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

↓ 2 callersFunctionbuild_loss

Build loss.

src/custom_mmpkg/custom_mmseg/models/builder.py:30

↓ 2 callersFunctionbuild_segmentor

Build segmentor.

src/custom_mmpkg/custom_mmseg/models/builder.py:35

↓ 2 callersFunctioncheck_outside_inside

(segments_info, connect_idx)

src/custom_controlnet_aux/mlsd/utils.py:410

↓ 2 callersFunctioncheck_path

(path)

src/custom_controlnet_aux/unimatch/utils/misc.py:13

↓ 2 callersFunctioncheck_prerequisites

A decorator factory to check if prerequisites are satisfied. Args: prerequisites (str of list[str]): Prerequisites to be checked.

src/custom_mmpkg/custom_mmcv/utils/misc.py:206

↓ 2 callersFunctionclamp

(value, min_value=None, max_value=None)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ema.py:10

↓ 2 callersFunctionclamp

(x: float)

src/custom_controlnet_aux/diffusion_edge/taming/data/conditional_builder/utils.py:46

↓ 2 callersMethodclean_up_annotations_and_image_descriptions

(self)

src/custom_controlnet_aux/diffusion_edge/taming/data/annotated_objects_dataset.py:154

↓ 2 callersFunctioncollate

Puts each data field into a tensor/DataContainer with outer dimension batch size. Extend default_collate to add support for :type:`~mmcv.

src/custom_mmpkg/custom_mmcv/parallel/collate.py:11

↓ 2 callersFunctionconfig_save_file

(tsv_file, save_file=None, append_str='.new.tsv')

src/custom_mesh_graphormer/utils/tsv_file_ops.py:61

↓ 2 callersMethodcontrast

Contrast distortion.

src/custom_mmpkg/custom_mmseg/datasets/pipelines/transforms.py:819

↓ 2 callersFunctionconv3x3

3x3 convolution with padding.

src/custom_mmpkg/custom_mmcv/cnn/resnet.py:10

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net_gridfeat.py:30

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net.py:30

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/custom_controlnet_aux/leres/leres/Resnet.py:17

↓ 2 callersFunctionconvex_upsampling

(out, up_mask, k)

src/custom_controlnet_aux/dsine/models/submodules/__init__.py:145

↓ 2 callersFunctioncoords_grid

(batch, ht, wd)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py:229

↓ 2 callersFunctioncoords_grid

(batch, ht, wd, normalize=False)

src/custom_controlnet_aux/unimatch/utils/utils.py:61

↓ 2 callersMethodcopy_grads_to_fp32

Copy gradients from fp16 model to fp32 weight copy.

src/custom_mmpkg/custom_mmcv/runner/hooks/optimizer.py:193

↓ 2 callersMethodcopy_params_from_model_to_ema

(self)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ema.py:123

↓ 2 callersMethodcopy_params_to_fp16

Copy updated params from fp32 weight copy to fp16 model.

src/custom_mmpkg/custom_mmcv/runner/hooks/optimizer.py:203

↓ 2 callersFunctioncrop

Crop image according to the supplied bounding box.

src/custom_mesh_graphormer/utils/image_ops.py:97

↓ 2 callersFunctioncrop_len

(orig_len, n_crops, overlap)

src/custom_controlnet_aux/sam/utils/amg.py:215

↓ 2 callersMethodcurrent_lr

Get current learning rates. Returns: list[float] | dict[str, list[float]]: Current learning rates of all param gr

src/custom_mmpkg/custom_mmcv/runner/base_runner.py:205

↓ 2 callersFunctioncustom_hf_download

Download model files from HuggingFace Hub

src/custom_controlnet_aux/dsine/__init__.py:97

↓ 2 callersFunctioncycle

(dl)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/utils.py:35

↓ 2 callersFunctiondeccode_output_score_and_ptss

tpMap: center: tpMap[1, 0, :, :] displacement: tpMap[1, 1:5, :, :]

src/custom_controlnet_aux/mlsd/utils.py:19

↓ 2 callersFunctiondecode_json_as_poses

Decode the json_string complying with the openpose JSON output format to poses that controlnet recognizes. https://github.com/CMU-Perceptual-C

