MCPcopy Create free account

hub / github.com/aigc3d/LHM / functions

Functions3,669 in github.com/aigc3d/LHM

⨍ Functions 3,669◇ Types & classes 691↳ Endpoints 36
↓ 9 callersFunctionto_np
(array, dtype=np.float32)
LHM/models/rendering/smplx/smplx/utils.py:114
↓ 9 callersFunctionto_np
(array, dtype=np.float32)
LHM/models/rendering/smplx_gsavatar/utils.py:116
↓ 9 callersMethodtrain
(self, mode=True)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/shufflenet_v2.py:296
↓ 9 callersMethodtrain
Convert the model into training mode.
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/resnet.py:679
↓ 9 callersFunctionvis_pose_tracking_result
Visualize the pose tracking results on the image. Args: model (nn.Module): The loaded detector. img (str | np.ndarray): Image fil
engine/pose_estimation/third-party/ViTPose/mmpose/apis/inference_tracking.py:217
↓ 8 callersMethod__init__
(self, input_transform="resize_concat", in_index=(0, 1, 2, 3), upsample=1, **kwargs)
LHM/models/encoders/dinov2/hub/depth/decode_heads.py:226
↓ 8 callersMethod__init__
(self, dim: int, fn: Callable, norm: str = "layer", norm_cond_dim: int = -1)
engine/pose_estimation/blocks/cross_attn_transformer.py:76
↓ 8 callersMethod__init__
(self, input_transform="resize_concat", in_index=(0, 1, 2, 3), upsample=1, **kwargs)
engine/pose_estimation/dinov2/dinov2/hub/depth/decode_heads.py:226
↓ 8 callersMethod__init__
(self, name: str, frame_buffer: str, output_buffer: Union[s
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/nodes/frame_effect_node.py:696
↓ 8 callersFunction_ceil_to_multiples_of
Transform x to the integral multiple of the base.
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/pipelines/bottom_up_transform.py:11
↓ 8 callersFunction_make_dinov2_linear_classifier
( *, arch_name: str = "vit_large", layers: int = 4, pretrained: bool = True, weights: Unio
LHM/models/encoders/dinov2/hub/classifiers.py:86
↓ 8 callersFunction_make_dinov2_linear_classifier
( *, arch_name: str = "vit_large", layers: int = 4, pretrained: bool = True, weights: Unio
engine/pose_estimation/dinov2/dinov2/hub/classifiers.py:86
↓ 8 callersFunctionflip_back
Flip the flipped heatmaps back to the original form. Note: - batch_size: N - num_keypoints: K - heatmap height: H
engine/pose_estimation/third-party/ViTPose/mmpose/core/post_processing/post_transforms.py:110
↓ 8 callersMethodget_accuracy
Calculate accuracy for hand type. Args: output (list[Tensor]): a list of outputs from multiple heads. target (list[Te
engine/pose_estimation/third-party/ViTPose/mmpose/models/heads/interhand_3d_head.py:365
↓ 8 callersMethodget_query_points
transform_mat_neutral_pose is function to warp pre-defined posed to zero-pose
LHM/models/rendering/smpl_x.py:1041
↓ 8 callersFunctionimage2patches
( image, grid_h=2, grid_w=2, patch_ref=None, transformation="b c (hg h) (wg w) -> (b hg wg
engine/BiRefNet/models/birefnet.py:19
↓ 8 callersFunctionimshow_bboxes
Draw bboxes with labels (optional) on an image. This is a wrapper of mmcv.imshow_bboxes. Args: img (str or ndarray): The image to be
engine/pose_estimation/third-party/ViTPose/mmpose/core/visualization/image.py:27
↓ 8 callersFunctionimshow_keypoints
Draw keypoints and links on an image. Args: img (str or Tensor): The image to draw poses on. If an image array is giv
engine/pose_estimation/third-party/ViTPose/mmpose/core/visualization/image.py:107
↓ 8 callersFunctioninference_pose_lifter_model
Inference 3D pose from 2D pose sequences using a pose lifter model. Args: model (nn.Module): The loaded pose lifter model pose_re
engine/pose_estimation/third-party/ViTPose/mmpose/apis/inference_3d.py:212
↓ 8 callersFunctionis_norm
Check if is one of the norms.
