Skip to content

GitLab

Commit d136760c authored by zhangwenwei's avatar zhangwenwei
Browse files

Merge branch 'add-model-docstring' into 'master' 

Reformat docstrings in code

See merge request open-mmlab/mmdet.3d!115
parents 64d7fbc2 80b39bd0
Show whitespace changes
Inline Side-by-side
Showing with 152 additions and 85 deletions
mmdet3d/models/dense_heads/vote_head.py
View file @ d136760c
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import ConvModule
from torch import nn as nn
from torch.nn import functional as F
from mmdet3d.core.post_processing import aligned_3d_nms
from mmdet3d.models.builder import build_loss
......
mmdet3d/models/detectors/base.py
View file @ d136760c
import os.path as osp
from os import path as osp
from mmdet3d.core import Box3DMode, show_result
from mmdet.models.detectors import BaseDetector
class Base3DDetector(BaseDetector):
"""Base class for detectors"""
"""Base class for detectors."""
def forward_test(self, points, img_metas, img=None, **kwargs):
"""
......@@ -42,14 +42,15 @@ class Base3DDetector(BaseDetector):
return self.aug_test(points, img_metas, img, **kwargs)
def forward(self, return_loss=True, **kwargs):
"""
Calls either forward_train or forward_test depending on whether
return_loss=True. Note this setting will change the expected inputs.
When `return_loss=True`, img and img_metas are single-nested (i.e.
"""Calls either forward_train or forward_test depending on whether
return_loss=True.
Note this setting will change the expected inputs. When
`return_loss=True`, img and img_metas are single-nested (i.e.
torch.Tensor and list[dict]), and when `resturn_loss=False`, img and
img_metas should be double nested
(i.e. list[torch.Tensor], list[list[dict]]), with the outer list
indicating test time augmentations.
img_metas should be double nested (i.e. list[torch.Tensor],
list[list[dict]]), with the outer list indicating test time
augmentations.
"""
if return_loss:
return self.forward_train(**kwargs)
......
mmdet3d/models/detectors/dynamic_voxelnet.py
View file @ d136760c
import torch
import torch.nn.functional as F
from torch.nn import functional as F
from mmdet.models import DETECTORS
from .voxelnet import VoxelNet
......@@ -7,8 +7,8 @@ from .voxelnet import VoxelNet
@DETECTORS.register_module()
class DynamicVoxelNet(VoxelNet):
"""VoxelNet using `dynamic voxelization
<https://arxiv.org/abs/1910.06528>`_."""
r"""VoxelNet using `dynamic voxelization <https://arxiv.org/abs/1910.06528>`_.
"""
def __init__(self,
voxel_layer,
......@@ -33,7 +33,7 @@ class DynamicVoxelNet(VoxelNet):
)
def extract_feat(self, points, img_metas):
"""Extract features from points"""
"""Extract features from points."""
voxels, coors = self.voxelize(points)
voxel_features, feature_coors = self.voxel_encoder(voxels, coors)
batch_size = coors[-1, 0].item() + 1
......@@ -45,7 +45,14 @@ class DynamicVoxelNet(VoxelNet):
@torch.no_grad()
def voxelize(self, points):
"""Apply dynamic voxelization to points"""
"""Apply dynamic voxelization to points.
Args:
points (list[torch.Tensor]): Points of each sample.
Returns:
tuple[torch.Tensor]: Concatenated points and coordinates.
"""
coors = []
# dynamic voxelization only provide a coors mapping
for res in points:
......
mmdet3d/models/detectors/mvx_faster_rcnn.py
View file @ d136760c
import torch
import torch.nn.functional as F
from torch.nn import functional as F
from mmdet.models import DETECTORS
from .mvx_two_stage import MVXTwoStageDetector
......@@ -7,6 +7,7 @@ from .mvx_two_stage import MVXTwoStageDetector
@DETECTORS.register_module()
class MVXFasterRCNN(MVXTwoStageDetector):
"""Multi-modality VoxelNet using Faster R-CNN."""
def __init__(self, **kwargs):
super(MVXFasterRCNN, self).__init__(**kwargs)
......@@ -14,12 +15,21 @@ class MVXFasterRCNN(MVXTwoStageDetector):
@DETECTORS.register_module()
class DynamicMVXFasterRCNN(MVXTwoStageDetector):
"""Multi-modality VoxelNet using Faster R-CNN and dynamic voxelization."""
def __init__(self, **kwargs):
super(DynamicMVXFasterRCNN, self).__init__(**kwargs)
@torch.no_grad()
def voxelize(self, points):
"""Apply dynamic voxelization to points.
