Functions — github.com/Fannovel16/comfyui_controlnet

hub / github.com/Fannovel16/comfyui_controlnet_aux / functions

Functions4,192 in github.com/Fannovel16/comfyui_controlnet_aux

⨍ Functions 4,192◇ Types & classes 975↳ Endpoints 1

Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type): Expected typ

src/custom_mmpkg/custom_mmcv/utils/misc.py:128

↓ 5 callersFunctionis_tuple_of

Check whether it is a tuple of some type. A partial method of :func:`is_seq_of`.

src/custom_mmpkg/custom_mmcv/utils/misc.py:160

↓ 5 callersFunctionload_ckpt_dino

(checkpoint, model)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:1092

↓ 5 callersFunctionload_url_dist

In distributed setting, this function only download checkpoint at local rank 0.

src/custom_controlnet_aux/uniformer/mmcv_custom/checkpoint.py:109

↓ 5 callersMethodpred_x0_from_xt

(self, xt, noise, C, t)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:348

↓ 5 callersMethodrender

(self, vertices, faces=None, img=None, camera_t=np.zeros([3], dtype=np.float32),

src/custom_mesh_graphormer/utils/renderer.py:524

↓ 5 callersFunctionset_seed

(seed, n_gpu)

src/custom_mesh_graphormer/utils/miscellaneous.py:149

↓ 5 callersMethodsize

(self, *args, **kwargs)

src/custom_mmpkg/custom_mmcv/parallel/data_container.py:84

↓ 5 callersMethodto

(self, device)

src/custom_controlnet_aux/mesh_graphormer/__init__.py:26

↓ 5 callersMethodupsample

(self, x, scale_factor=2)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/HourGlassDecoder.py:221

↓ 5 callersFunctionweight_reduce_loss

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

src/custom_mmpkg/custom_mmseg/models/losses/utils.py:46

↓ 4 callersMethod__init__

Initialize BaseModule, inherited from `torch.nn.Module`

src/custom_mmpkg/custom_mmcv/runner/base_module.py:33

↓ 4 callersMethod__init__

(self, by_epoch=True, warmup=None, warmup_iters=0,

src/custom_mmpkg/custom_mmcv/runner/hooks/momentum_updater.py:9

↓ 4 callersMethod__init__

(self, in_features, hidden_features=None, out_features=None

src/custom_mmpkg/custom_mmseg/models/backbones/vit.py:36

↓ 4 callersMethod__init__

(self, depth, in_channels=3, stem_channels=64,

src/custom_mmpkg/custom_mmseg/models/backbones/resnet.py:373

↓ 4 callersMethod__init__

(self, low_in_channels, high_in_channels, channels, out_channels, query_scales, key_pool_scal

src/custom_mmpkg/custom_mmseg/models/decode_heads/ann_head.py:99

↓ 4 callersMethod__init__

(self, hidden_dim, input_dim, ks=3)

src/custom_controlnet_aux/dsine/models/submodules/__init__.py:25

↓ 4 callersMethod__init__

Imagenet Superresolution Dataloader Performs following ops in order: 1. crops a crop of size s from image either as random o

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/imagenet.py:274

↓ 4 callersMethod__init__

( self, cnf: MBConvConfig, stochastic_depth_prob: float, norm_layer: Callable[

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/efficientnet.py:106

↓ 4 callersMethod__init__

(self, num_tokens, codebook_dim, decay=0.99, eps=1e-5)

src/custom_controlnet_aux/diffusion_edge/taming/modules/vqvae/quantize.py:332

↓ 4 callersMethod__init__

(self, *args, **kwargs)

src/custom_controlnet_aux/diffusion_edge/taming/data/faceshq.py:10

↓ 4 callersMethod__str__

(self)

src/custom_mesh_graphormer/utils/tsv_file.py:56

↓ 4 callersFunction_convert_input_type_range

Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-

src/custom_mmpkg/custom_mmcv/image/colorspace.py:84

↓ 4 callersFunction_convert_output_type_range

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, im

src/custom_mmpkg/custom_mmcv/image/colorspace.py:112

↓ 4 callersFunction_isGray

(I)

src/custom_controlnet_aux/tile/guided_filter.py:27

↓ 4 callersFunction_make_divisible

This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen

src/custom_controlnet_aux/mlsd/models/mbv2_mlsd_tiny.py:71

↓ 4 callersFunction_make_fusion_block

(features, use_bn, size=None)

src/custom_controlnet_aux/depth_anything_v2/dpt.py:12

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1, dilate=False)

src/custom_controlnet_aux/leres/leres/Resnext_torch.py:172

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

src/custom_controlnet_aux/leres/leres/Resnet.py:118

↓ 4 callersMethod_make_layer

( self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int,

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/resnet.py:225

↓ 4 callersFunction_ntuple

(n)

src/custom_mmpkg/custom_mmcv/utils/misc.py:14

↓ 4 callersMethod_set_real_position

(self, frame_id)

src/custom_mmpkg/custom_mmcv/video/io.py:127

↓ 4 callersMethodadjust_channels

(channels: int, width_mult: float, min_value: Optional[int] = None)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/efficientnet.py:58