engine/pose_estimation/third-party/ViTPose/tests/test_backbones/test_shufflenet_v1.py:18
↓ 8 callersFunctionmatrix_to_axis_angle
Convert rotations given as rotation matrices to axis/angle. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Ret
LHM/utils/rot6d.py:111
↓ 8 callersMethodnorm3
nn.Module: the normalization layer named "norm3"
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/resnet.py:237
↓ 8 callersMethodpop
(self, *args, **kwargs)
LHM/outputs/base.py:74
↓ 8 callersMethodscatter
Scatter function. Args: inputs (Tensor): Input Tensor. kwargs (dict): Args for ``mmcv.parallel.scatte
engine/pose_estimation/third-party/ViTPose/mmpose/core/distributed_wrapper.py:97
↓ 8 callersMethodtrain
(self, mode=True)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/mobilenet_v3.py:182
↓ 8 callersMethodtrain
(self, mode=True)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vgg.py:186
↓ 7 callersMethod__init__
(self, *args, **kwargs)
engine/pose_estimation/third-party/ViTPose/mmpose/deprecated.py:176
↓ 7 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vit_moe.py:62
↓ 7 callersMethod__init__
(self, in_channels, stem_channels, out_channels,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/litehrnet.py:225
↓ 7 callersMethod__init__
(self, use_target_weight=False, loss_weight=1.)
engine/pose_estimation/third-party/ViTPose/mmpose/models/losses/regression_loss.py:243
↓ 7 callersMethod__init__
(self)
engine/BiRefNet/loss.py:43
↓ 7 callersFunction_prepare_data
(pred: np.ndarray, gt: np.ndarray)
engine/BiRefNet/evaluation/metrics.py:131
↓ 7 callersMethod_report_metric
Keypoint evaluation. Args: res_file (str): Json file stored prediction results. metrics (str | list[str]): Metric to
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/datasets/hand/interhand3d_dataset.py:374
↓ 7 callersFunctionbatch_rigid_transform
Applies a batch of rigid transformations to the joints Parameters ---------- rot_mats : torch.tensor BxNx3x3 Tensor of rotat
LHM/models/rendering/smplx/smplx/lbs.py:362
↓ 7 callersFunctionbuild_dataloader
Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/builder.py:90
↓ 7 callersFunctionbuild_optimizers
Build multiple optimizers from configs. If `cfgs` contains several dicts for optimizers, then a dict for each constructed optimizers will be
engine/pose_estimation/third-party/ViTPose/mmpose/core/optimizer/builder.py:8
↓ 7 callersFunctionchannel_shuffle
Channel Shuffle operation. This function enables cross-group information flow for multiple groups convolution layers. Args: x (T
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/utils/channel_shuffle.py:5
↓ 7 callersFunctiondigit_version
(version_str)
engine/pose_estimation/third-party/ViTPose/mmpose/__init__.py:7
↓ 7 callersFunctionget_affine_transform
Get the affine transform matrix, given the center/scale/rot/output_size. Args: center (np.ndarray[2, ]): Center of the bounding box (x, y
engine/pose_estimation/third-party/ViTPose/mmpose/core/post_processing/post_transforms.py:197
↓ 7 callersFunctionget_expansion
Get the expansion of a residual block. The block expansion will be obtained by the following order: 1. If ``expansion`` is given, just retur
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vipnas_resnet.py:175
↓ 7 callersFunctioninference_bottom_up_pose_model
Inference a single image with a bottom-up pose model. Note: - num_people: P - num_keypoints: K - bbox height: H -
engine/pose_estimation/third-party/ViTPose/mmpose/apis/inference.py:553
↓ 7 callersMethodinit_weights
Initialize model weights.
