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 callersFunctionget_vit_lr_decay_rate
Calculate lr decay rate for different ViT blocks. Args: name (string): parameter name. lr_decay_rate (float): base lr decay r
dinov2/dinov2/utils/param_groups.py:14
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
ldm/modules/image_degradation/bsrgan_light.py:85
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
ldm/modules/image_degradation/bsrgan.py:86
↓ 1 callersFunctionhas_batchnorms
(model)
dinov2/dinov2/utils/utils.py:91
↓ 1 callersFunctionhas_ddp_wrapper
(m: nn.Module)
dinov2/dinov2/eval/linear.py:155
↓ 1 callersFunctionimread_uint
(path, n_channels=3)
ldm/modules/image_degradation/utils_image.py:185
↓ 1 callersFunctionimssave
imgs: list, N images of size WxHxC
ldm/modules/image_degradation/utils_image.py:112
↓ 1 callersFunctioninference_single_image
(ref_image, ref_mask, tar_image, tar_mask, guidance_scale = 5.0)
run_inference.py:150
↓ 1 callersFunctioninference_single_image
(ref_image, ref_mask, tar_image,
run_gradio_demo.py:73
↓ 1 callersMethodinference_single_image
(self, ref_image, ref_mask, tar_image, tar_mask, strength, ddim_steps, guidance_scale, seed, enable_shape_cont
predict.py:159
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
ldm/models/autoencoder.py:52
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/ddpm.py:1533
↓ 1 callersMethodinit_weights
(self)
dinov2/dinov2/models/vision_transformer.py:160
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/ddpm.py:622
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/ddpm.py:615
↓ 1 callersMethodinstantiate_low_stage
(self, config)
ldm/models/diffusion/ddpm.py:1375
↓ 1 callersMethodinstantiate_low_stage
(self, config)
ldm/models/diffusion/ddpm.py:1764
↓ 1 callersMethodinterpolate_pos_encoding
(self, x, w, h)
dinov2/dinov2/models/vision_transformer.py:165
↓ 1 callersFunctionis_fsdp
(x)
dinov2/dinov2/fsdp/__init__.py:58
↓ 1 callersFunctionis_image_file
(filename)
ldm/modules/image_degradation/utils_image.py:29
↓ 1 callersFunctionis_main_process
Returns: True if the current process is the main one.
dinov2/dinov2/distributed/__init__.py:67
↓ 1 callersFunctionis_sharded_fsdp
(x)
dinov2/dinov2/fsdp/__init__.py:62
↓ 1 callersFunctionload_midas_transform
(model_type)
ldm/modules/midas/api.py:28
↓ 1 callersFunctionload_model
(model_type)
ldm/modules/midas/api.py:73
↓ 1 callersMethodload_pretrained_weights
(self, path_to_weights= ' ')
iseg/coarse_mask_refine_util.py:212
↓ 1 callersMethodlog_images
(self, batch, N=4, n_row=2, sample=False, ddim_steps=50, ddim_eta=0.0, return_keys=None, qu
cldm/cldm.py:348
↓ 1 callersMethodlog_img
(self, pl_module, batch, batch_idx, split="train")
cldm/logger.py:42
↓ 1 callersMethodlog_local
(self, save_dir, split, images, global_step, current_epoch, batch_idx)
cldm/logger.py:28
↓ 1 callersFunctionlossfunc
(t, s, temp)
dinov2/dinov2/loss/ibot_patch_loss.py:21
↓ 1 callersFunctionmain
(args)
dinov2/dinov2/eval/linear.py:595
↓ 1 callersFunctionmain
(args)
dinov2/dinov2/eval/log_regression.py:423
↓ 1 callersFunctionmain
(args)
dinov2/dinov2/eval/knn.py:379
↓ 1 callersFunctionmain
(args)
dinov2/dinov2/train/train.py:298
↓ 1 callersFunctionmain
()
dinov2/dinov2/run/eval/linear.py:45
↓ 1 callersFunctionmain
()
dinov2/dinov2/run/eval/log_regression.py:45
↓ 1 callersFunctionmain
()
dinov2/dinov2/run/eval/knn.py:45
↓ 1 callersFunctionmain
()
dinov2/dinov2/run/train/train.py:45
↓ 1 callersFunctionmake_classification_train_transform
( *, crop_size: int = 224, interpolation=transforms.InterpolationMode.BICUBIC, hflip_prob: flo
dinov2/dinov2/data/transforms.py:56
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/ddpm.py:584
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
ldm/models/diffusion/ddim.py:23
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
ldm/models/diffusion/plms.py:25
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
cldm/ddim_hacked.py:23
↓ 1 callersFunctionmask_score
Scoring the mask according to connectivity.
