MCPcopy Create free account

hub / github.com/CGuangyan-BIT/PointGPT / functions

Functions329 in github.com/CGuangyan-BIT/PointGPT

↓ 64 callersFunctionprint_log
Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used.
utils/logger.py:103
↓ 20 callersMethodget
(cls, file_path)
datasets/io.py:8
↓ 15 callersFunctionlog_string
(str)
segmentation/main.py:98
↓ 9 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
models/PointGPT.py:189
↓ 9 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
segmentation/models/pt.py:192
↓ 9 callersMethodstate_dict
(self)
tools/runner_pretrain.py:44
↓ 9 callersMethodupdate
(self, values)
utils/AverageMeter.py:13
↓ 7 callersFunctionindex_points
Input: points: input points data, [B, N, C] idx: sample index data, [B, S, [K]] Return: new_points:, indexed points d
segmentation/pointnet_util.py:39
↓ 7 callersFunctionindex_points
Input: points: input points data, [B, N, C] idx: sample index data, [B, S] Return: new_points:, indexed points data,
segmentation/models/pointnet2_utils.py:41
↓ 7 callersMethodstep
(self, epoch=None)
utils/misc.py:117
↓ 6 callersMethodbackward
(ctx, grad_cost)
extensions/emd/emd.py:17
↓ 6 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 handl
utils/logger.py:29
↓ 5 callersMethodget
Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding c
utils/registry.py:123
↓ 5 callersMethodstep
(self, epoch=None)
segmentation/misc.py:122
↓ 4 callersMethodavg
(self, idx=None)
utils/AverageMeter.py:36
↓ 4 callersFunctionsquare_distance
Calculate Euclid distance between each two points. src^T * dst = xn * xm + yn * ym + zn * zm; sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;
segmentation/pointnet_util.py:22
↓ 3 callersMethod_register_module
(self, module_class, module_name=None, force=False)
utils/registry.py:168
↓ 3 callersMethodbackward
(ctx, grad_cost)
segmentation/extensions/emd/emd.py:17
↓ 3 callersFunctionfarthest_point_sample
Input: xyz: pointcloud data, [B, N, 3] npoint: number of samples Return: centroids: sampled pointcloud index, [B, npo
segmentation/pointnet_util.py:53
↓ 3 callersFunctionfps
data B N 3 number int
utils/misc.py:13
↓ 3 callersFunctionfps
data B N 3 number int
segmentation/misc.py:13
↓ 3 callersFunctionsplit_by_3
Method to separate bits of a 32-bit integer by 3 positions apart, using the magic bits https://www.forceflow.be/2013/10/07/morton-encodin
models/z_order.py:23
↓ 3 callersFunctionsplit_by_3
Method to separate bits of a 32-bit integer by 3 positions apart, using the magic bits https://www.forceflow.be/2013/10/07/morton-encodin
segmentation/models/z_order.py:23
↓ 3 callersMethodval
(self, idx=None)
utils/AverageMeter.py:24
↓ 2 callersMethod__init__
(self, ignore_zeros=False)
extensions/chamfer_dist/__init__.py:31
↓ 2 callersMethod__init__
(self, embed_dim, num_heads)
models/GPT.py:9
↓ 2 callersMethod__init__
(self, npoint, radius, nsample, in_channel, mlp, group_all, knn=False)
segmentation/pointnet_util.py:160
↓ 2 callersMethod__init__
(self, ignore_zeros=False)
segmentation/extensions/chamfer_dist/__init__.py:31
↓ 2 callersMethod__init__
(self, embed_dim, num_heads, drop_path)
segmentation/models/gpt2_seg.py:8
↓ 2 callersMethod__init__
(self, npoint, radius, nsample, in_channel, mlp, group_all)
segmentation/models/pointnet2_utils.py:159
↓ 2 callersMethod__len__
(self)
datasets/ModelNetDataset.py:118
↓ 2 callersFunction_group_checkpoint_keys
Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of para
utils/checkpoint.py:83
↓ 2 callersFunction_group_checkpoint_keys
Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of para
segmentation/logger.py:208
↓ 2 callersFunction_group_to_str
Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Retur