src/custom_controlnet_aux/dwpose/__init__.py:125

↓ 2 callersFunctiondenormalize

Denormalize input grid from range [0, 1] to [-1, 1] Args: grid (Tensor): The grid to be denormalize, range [0, 1]. Returns: Te

src/custom_mmpkg/custom_mmcv/ops/point_sample.py:105

↓ 2 callersFunctiondoubleestimate

(img, size1, size2, pix2pixsize, model, net_type, pix2pixmodel)

src/custom_controlnet_aux/leres/leres/depthmap.py:132

↓ 2 callersFunctiondrawBetweenKeypointsList

(pose_img, keypoints, keypointPairsList, colorsList, scaleFactor)

src/custom_controlnet_aux/dwpose/animalpose.py:30

↓ 2 callersFunctiondraw_poses

Draw the detected poses on an empty canvas. Args: poses (List[PoseResult]): A list of PoseResult objects containing the detected pos

src/custom_controlnet_aux/dwpose/__init__.py:94

↓ 2 callersFunctiondraw_text

content is a dict. draws key: val on image Assumes key is str, val is float

src/custom_mesh_graphormer/utils/renderer.py:235

↓ 2 callersFunctiondrop_add_residual_stochastic_depth

( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )

src/custom_controlnet_aux/depth_anything_v2/dinov2_layers/block.py:110

↓ 2 callersFunctiondrop_add_residual_stochastic_depth

( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, attn_bias=

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:392

↓ 2 callersFunctiondrop_add_residual_stochastic_depth

( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, attn_bias=

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:574

↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list

( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =

src/custom_controlnet_aux/depth_anything_v2/dinov2_layers/block.py:181

↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list

( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:463

↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list

( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:645

↓ 2 callersFunctionefficientnet_b7

EfficientNet B7 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks <https://arxiv.org/abs/1905.

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/efficientnet.py:969

↓ 2 callersMethodend_of_epoch

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/hook.py:64

↓ 2 callersFunctionestimateleres

(img, model, w, h)

src/custom_controlnet_aux/leres/leres/depthmap.py:35

↓ 2 callersMethodevaluate

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

src/custom_mmpkg/custom_mmseg/datasets/custom.py:305

↓ 2 callersMethodextract_feat

Extract features from images.

src/custom_mmpkg/custom_mmseg/models/segmentors/encoder_decoder.py:77

↓ 2 callersMethodfilter

(self, p)

src/custom_controlnet_aux/tile/guided_filter.py:116

↓ 2 callersMethodfilter_categories

(self)

src/custom_controlnet_aux/diffusion_edge/taming/data/annotated_objects_dataset.py:136

↓ 2 callersMethodfilter_object_number

(all_annotations: Dict[str, List[Annotation]], min_object_area: float, min_object

src/custom_controlnet_aux/diffusion_edge/taming/data/annotated_objects_dataset.py:160

↓ 2 callersFunctionfind_model_using_name

Import the module "models/[model_name]_model.py". In the file, the class called DatasetNameModel() will be instantiated. It has to be a subcl

src/custom_controlnet_aux/leres/pix2pix/models/__init__.py:25

↓ 2 callersFunctionflatten_binary_logits

Flattens predictions in the batch (binary case) Remove labels equal to 'ignore_index'.

src/custom_mmpkg/custom_mmseg/models/losses/lovasz_loss.py:29

↓ 2 callersFunctionflatten_probs

Flattens predictions in the batch.

src/custom_mmpkg/custom_mmseg/models/losses/lovasz_loss.py:42

↓ 2 callersFunctionflip_img

Flip rgb images or masks. channels come last, e.g. (256,256,3).

src/custom_mesh_graphormer/utils/image_ops.py:173

↓ 2 callersFunctionflip_pose

Flip pose. The flipping is based on SMPL parameters.

