
(model_cfg, modules_to_wrap=set())
dinov2/dinov2/fsdp/__init__.py:23
↓ 2 callersFunctionget_global_rank
Returns: The rank of the current process within the global process group.
dinov2/dinov2/distributed/__init__.py:36
↓ 2 callersFunctionget_global_size
Returns: The number of processes in the process group
dinov2/dinov2/distributed/__init__.py:28
↓ 2 callersMethodget_image_data
(self, index: int)
dinov2/dinov2/data/datasets/extended.py:18
↓ 2 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
ldm/models/diffusion/ddpm.py:769
↓ 2 callersMethodget_intermediate_layers
( self, x: torch.Tensor, n: Union[int, Sequence] = 1, # Layers or n last layers to ta
dinov2/dinov2/models/vision_transformer.py:264
↓ 2 callersFunctionget_model_input_time
Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. For discrete-time DPMs, we convert `t_continuou
ldm/models/diffusion/dpm_solver/dpm_solver.py:246
↓ 2 callersFunctionget_random_structure
(size)
datasets/data_utils.py:239
↓ 2 callersFunctionget_readout_oper
(vit_features, features, use_readout, start_index=1)
ldm/modules/midas/midas/vit.py:166
↓ 2 callersFunctionget_requirements
(path: str = HERE / "requirements.txt")
dinov2/setup.py:30
↓ 2 callersFunctionget_slurm_partition
(cluster_type: Optional[ClusterType] = None)
dinov2/dinov2/utils/cluster.py:62
↓ 2 callersFunctionget_state_dict
(d)
cldm/model.py:8
↓ 2 callersMethodget_target
(self, index: int)
dinov2/dinov2/data/datasets/extended.py:21
← previousnext →101–200 of 1,053, ranked by callers