↓ 4 callersFunctionadopt_weight

(weight, global_step, threshold=0, value=0.)

src/custom_controlnet_aux/diffusion_edge/taming/modules/losses/vqperceptual.py:14

↓ 4 callersFunctionall_gather

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

src/custom_mesh_graphormer/utils/comm.py:107

↓ 4 callersMethodbuild_project

Build projection layer for key/query/value/out.

src/custom_mmpkg/custom_mmseg/models/utils/self_attention_block.py:99

↓ 4 callersFunctioncheck_file_exist

(filename, msg_tmpl='file "{}" does not exist')

src/custom_mmpkg/custom_mmcv/utils/path.py:21

↓ 4 callersMethodclear_output

(self)

src/custom_mmpkg/custom_mmcv/runner/log_buffer.py:20

↓ 4 callersMethodclose

(self)

src/custom_controlnet_aux/unimatch/utils/logger.py:103

↓ 4 callersFunctioncompress_keypoints

(keypoints: Union[List[Keypoint], None])

src/custom_controlnet_aux/open_pose/__init__.py:73

↓ 4 callersFunctioncompress_keypoints

(keypoints: Union[List[Keypoint], None])

src/custom_controlnet_aux/dwpose/__init__.py:187

↓ 4 callersFunctiondownload

(url, local_path, chunk_size=1024)

src/custom_controlnet_aux/diffusion_edge/taming/modules/losses/util.py:18

↓ 4 callersFunctiondraw_skeleton

joints is 3 x 19. but if not will transpose it. 0: Right ankle 1: Right knee 2: Right hip 3: Left hip 4: Left knee 5: Lef

src/custom_mesh_graphormer/utils/renderer.py:28

↓ 4 callersMethoddump_to_fileobj

(self, obj, file, **kwargs)

src/custom_mmpkg/custom_mmcv/fileio/handlers/base.py:17

↓ 4 callersMethodencode

(self, x)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/encoder_decoder.py:952

↓ 4 callersFunctioneval_metrics

Calculate evaluation metrics Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic

src/custom_mmpkg/custom_mmseg/core/evaluation/metrics.py:257

↓ 4 callersMethodevaluate

Evaluate the results. Args: runner (:obj:`mmcv.Runner`): The underlined training runner. results (list): Output resul

src/custom_mmpkg/custom_mmcv/runner/hooks/evaluation.py:354

↓ 4 callersFunctionexists

(x)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/utils.py:24

↓ 4 callersFunctionfit_img_postfix

(img_path)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/data.py:28

↓ 4 callersFunctionflip_kp

Flip keypoints.

src/custom_mesh_graphormer/utils/image_ops.py:180

↓ 4 callersFunctionflow_warp

(feature, flow, mask=False, padding_mode='zeros')

src/custom_controlnet_aux/unimatch/unimatch/geometry.py:65

↓ 4 callersMethodfrom_pretrained

Create OneFormer model from pretrained weights.

src/custom_controlnet_aux/oneformer/transformers.py:38

↓ 4 callersMethodfrom_pretrained

Create ZoeDetector from pretrained model.

src/custom_controlnet_aux/zoe/transformers.py:104

↓ 4 callersMethodfrom_pretrained

(cls, pretrained_model_or_path=None, model_type="dpt_hybrid", filename="dpt_hybrid-midas-501f0c75.pt")

src/custom_controlnet_aux/midas/transformers.py:29

↓ 4 callersMethodget

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding

src/custom_mmpkg/custom_mmcv/utils/registry.py:186

↓ 4 callersFunctionget_alignMesh

Do Procrustes alignment and compute reconstruction error.

src/custom_mesh_graphormer/utils/metric_pampjpe.py:91

↓ 4 callersMethodget_buffers_iter

(self, model)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ema.py:117

↓ 4 callersMethodget_last_layer

(self)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/encoder_decoder.py:1029

↓ 4 callersMethodget_line_no

(self, idx)

src/custom_mesh_graphormer/datasets/human_mesh_tsv.py:165

↓ 4 callersMethodget_line_no

(self, idx)

src/custom_mesh_graphormer/datasets/hand_mesh_tsv.py:169

↓ 4 callersFunctionget_logger

Initialize and get a logger by name. If the logger has not been initialized, this method will initialize the logger by adding one or two hand

src/custom_mmpkg/custom_mmcv/utils/logging.py:9

↓ 4 callersMethodget_metrics

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:264

↓ 4 callersMethodget_mode

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/logger/base.py:59

↓ 4 callersFunctionget_model_type

(Nodesname, filename)

src/custom_controlnet_aux/dwpose/util.py:454

↓ 4 callersMethodget_params_iter

(self, model)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ema.py:111

↓ 4 callersMethodget_preprocess_shape

Compute the output size given input size and target long side length.