Args:
points (list[torch.Tensor]): Points of each sample.
Returns:
tuple[torch.Tensor]: Concatenated points and coordinates.
"""
coors = []
# dynamic voxelization only provide a coors mapping
for res in points:
......@@ -34,6 +44,7 @@ class DynamicMVXFasterRCNN(MVXTwoStageDetector):
return points, coors_batch
def extract_pts_feat(self, points, img_feats, img_metas):
"""Extract point features."""
if not self.with_pts_bbox:
return None
voxels, coors = self.voxelize(points)
......
mmdet3d/models/detectors/mvx_two_stage.py
View file @ d136760c
import os.path as osp
import torch
import torch.nn as nn
import torch.nn.functional as F
from os import path as osp
from torch import nn as nn
from torch.nn import functional as F
from mmdet3d.core import (Box3DMode, bbox3d2result, merge_aug_bboxes_3d,
show_result)
......@@ -15,6 +14,7 @@ from .base import Base3DDetector
@DETECTORS.register_module()
class MVXTwoStageDetector(Base3DDetector):
"""Base class of Multi-modality VoxelNet."""
def __init__(self,
pts_voxel_layer=None,
......@@ -69,6 +69,7 @@ class MVXTwoStageDetector(Base3DDetector):
self.init_weights(pretrained=pretrained)
def init_weights(self, pretrained=None):
"""Initialize model weights."""
super(MVXTwoStageDetector, self).init_weights(pretrained)
if pretrained is None:
img_pretrained = None
......@@ -99,59 +100,72 @@ class MVXTwoStageDetector(Base3DDetector):
@property
def with_img_shared_head(self):
"""bool: Whether the detector has a shared head in image branch."""
return hasattr(self,
'img_shared_head') and self.img_shared_head is not None
@property
def with_pts_bbox(self):
"""bool: Whether the detector has a 3D box head."""
return hasattr(self,
'pts_bbox_head') and self.pts_bbox_head is not None
@property
def with_img_bbox(self):
"""bool: Whether the detector has a 2D image box head."""
return hasattr(self,
'img_bbox_head') and self.img_bbox_head is not None
@property
def with_img_backbone(self):
"""bool: Whether the detector has a 2D image backbone."""
return hasattr(self, 'img_backbone') and self.img_backbone is not None
@property
def with_pts_backbone(self):
"""bool: Whether the detector has a 3D backbone."""
return hasattr(self, 'pts_backbone') and self.pts_backbone is not None
@property
def with_fusion(self):
"""bool: Whether the detector has a fusion layer."""
return hasattr(self,
'pts_fusion_layer') and self.fusion_layer is not None
@property
def with_img_neck(self):
"""bool: Whether the detector has a neck in image branch."""
return hasattr(self, 'img_neck') and self.img_neck is not None
@property
def with_pts_neck(self):
"""bool: Whether the detector has a neck in 3D detector branch."""
return hasattr(self, 'pts_neck') and self.pts_neck is not None
@property
def with_img_rpn(self):
"""bool: Whether the detector has a 2D RPN in image detector branch."""
return hasattr(self, 'img_rpn_head') and self.img_rpn_head is not None
@property
def with_img_roi_head(self):
"""bool: Whether the detector has a RoI Head in image branch."""
return hasattr(self, 'img_roi_head') and self.img_roi_head is not None
@property
def with_voxel_encoder(self):
"""bool: Whether the detector has a voxel encoder."""
return hasattr(self,
'voxel_encoder') and self.voxel_encoder is not None
@property
def with_middle_encoder(self):
"""bool: Whether the detector has a middle encoder."""
return hasattr(self,
'middle_encoder') and self.middle_encoder is not None
def extract_img_feat(self, img, img_metas):
"""Extract features of images."""