utils/checkpoint.py:104
↓ 2 callersFunction_group_to_str
Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Retur
segmentation/logger.py:229
↓ 2 callersMethodbetter_than
(self, other)
tools/runner_finetune.py:46
↓ 2 callersMethodbuild
(self, *args, **kwargs)
utils/registry.py:146
↓ 2 callersFunctionfarthest_point_sample
Input: xyz: pointcloud data, [N, D] npoint: number of samples Return: centroids: sampled pointcloud index, [npoint, D
datasets/ModelNetDataset.py:29
↓ 2 callersFunctionfarthest_point_sample
Input: xyz: pointcloud data, [B, N, 3] npoint: number of samples Return: centroids: sampled pointcloud index, [B, npo
segmentation/models/pointnet2_utils.py:60
↓ 2 callersFunctionget_config
(args, logger=None)
utils/config.py:52
↓ 2 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 handl
segmentation/logger.py:41
↓ 2 callersFunctionget_root_logger
Get root logger and add a keyword filter to it. The logger will be initialized if it has not been initialized. By default a StreamHandler will
utils/logger.py:6
↓ 2 callersFunctionlog_args_to_file
(args, pre='args', logger=None)
utils/config.py:7
↓ 2 callersFunctionlog_config_to_file
(cfg, pre='cfg', logger=None)
utils/config.py:12
↓ 2 callersFunctionparse_args
()
segmentation/main.py:49
↓ 2 callersFunctionpc_normalize
(pc)
segmentation/pointnet_util.py:15
↓ 2 callersFunctionquery_ball_point
Input: radius: local region radius nsample: max sample number in local region xyz: all points, [B, N, 3] new_xyz:
segmentation/pointnet_util.py:76
↓ 2 callersFunctionquery_ball_point
Input: radius: local region radius nsample: max sample number in local region xyz: all points, [B, N, 3] new_xyz:
segmentation/models/pointnet2_utils.py:84
↓ 2 callersFunctionsquare_distance
Calculate Euclid distance between each two points. src^T * dst = xn * xm + yn * ym + zn * zm; sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;
segmentation/models/pointnet2_utils.py:19
↓ 2 callersFunctiontest_net
(args, config)
tools/runner.py:14
↓ 2 callersFunctionto_categorical
1-hot encodes a tensor
segmentation/main.py:41
↓ 1 callersMethod__init__
(self, config, **kwargs)
datasets/ScanObjectNNDataset.py:13
↓ 1 callersMethod_add_children
Add children for a registry. The ``registry`` will be added as children based on its scope. The parent registry could build objects fr
utils/registry.py:149
↓ 1 callersMethod_get_item
(self, index)
datasets/ModelNetDataset.py:121
↓ 1 callersMethod_get_item
(self, index)
segmentation/dataset.py:39
↓ 1 callersFunction_init_dist_pytorch
(backend, **kwargs)
utils/dist_utils.py:18
↓ 1 callersMethod_read_h5
(cls, file_path)
datasets/io.py:40
↓ 1 callersMethod_read_npy
(cls, file_path)
datasets/io.py:24
↓ 1 callersMethod_read_txt
(cls, file_path)
datasets/io.py:36
↓ 1 callersFunctionadd_weight_decay
(model, weight_decay=1e-5, skip_list=())
tools/builder.py:47
↓ 1 callersFunctionadd_weight_decay
(model, weight_decay=1e-5, skip_list=())
segmentation/main.py:165
↓ 1 callersFunctionbuild_dataset_from_cfg
Build a dataset, defined by `dataset_name`. Args: cfg (eDICT): Returns: Dataset: a constructed dataset specified by data
datasets/build.py:7
↓ 1 callersFunctionbuild_lambda_bnsche
(model, config)
utils/misc.py:34
↓ 1 callersFunctionbuild_lambda_sche
(opti, config)
utils/misc.py:26
↓ 1 callersMethodbuild_loss_func
(self, loss_type)
models/PointGPT.py:463
↓ 1 callersMethodbuild_loss_func
(self, loss_type='cdl12')
models/PointGPT.py:561
↓ 1 callersFunctionbuild_model_from_cfg
Build a dataset, defined by `dataset_name`. Args: cfg (eDICT): Returns: Dataset: a constructed dataset specified by data
models/build.py:7
↓ 1 callersFunctioncfg_from_yaml_file