src/custom_controlnet_aux/sam/utils/transforms.py:94

↓ 4 callersMethodget_ray

(self, intrins, H, W, orig_H, orig_W, return_uv=False)

src/custom_controlnet_aux/dsine/models/dsine_arch.py:91

↓ 4 callersFunctionget_world_size

()

src/custom_controlnet_aux/metric3d/mono/utils/comm.py:25

↓ 4 callersFunctionguess_onnx_input_shape_dtype

(filename)

src/custom_controlnet_aux/dwpose/util.py:423

↓ 4 callersFunctionimread

Read an image. Args: img_or_path (ndarray or str or Path): Either a numpy array or str or pathlib.Path. If it is a numpy arra

src/custom_mmpkg/custom_mmcv/image/io.py:140

↓ 4 callersFunctioninterp

(x, dest)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py:356

↓ 4 callersFunctioninterpolate_float32

(x, size=None, scale_factor=None, mode='nearest', align_corners=None)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py:218

↓ 4 callersMethodis_last_iter

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/hook.py:70

↓ 4 callersFunctionis_model_torchscript

(model)

src/custom_controlnet_aux/dwpose/util.py:451

↓ 4 callersMethodload_from_fileobj

(self, file, **kwargs)

src/custom_mmpkg/custom_mmcv/fileio/handlers/base.py:13

↓ 4 callersFunctionmake_divisible

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

src/custom_mmpkg/custom_mmseg/models/utils/make_divisible.py:1

↓ 4 callersFunctionmake_noise_disk

(H, W, C, F, rng=None)

src/custom_controlnet_aux/util.py:82

↓ 4 callersFunctionmkdir_or_exist

(dir_name, mode=0o777)

src/custom_mmpkg/custom_mmcv/utils/path.py:26

↓ 4 callersMethodnorm3

nn.Module: normalization layer after the third convolution layer

src/custom_mmpkg/custom_mmseg/models/backbones/resnet.py:260

↓ 4 callersFunctionnorm_normalize

(norm_out)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py:235

↓ 4 callersFunctionnp2tmp

Save ndarray to local numpy file. Args: array (ndarray): Ndarray to save. temp_file_name (str): Numpy file name. If 'temp_file_na

src/custom_mmpkg/custom_mmseg/apis/test.py:14

↓ 4 callersMethodprepare_tokens_with_masks

(self, x, masks=None)

src/custom_controlnet_aux/depth_anything_v2/dinov2.py:212

↓ 4 callersMethodprepare_tokens_with_masks

(self, x, masks=None)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:708

↓ 4 callersMethodprepare_tokens_with_masks

(self, x, masks=None, step=-1)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:1104

↓ 4 callersMethodprepare_tokens_with_masks

(self, x, masks=None)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:921

↓ 4 callersFunctionretrieve

Given a nested list or dict return the desired value at key expanding callable nodes if necessary and :attr:`expand` is ``True``. The expansion

src/custom_controlnet_aux/diffusion_edge/taming/modules/losses/util.py:62

↓ 4 callersMethodrun

(self, data_loaders, workflow, **kwargs)

src/custom_mmpkg/custom_mmcv/runner/base_runner.py:193

↓ 4 callersMethodsample

(self, batch_size=16, up_scale=1, cond=None, denoise=True)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:481

↓ 4 callersFunctionscatter_kwargs

Scatter with support for kwargs dictionary.

src/custom_mmpkg/custom_mmcv/parallel/scatter_gather.py:49

↓ 4 callersFunctionsetup_logger

(name, save_dir, distributed_rank, filename="log.txt")

src/custom_mesh_graphormer/utils/logger.py:82

↓ 4 callersFunctionspmm

(sparse, dense)

src/custom_mesh_graphormer/modeling/_smpl.py:162

↓ 4 callersFunctionspmm

(sparse, dense)

src/custom_mesh_graphormer/modeling/_mano.py:86

↓ 4 callersMethodstart

Start the timer.

src/custom_mmpkg/custom_mmcv/utils/timer.py:57

↓ 4 callersFunctionstrip_prefix_if_present

(state_dict, prefix)

src/custom_controlnet_aux/leres/leres/net_tools.py:47

↓ 4 callersFunctionth_with_zeros

(tensor)

src/custom_manopth/tensutils.py:15

↓ 4 callersMethodto

(self, device)

src/custom_controlnet_aux/anime_face_segment/__init__.py:33

↓ 4 callersFunctionto_tensor

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

src/custom_mmpkg/custom_mmseg/datasets/pipelines/formating.py:11

↓ 4 callersMethodtrain

(self, mode=True)

src/custom_mmpkg/custom_mmcv/cnn/vgg.py:159

↓ 4 callersMethodupdate_metrics_gpu

Update metric on GPU. It supports distributed processing. If multiple machines are employed, please set 'is_distributed' as True.

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:120

↓ 3 callersMethodIMAGE

()

utils.py:101

← previous next →201–300 of 4,192, ranked by callers