if self.with_img_backbone:
if img.dim() == 5 and img.size(0) == 1:
img.squeeze_()
......@@ -166,6 +180,7 @@ class MVXTwoStageDetector(Base3DDetector):
return img_feats
def extract_pts_feat(self, pts, img_feats, img_metas):
"""Extract features of points."""
if not self.with_pts_bbox:
return None
voxels, num_points, coors = self.voxelize(pts)
......@@ -179,12 +194,22 @@ class MVXTwoStageDetector(Base3DDetector):
return x
def extract_feat(self, points, img, img_metas):
"""Extract features from images and points."""
img_feats = self.extract_img_feat(img, img_metas)
pts_feats = self.extract_pts_feat(points, img_feats, img_metas)
return (img_feats, pts_feats)
@torch.no_grad()
def voxelize(self, points):
"""Apply dynamic voxelization to points.
Args:
points (list[torch.Tensor]): Points of each sample.
Returns:
tuple[torch.Tensor]: Concatenated points, number of points
per voxel, and coordinates.
"""
voxels, coors, num_points = [], [], []
for res in points:
res_voxels, res_coors, res_num_points = self.pts_voxel_layer(res)
......@@ -208,8 +233,33 @@ class MVXTwoStageDetector(Base3DDetector):
gt_labels=None,
gt_bboxes=None,
img=None,
bboxes=None,
proposals=None,
gt_bboxes_ignore=None):
"""Forward training function.
Args:
points (list[torch.Tensor], optional): Points of each sample.
Defaults to None.
img_metas (list[dict], optional): Meta information of each sample.
Defaults to None.
gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`], optional):
Ground truth 3D boxes. Defaults to None.
gt_labels_3d (list[torch.Tensor], optional): Ground truth labels
of 3D boxes. Defaults to None.
gt_labels (list[torch.Tensor], optional): Ground truth labels
of 2D boxes in images. Defaults to None.
gt_bboxes (list[torch.Tensor], optional): Ground truth 2D boxes in
images. Defaults to None.
img (torch.Tensor optional): Images of each sample with shape
(N, C, H, W). Defaults to None.
proposals ([list[torch.Tensor], optional): Predicted proposals
used for training Fast RCNN. Defaults to None.
gt_bboxes_ignore (list[torch.Tensor], optional): Ground truth
2D boxes in images to be ignored. Defaults to None.
Returns:
dict: Losses of different branches.
"""
img_feats, pts_feats = self.extract_feat(
points, img=img, img_metas=img_metas)
losses = dict()
......@@ -225,8 +275,7 @@ class MVXTwoStageDetector(Base3DDetector):
gt_bboxes=gt_bboxes,
gt_labels=gt_labels,
gt_bboxes_ignore=gt_bboxes_ignore,
bboxes=bboxes,
)
proposals=proposals)
losses.update(losses_img)
return losses
......
mmdet3d/models/detectors/parta2.py
View file @ d136760c
import torch
import torch.nn.functional as F
from torch.nn import functional as F
from mmdet3d.ops import Voxelization
from mmdet.models import DETECTORS
......@@ -9,7 +9,7 @@ from .two_stage import TwoStage3DDetector
@DETECTORS.register_module()
class PartA2(TwoStage3DDetector):
"""Part-A2 detector
"""Part-A2 detector.
Please refer to the `paper <https://arxiv.org/abs/1907.03670>`_
"""
......
mmdet3d/models/detectors/single_stage.py
View file @ d136760c
import torch.nn as nn
from torch import nn as nn
from mmdet.models import DETECTORS, build_backbone, build_head, build_neck
from .base import Base3DDetector
......@@ -6,7 +6,7 @@ from .base import Base3DDetector
@DETECTORS.register_module()
class SingleStage3DDetector(Base3DDetector):
"""SingleStage3DDetector
"""SingleStage3DDetector.
This class serves as a base class for single-stage 3D detectors.
......
mmdet3d/models/detectors/two_stage.py
View file @ d136760c
......@@ -4,11 +4,11 @@ from .base import Base3DDetector
@DETECTORS.register_module()
class TwoStage3DDetector(Base3DDetector, TwoStageDetector):
"""Base class of two-stage 3D detector
"""Base class of two-stage 3D detector.
It inherits original ``:class:TwoStageDetector`` and
``:class:Base3DDetector``. This class could serve as a base class for
all two-stage 3D detectors.