datasets/data_utils.py:6
↓ 1 callersFunctionmean_flat
Take the mean over all non-batch dimensions.
ldm/modules/diffusionmodules/util.py:195
↓ 1 callersFunctionmobilenet_v2
(norm_layer=nn.BatchNorm2d)
iseg/coarse_mask_refine_util.py:157
↓ 1 callersFunctionmodel_wrapper
Create a wrapper function for the noise prediction model. DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discre
ldm/models/diffusion/dpm_solver/dpm_solver.py:161
↓ 1 callersMethodmultistep_dpm_solver_second_update
Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at ti
ldm/models/diffusion/dpm_solver/dpm_solver.py:723
↓ 1 callersMethodmultistep_dpm_solver_third_update
Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at ti
ldm/models/diffusion/dpm_solver/dpm_solver.py:780
↓ 1 callersFunctionnamed_apply
(fn: Callable, module: nn.Module, name="", depth_first=True, include_root=False)
dinov2/dinov2/models/vision_transformer.py:27
↓ 1 callersFunctionnorm_thresholding
(x0, value)
ldm/models/diffusion/sampling_util.py:14
↓ 1 callersFunctionnormal_kl
source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12 Compute the K
ldm/modules/distributions/distributions.py:65
↓ 1 callersMethodp_losses
(self, x_start, t, noise=None)
ldm/models/diffusion/ddpm.py:382
↓ 1 callersMethodp_losses
(self, x_start, cond, t, noise=None)
ldm/models/diffusion/ddpm.py:889
↓ 1 callersMethodp_mean_variance
(self, x, t, clip_denoised: bool)
ldm/models/diffusion/ddpm.py:313
↓ 1 callersMethodp_mean_variance
(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
ldm/models/diffusion/ddpm.py:934
↓ 1 callersMethodp_sample
(self, x, t, clip_denoised=True, repeat_noise=False)
ldm/models/diffusion/ddpm.py:326
↓ 1 callersMethodp_sample_loop
(self, shape, return_intermediates=False)
ldm/models/diffusion/ddpm.py:335
↓ 1 callersMethodp_sample_loop
(self, cond, shape, return_intermediates=False, x_T=None, verbose=True, callback=None, t
ldm/models/diffusion/ddpm.py:1053
↓ 1 callersMethodp_sample_plms
(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/plms.py:178
↓ 1 callersFunctionpad
(x, p, i)
cldm/hack.py:50
↓ 1 callersMethodpairwise_NNs_inner
Pairwise nearest neighbors for L2-normalized vectors. Uses Torch rather than Faiss to remain on GPU.
dinov2/dinov2/loss/koleo_loss.py:26
↓ 1 callersMethodparse_image_relpath
(self, image_relpath: str)
dinov2/dinov2/data/datasets/image_net.py:45
↓ 1 callersFunctionpatches_from_image
(img, p_size=512, p_overlap=64, p_max=800)
ldm/modules/image_degradation/utils_image.py:93
↓ 1 callersFunctionperturb_mask
(gt, min_iou = 0.3, max_iou = 0.99)
datasets/data_utils.py:283
↓ 1 callersMethodplms_sampling
(self, cond, shape, x_T=None, ddim_use_original_steps=False, callb
ldm/models/diffusion/plms.py:118
↓ 1 callersMethodprepare_for_distributed_training
(self)
dinov2/dinov2/train/ssl_meta_arch.py:393
↓ 1 callersMethodprepare_input
(self, image)
iseg/coarse_mask_refine_util.py:263
↓ 1 callersFunctionprocess_image_mask
(image_np, mask_np)
run_gradio_demo.py:45
↓ 1 callersFunctionprocess_pairs
(ref_image, ref_mask, tar_image, tar_mask, max_ratio = 0.8, enable_shape_control = False)
predict.py:31
↓ 1 callersFunctionprocess_pairs
(ref_image, ref_mask, tar_image, tar_mask)
run_inference.py:46
↓ 1 callersFunctionprocess_pairs
(ref_image, ref_mask, tar_image, tar_mask, max_ratio = 0.8, enable_shape_control = False)