(cfg_file)
utils/config.py:41
↓ 1 callersFunctioncreate_experiment_dir
(args)
utils/parser.py:104
↓ 1 callersMethoddeprecated_register_module
(self, cls=None, force=False)
utils/registry.py:183
↓ 1 callersFunctionevaluate_svm
(train_features, train_labels, test_features, test_labels)
tools/runner_pretrain.py:50
↓ 1 callersFunctionfps
data B N 3 number int
segmentation/models/pt.py:17
↓ 1 callersFunctiongenerate_fewshot_data
(way, shot, prefix_ind, eval_sample=20)
datasets/generate_few_shot_data.py:20
↓ 1 callersMethodget_loss_acc
(self, ret, gt)
models/PointGPT.py:574
↓ 1 callersFunctionget_missing_parameters_message
Get a logging-friendly message to report parameter names (keys) that are in the model but not found in a checkpoint. Args: keys (
utils/checkpoint.py:16
↓ 1 callersFunctionget_missing_parameters_message
Get a logging-friendly message to report parameter names (keys) that are in the model but not found in a checkpoint. Args: keys (
segmentation/logger.py:141
↓ 1 callersFunctionget_model_loss
(MODEL, args, num_part)
segmentation/main.py:79
↓ 1 callersFunctionget_unexpected_parameters_message
Get a logging-friendly message to report parameter names (keys) that are in the checkpoint but not found in the model. Args: keys
utils/checkpoint.py:33
↓ 1 callersFunctionget_unexpected_parameters_message
Get a logging-friendly message to report parameter names (keys) that are in the checkpoint but not found in the model. Args: keys
segmentation/logger.py:158
↓ 1 callersFunctionget_z_order
Given 3 arrays of corresponding x, y, z coordinates, compute the morton (or z) code for each point and return an index array We compu
models/z_order.py:50
↓ 1 callersFunctionget_z_order
Given 3 arrays of corresponding x, y, z coordinates, compute the morton (or z) code for each point and return an index array We compu
segmentation/models/z_order.py:50
↓ 1 callersFunctionget_z_values
Computes the z values for a point array :param data: Nx3 array of x, y, and z location :return: Nx1 array of z values
models/z_order.py:72
↓ 1 callersFunctionget_z_values
Computes the z values for a point array :param data: Nx3 array of x, y, and z location :return: Nx1 array of z values
segmentation/models/z_order.py:72
↓ 1 callersMethodinfer_scope
Infer the scope of registry. The name of the package where registry is defined will be returned. Example: # in mmdet/model
utils/registry.py:69
↓ 1 callersMethodload_model_from_ckpt
(self, bert_ckpt_path)
models/PointGPT.py:580
↓ 1 callersMethodload_model_from_ckpt
(self, bert_ckpt_path)
segmentation/models/pt.py:422
↓ 1 callersFunctionmain
()
main_vis.py:11
↓ 1 callersFunctionmain
()
main.py:14
↓ 1 callersFunctionmain
(args)
segmentation/main.py:97
↓ 1 callersFunctionmerge_new_config
(config, new_config)
utils/config.py:21
↓ 1 callersMethodpc_norm
pc: NxC, return NxC
datasets/UnlabeledHybrid.py:52
↓ 1 callersMethodpc_norm
pc: NxC, return NxC
datasets/LabeledHybrid.py:40
↓ 1 callersMethodpc_norm
pc: NxC, return NxC
datasets/ShapeNet55Dataset.py:52
↓ 1 callersFunctionpc_normalize
(pc)
datasets/ModelNetDatasetFewShot.py:21
↓ 1 callersFunctionpc_normalize
(pc)
datasets/ModelNetDataset.py:20
↓ 1 callersMethodrandom_sample
(self, pc, num)
datasets/UnlabeledHybrid.py:60
↓ 1 callersMethodrandom_sample
(self, pc, num)
datasets/LabeledHybrid.py:49
↓ 1 callersMethodrandom_sample
(self, pc, num)
datasets/ShapeNet55Dataset.py:60
↓ 1 callersMethodreset
(self)
utils/AverageMeter.py:8
↓ 1 callersFunctionround_to_int_32
Takes a Numpy array of float values between -1 and 1, and rounds them to significant 32-bit integer values, to be used in the morton
models/z_order.py:4
next →1–100 of 329, ranked by callers