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vipnas_resnet.py:548
↓ 7 callersMethodinit_weights
(self, pretrained=None)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vipnas_mbv3.py:137
↓ 7 callersFunctionkeypoints_from_heatmaps
Get final keypoint predictions from heatmaps and transform them back to the image. Note: - batch size: N - num keypoints: K
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/top_down_eval.py:474
↓ 7 callersMethodname
(self)
LHM/models/rendering/smplx/smplx/body_models.py:295
↓ 7 callersMethodregister_input_buffer
Register an input buffer, so that Node can automatically check if data is ready, fetch data from the buffers and format the inputs to
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/nodes/node.py:119
↓ 7 callersMethodremove
(self)
engine/pose_estimation/third-party/ViTPose/mmpose/utils/hooks.py:42
↓ 7 callersMethodtrain
(self, mode=True)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vipnas_mbv3.py:173
↓ 6 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vit.py:62
↓ 6 callersMethod__init__
(self, in_channels, out_channels, num_steps=4,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/rsn.py:35
↓ 6 callersMethod__init__
(self, unit_channels=256, num_stages=4, num_units=4,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/mspn.py:421
↓ 6 callersMethod__init__
( self, in_features, hidden_features=None, out_features=None, act_laye
engine/BiRefNet/models/backbones/swin_v1.py:23
↓ 6 callersFunction_make_dinov2_model_name
(arch_name: str, patch_size: int, num_register_tokens: int = 0)
LHM/models/encoders/dinov2/hub/utils.py:17
↓ 6 callersFunction_make_dinov2_model_name
(arch_name: str, patch_size: int, num_register_tokens: int = 0)
engine/pose_estimation/dinov2/dinov2/hub/utils.py:17
↓ 6 callersFunctionaffine_transform
Apply an affine transformation to the points. Args: pt (np.ndarray): a 2 dimensional point to be transformed trans_mat (np.ndarra
engine/pose_estimation/third-party/ViTPose/mmpose/core/post_processing/post_transforms.py:255
↓ 6 callersFunctionaggregate_stage_flip
Inference the model to get multi-stage outputs (heatmaps & tags), and resize them to base sizes. Args: feature_maps (list[Tensor]): f
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/bottom_up_eval.py:165
↓ 6 callersFunctionbatch_rodrigues
Calculates the rotation matrices for a batch of rotation vectors Parameters ---------- rot_vecs: torch.tensor Nx3
LHM/models/rendering/smplx/transfer_model/utils/pose_utils.py:62
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
LHM/models/encoders/dpt_util/transform.py:50
↓ 6 callersMethodcreate_camera
(self, R=None, T=None)
engine/pose_estimation/pose_utils/render.py:152
↓ 6 callersMethodenhance
(self, img, outscale=None, alpha_upsampler="realesrgan")
LHM/models/ESRGANer_utils.py:255
↓ 6 callersMethodforward_animate_gs
( self, gs_attr_list, query_points, smplx_data, c2w, intrinsic
LHM/models/rendering/gs_renderer.py:1355
↓ 6 callersMethodget_box
(self)
LHM/utils/bbox.py:67
↓ 6 callersMethodinfer_single_view
( self, image, source_c2ws, source_intrs, render_c2ws, render_
LHM/models/modeling_human_lrm.py:437
↓ 6 callersFunctionis_norm
Check if is one of the norms.
engine/pose_estimation/third-party/ViTPose/tests/test_backbones/test_shufflenet_v2.py:18
↓ 6 callersFunctionkeypoint_3d_pck
Calculate the Percentage of Correct Keypoints (3DPCK) w. or w/o rigid alignment. Paper ref: `Monocular 3D Human Pose Estimation In The Wild U
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/pose3d_eval.py:58
↓ 6 callersFunctionkeypoint_epe
Calculate the end-point error. Note: - batch_size: N - num_keypoints: K Args: pred (np.ndarray[N, K, 2]): Predicted
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/top_down_eval.py:273
↓ 6 callersFunctionmake_divisible
Make divisible function. This function rounds the channel number down to the nearest value that can be divisible by the divisor. Args:
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/utils/make_divisible.py:2
↓ 6 callersFunctionmatrix_to_quaternion
Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re
LHM/utils/rot6d.py:38
↓ 6 callersMethodput
(self, name, item, block=True, timeout=None)
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/utils/buffer.py:76
↓ 6 callersMethodregister_event
Register an event. All events used in the node need to be registered in __init__(). If a callable handler is given, a thread will be create
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/nodes/node.py:163
↓ 6 callersMethodregister_output_buffer
Register one or multiple output buffers, so that the Node can automatically send the output of the `process` method to these buffers.
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/nodes/node.py:145
↓ 6 callersMethodset
(self, event_name: str = None, is_keyboard: bool = False)
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/utils/event.py:20
↓ 6 callersFunctionsetup_multi_processes
Setup multi-processing environment variables.
engine/pose_estimation/third-party/ViTPose/mmpose/utils/setup_env.py:10
↓ 6 callersMethodto_tensor
(self, order)
engine/SegmentAPI/base.py:184
↓ 6 callersMethodtrain
Convert the model into training mode.