src/custom_mesh_graphormer/utils/image_ops.py:187

↓ 2 callersFunctionflops_to_string

Convert FLOPs number into a string. Note that Here we take a multiply-add counts as one FLOP. Args: flops (float): FLOPs number to b

src/custom_mmpkg/custom_mmcv/cnn/utils/flops_counter.py:118

↓ 2 callersFunctionflow_tensor_to_image

Used for tensorboard visualization

src/custom_controlnet_aux/unimatch/utils/flow_viz.py:283

↓ 2 callersMethodformat_body_result

Format the body results from the candidate and subset arrays into a list of BodyResult objects. Args: candidate

src/custom_controlnet_aux/open_pose/body.py:232

↓ 2 callersMethodforward

(target_gpus, input)

src/custom_mmpkg/custom_mmcv/parallel/_functions.py:67

↓ 2 callersMethodforward

Placeholder of forward function.

src/custom_mmpkg/custom_mmseg/models/decode_heads/decode_head.py:166

↓ 2 callersMethodforward

(self, fine_grained_point_feats, coarse_point_feats)

src/custom_mmpkg/custom_mmseg/models/decode_heads/point_head.py:116

↓ 2 callersMethodforward

Forward function.

src/custom_mmpkg/custom_mmseg/models/decode_heads/enc_head.py:129

↓ 2 callersMethodforward

Placeholder of forward function.

src/custom_mmpkg/custom_mmseg/models/decode_heads/cascade_decode_head.py:14

↓ 2 callersMethodforward

(self, x: Tensor)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:185

↓ 2 callersMethodforward

(self, x: Tensor)

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:285

↓ 2 callersMethodforward_single

Scatters points into voxels. Args: points (torch.Tensor): Points to be reduced into voxels. coors (torch.Tensor): Cor

src/custom_mmpkg/custom_mmcv/ops/scatter_points.py:82

↓ 2 callersMethodforward_with_coords

Positionally encode points that are not normalized to [0,1].

src/custom_controlnet_aux/sam/modeling/prompt_encoder.py:207

↓ 2 callersMethodfrom_pretrained

Create DepthAnything from pretrained model, mapping legacy names to HuggingFace models.

src/custom_controlnet_aux/depth_anything/transformers.py:28

↓ 2 callersMethodgather_options

Initialize our parser with basic options(only once). Add additional model-specific and dataset-specific options. These options are def

src/custom_controlnet_aux/leres/pix2pix/options/base_options.py:79

↓ 2 callersMethodget

Read data from a given ``filepath`` with 'rb' mode. Args: filepath (str or Path): Path to read data. Returns:

src/custom_mmpkg/custom_mmcv/fileio/file_client.py:147

↓ 2 callersFunctiongetGF_fromintegral

(integralimage, rect)

src/custom_controlnet_aux/leres/leres/depthmap.py:210

↓ 2 callersFunctionget_absrel_err

Computes absolute relative error. Tasks preprocessed depths (no nans, infs and non-positive values). pred, target, and mask should be in

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:281

↓ 2 callersFunctionget_attn_bias_and_cat

this will perform the index select, cat the tensors, and provide the attn_bias from cache

src/custom_controlnet_aux/depth_anything_v2/dinov2_layers/block.py:157

↓ 2 callersFunctionget_attn_bias_and_cat

this will perform the index select, cat the tensors, and provide the attn_bias from cache

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO.py:439

↓ 2 callersFunctionget_attn_bias_and_cat

this will perform the index select, cat the tensors, and provide the attn_bias from cache

src/custom_controlnet_aux/metric3d/mono/model/backbones/ViT_DINO_reg.py:621

↓ 2 callersFunctionget_ckpt_path

(name, root, check=False)

src/custom_controlnet_aux/diffusion_edge/taming/modules/losses/util.py:36

↓ 2 callersFunctionget_configured_monodepth_model

Args: @ configs: configures for the network. @ load_imagenet_model: whether to initialize from ImageNet-pretrained model.

src/custom_controlnet_aux/metric3d/mono/model/monodepth_model.py:25

↓ 2 callersMethodget_crop_bbox

Randomly get a crop bounding box.