run_gradio_demo.py:136
↓ 1 callersMethodpt2np
(self, x)
ldm/data/util.py:11
↓ 1 callersMethodq_mean_variance
Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff
ldm/models/diffusion/ddpm.py:272
↓ 1 callersMethodq_sample
(self, x_start, t, noise=None)
ldm/modules/diffusionmodules/upscaling.py:44
↓ 1 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
ldm/modules/image_degradation/bsrgan_light.py:430
↓ 1 callersFunctionrandom_dilate
(seg, min=3, max=10)
datasets/data_utils.py:251
↓ 1 callersFunctionrandom_erode
(seg, min=3, max=10)
datasets/data_utils.py:257
↓ 1 callersMethodreduce_center_update
(self, teacher_patch_tokens)
dinov2/dinov2/loss/ibot_patch_loss.py:134
↓ 1 callersMethodreduce_center_update
(self, teacher_output)
dinov2/dinov2/loss/dino_clstoken_loss.py:82
↓ 1 callersMethodregister_buffer
(self, name, attr)
ldm/models/diffusion/dpm_solver/sampler.py:20
↓ 1 callersMethodregister_schedule
(self, beta_schedule="linear", timesteps=1000, linear_start=1e-4, linear_end=2e-2, c
ldm/modules/diffusionmodules/upscaling.py:17
↓ 1 callersFunctionreshard_fsdp_model
(x)
dinov2/dinov2/fsdp/__init__.py:77
↓ 1 callersFunctionrun_eval_linear
( model, output_dir, train_dataset_str, val_dataset_str, batch_size, epochs, epoch
dinov2/dinov2/eval/linear.py:463
↓ 1 callersMethodsample
(self, S, batch_size, shape, conditioning=None,
ldm/models/diffusion/ddim.py:55
↓ 1 callersMethodsample
(self, cond, batch_size=16, return_intermediates=False, x_T=None, verbose=True, timesteps=None,
ldm/models/diffusion/ddpm.py:1104
↓ 1 callersMethodsample
Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. ==========================================
ldm/models/diffusion/dpm_solver/dpm_solver.py:939
↓ 1 callersFunctionscale_lr
(learning_rates, batch_size)
dinov2/dinov2/eval/linear.py:231
↓ 1 callersFunctionselect_max_region
(mask)
datasets/data_utils.py:269
↓ 1 callersFunctionsetup_linear_classifiers
(sample_output, n_last_blocks_list, learning_rates, batch_size, num_classes=1000)
dinov2/dinov2/eval/linear.py:235
↓ 1 callersMethodsinglestep_dpm_solver_update
Singlestep DPM-Solver with the order `order` from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at t
ldm/models/diffusion/dpm_solver/dpm_solver.py:827
↓ 1 callersFunctionsplit
(x)
cldm/hack.py:47
↓ 1 callersFunctionsweep_C_values
( *, train_features, train_labels, test_data_loader, metric_type, num_classes, tra
dinov2/dinov2/eval/log_regression.py:187
↓ 1 callersMethodtag_last_checkpoint
Tag the last checkpoint. Args: last_filename_basename (str): the basename of the last filename.
dinov2/dinov2/fsdp/__init__.py:144
↓ 1 callersFunctiontest_on_datasets
( feature_model, linear_classifiers, test_dataset_strs, batch_size, num_workers, test_
dinov2/dinov2/eval/linear.py:429
↓ 1 callersMethodtext_transformer_forward
(self, x: torch.Tensor, attn_mask = None)
ldm/modules/encoders/modules.py:201
↓ 1 callersFunctiontokenize
(t)
cldm/hack.py:37
↓ 1 callersFunctiontrain_and_evaluate
( *, C, max_iter, train_features, train_labels, logreg_metric, test_data_loader,
dinov2/dinov2/eval/log_regression.py:159
↓ 1 callersFunctiontransformer_encode
(t)
cldm/hack.py:40
↓ 1 callersMethodupdate_teacher
(self, m)
dinov2/dinov2/train/ssl_meta_arch.py:359
↓ 1 callersFunctionvis_sample
(item)
run_dataset_debug.py:38
← previousnext →401–500 of 1,053, ranked by callers