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/vipnas_resnet.py:581
↓ 6 callersFunctiontransform_preds
Get final keypoint predictions from heatmaps and apply scaling and translation to map them back to the image. Note: num_keypoints: K
engine/pose_estimation/third-party/ViTPose/mmpose/core/post_processing/post_transforms.py:150
↓ 6 callersFunctionwrap_model_hub
(model_cls: nn.Module)
LHM/utils/hf_hub.py:20
↓ 5 callersMethod__init__
( self, w2c, intrinsic, FoVx, FoVy, height, width,
LHM/models/rendering/gs_renderer.py:103
↓ 5 callersMethod__init__
(self, input_channels, output_channels, mid_channels=32)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/v2v_net.py:227
↓ 5 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/hrformer.py:277
↓ 5 callersFunction_demo_inputs
Create a superset of inputs needed to run backbone. Args: input_shape (tuple): input batch dimensions. Default: (1, 3, 64, 64
engine/pose_estimation/third-party/ViTPose/tests/test_necks/test_posewarper_neck.py:131
↓ 5 callersFunction_demo_inputs
Create a superset of inputs needed to run head. Args: input_shape (tuple): input batch dimensions. Default: (1, 1024, 1).
engine/pose_estimation/third-party/ViTPose/tests/test_models/test_temporal_regression_head.py:93
↓ 5 callersMethod_get_db
Load dataset.
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/datasets/top_down/topdown_mhp_dataset.py:102
↓ 5 callersMethod_get_keyboard_event_name
(key)
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/utils/event.py:48
↓ 5 callersFunction_get_max_preds
Get keypoint predictions from score maps. Note: batch_size: N num_keypoints: K heatmap height: H heatmap width: W
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/top_down_eval.py:63
↓ 5 callersMethod_load_coco_keypoint_annotations
Ground truth bbox and keypoints.
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/datasets/top_down/topdown_coco_dataset.py:107
↓ 5 callersFunctionavaliable_device
()
app_motion_ms.py:89
↓ 5 callersMethodaverage
Get the average value of current window.
engine/pose_estimation/third-party/ViTPose/mmpose/utils/timer.py:26
↓ 5 callersFunctionblend_shapes
Calculates the per vertex displacement due to the blend shapes Parameters ---------- betas : torch.tensor Bx(num_betas) Blend sh
LHM/models/rendering/smplx/smplx/lbs.py:288
↓ 5 callersFunctionbuild_optimizer
(cfg, params_groups)
engine/pose_estimation/dinov2/dinov2/train/train.py:61
↓ 5 callersFunctioncalc_new_tgt_size_by_aspect
(cur_hw, aspect_standard, tgt_size, multiply)
LHM/runners/infer/utils.py:55
↓ 5 callersFunctioncenter_crop_according_to_mask
img: [H, W, 3] mask: [H, W]
LHM/runners/infer/utils.py:111
↓ 5 callersFunctioncompute_jitter
Compute jitter for the input tensor
engine/pose_estimation/smplify.py:34
↓ 5 callersFunctioncompute_similarity_transform
Computes a similarity transform (sR, t) that takes a set of 3D points source_points (N x 3) closest to a set of 3D points target_points, where R
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/mesh_eval.py:9
↓ 5 callersFunctionconvert_coco_to_output
(coco, is_wholebody=False)
engine/pose_estimation/third-party/ViTPose/tests/test_backward_compatibility/test_dataset_info_compatibility/test_bottom_up_dataset_compatibility.py:11
↓ 5 callersFunctionconvert_coco_to_output
(coco, is_wholebody=False)
engine/pose_estimation/third-party/ViTPose/tests/test_datasets/test_bottom_up_dataset.py:10
↓ 5 callersFunctiondistance
(p1, p2)
engine/SegmentAPI/SAM.py:54
↓ 5 callersFunctiondownload_extract_tar_from_url
(url, save_path='./')
LHM/utils/download_utils.py:62
↓ 5 callersFunctionflip_feature_maps
Flip the feature maps and swap the channels. Args: feature_maps (list[Tensor]): Feature maps. flip_index (list[int] | None): Chan
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/bottom_up_eval.py:46
↓ 5 callersFunctionfliplr_regression
Flip human joints horizontally. Note: - batch_size: N - num_keypoint: K Args: regression (np.ndarray([..., K, C])):
engine/pose_estimation/third-party/ViTPose/mmpose/core/post_processing/post_transforms.py:54
← previousnext →101–200 of 3,669, ranked by callers