src/custom_mmpkg/custom_mmseg/datasets/pipelines/transforms.py:512

↓ 2 callersMethodget_current_visuals

Return visualization images. train.py will display these images with visdom, and save the images to a HTML

src/custom_controlnet_aux/leres/pix2pix/models/base_model.py:132

↓ 2 callersMethodget_epoch

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/logger/base.py:72

↓ 2 callersMethodget_first_stage_encoding

(self, encoder_posterior)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:609

↓ 2 callersMethodget_frame

Get frame by index. Args: frame_id (int): Index of the expected frame, 0-based. Returns: ndarray or None: Re

src/custom_mmpkg/custom_mmcv/video/io.py:160

↓ 2 callersMethodget_hook_info

(self)

src/custom_mmpkg/custom_mmcv/runner/base_runner.py:309

↓ 2 callersFunctionget_host_info

Get hostname and username. Return empty string if exception raised, e.g. ``getpass.getuser()`` will lead to error in docker container

src/custom_mmpkg/custom_mmcv/runner/utils.py:16

↓ 2 callersFunctionget_log10_err

Computes log10 error. Tasks preprocessed depths (no nans, infs and non-positive values). pred, target, and mask should be in the shape of

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:329

↓ 2 callersMethodget_loss

(self, pred, target, mean=True)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:465

↓ 2 callersMethodget_lr

(self, runner, base_lr)

src/custom_mmpkg/custom_mmcv/runner/hooks/lr_updater.py:68

↓ 2 callersFunctionget_matching_parameters

Returns parameters matching regular expression

src/custom_mesh_graphormer/utils/miscellaneous.py:50

↓ 2 callersFunctionget_model_parameters_number

Calculate parameter number of a model. Args: model (nn.module): The model for parameter number calculation. Returns: float:

src/custom_mmpkg/custom_mmcv/cnn/utils/flops_counter.py:307

↓ 2 callersFunctionget_modules_mapping

()

src/custom_mmpkg/custom_mmcv/cnn/utils/flops_counter.py:553

↓ 2 callersMethodget_momentum

(self, runner, base_momentum)

src/custom_mmpkg/custom_mmcv/runner/hooks/momentum_updater.py:52

↓ 2 callersMethodget_momentum

(self, runner, param_group)

src/custom_mmpkg/custom_mmcv/runner/hooks/momentum_updater.py:465

↓ 2 callersFunctionget_norm_layer

Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNo

src/custom_controlnet_aux/leres/pix2pix/models/networks.py:18

↓ 2 callersFunctionget_plot_font_size

(font_size: Optional[int], figure_size: Tuple[int, int])

src/custom_controlnet_aux/diffusion_edge/taming/data/conditional_builder/utils.py:81

↓ 2 callersFunctionget_prediction

( model: torch.nn.Module, input: torch.tensor, cam_model: torch.tensor, pad_info: torch.tensor

src/custom_controlnet_aux/metric3d/mono/utils/do_test.py:138

↓ 2 callersFunctionget_preprocessor

(size=None, random_crop=False, additional_targets=None, crop_size=None)

src/custom_controlnet_aux/diffusion_edge/taming/data/imagenet.py:244

↓ 2 callersMethodget_regular_lr

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/lr_updater.py:71

↓ 2 callersMethodget_regular_momentum

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/momentum_updater.py:55

↓ 2 callersFunctionget_rel_pos

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu

src/custom_controlnet_aux/sam/modeling/image_encoder.py:292

↓ 2 callersFunctionget_rmse_err

Computes rmse error. Tasks preprocessed depths (no nans, infs and non-positive values). pred, target, and mask should be in the shape of

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:353

↓ 2 callersFunctionget_rmse_log_err

Computes log rmse error. Tasks preprocessed depths (no nans, infs and non-positive values). pred, target, and mask should be in the shape

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:376

↓ 2 callersFunctionget_silog_err

Computes log rmse error. Tasks preprocessed depths (no nans, infs and non-positive values). pred, target, and mask should be in the shape

src/custom_controlnet_aux/metric3d/mono/utils/avg_meter.py:400

↓ 2 callersFunctionget_timestep_embedding

This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches

src/custom_controlnet_aux/diffusion_edge/taming/modules/diffusionmodules/model.py:8

← previous next →501–600 of 4,192, ranked by callers