``:class:Base3DDetector``. This class could serve as a base class for all
two-stage 3D detectors.
"""
def __init__(self, **kwargs):
......
mmdet3d/models/detectors/voxelnet.py
View file @ d136760c
import torch
import torch.nn.functional as F
from torch.nn import functional as F
from mmdet3d.core import bbox3d2result, merge_aug_bboxes_3d
from mmdet3d.ops import Voxelization
......@@ -34,7 +34,7 @@ class VoxelNet(SingleStage3DDetector):
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
def extract_feat(self, points, img_metas):
"""Extract features from points"""
"""Extract features from points."""
voxels, num_points, coors = self.voxelize(points)
voxel_features = self.voxel_encoder(voxels, num_points, coors)
batch_size = coors[-1, 0].item() + 1
......@@ -46,7 +46,7 @@ class VoxelNet(SingleStage3DDetector):
@torch.no_grad()
def voxelize(self, points):
"""Apply hard voxelization to points"""
"""Apply hard voxelization to points."""
voxels, coors, num_points = [], [], []
for res in points:
res_voxels, res_coors, res_num_points = self.voxel_layer(res)
......
mmdet3d/models/fusion_layers/point_fusion.py
View file @ d136760c
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import ConvModule, xavier_init
from torch import nn as nn
from torch.nn import functional as F
from ..registry import FUSION_LAYERS
......@@ -23,7 +23,7 @@ def point_sample(
padding_mode='zeros',
align_corners=True,
):
"""Obtain image features using points
"""Obtain image features using points.
Args:
img_features (Tensor): 1xCxHxW image features
......@@ -113,7 +113,7 @@ def point_sample(
@FUSION_LAYERS.register_module()
class PointFusion(nn.Module):
"""Fuse image features from multi-scale features
"""Fuse image features from multi-scale features.
Args:
img_channels (list[int] | int): Channels of image features.
......@@ -225,7 +225,7 @@ class PointFusion(nn.Module):
xavier_init(m, distribution='uniform')
def forward(self, img_feats, pts, pts_feats, img_metas):
"""Forward function
"""Forward function.
Args:
img_feats (list[Tensor]): img features
......
mmdet3d/models/losses/chamfer_distance.py
View file @ d136760c
import torch
import torch.nn as nn
from torch import nn as nn
from torch.nn.functional import l1_loss, mse_loss, smooth_l1_loss
from mmdet.models.builder import LOSSES
......
mmdet3d/models/middle_encoders/pillar_scatter.py
View file @ d136760c
......@@ -23,7 +23,7 @@ class PointPillarsScatter(nn.Module):
self.in_channels = in_channels
def forward(self, voxel_features, coors, batch_size=None):
"""Foraward function to scatter features"""
"""Foraward function to scatter features."""
# TODO: rewrite the function in a batch manner
# no need to deal with different batch cases
if batch_size is not None:
......@@ -32,7 +32,7 @@ class PointPillarsScatter(nn.Module):
return self.forward_single(voxel_features, coors)
def forward_single(self, voxel_features, coors):
"""Scatter features of single sample
"""Scatter features of single sample.
Args:
voxel_features (torch.Tensor): Voxel features in shape (N, M, C).
......@@ -56,7 +56,7 @@ class PointPillarsScatter(nn.Module):
return [canvas]
def forward_batch(self, voxel_features, coors, batch_size):
"""Scatter features of single sample
"""Scatter features of single sample.
Args:
voxel_features (torch.Tensor): Voxel features in shape (N, M, C).
......
mmdet3d/models/middle_encoders/sparse_encoder.py
View file @ d136760c
import torch.nn as nn
from torch import nn as nn
import mmdet3d.ops.spconv as spconv
from mmdet3d.ops import make_sparse_convmodule
from mmdet3d.ops import spconv as spconv
from ..registry import MIDDLE_ENCODERS
@MIDDLE_ENCODERS.register_module()
class SparseEncoder(nn.Module):
"""Sparse encoder for Second
"""Sparse encoder for Second.
See https://arxiv.org/abs/1907.03670 for more detials.
......@@ -81,7 +81,7 @@ class SparseEncoder(nn.Module):
conv_type='SparseConv3d')
def forward(self, voxel_features, coors, batch_size):
"""Forward of SparseEncoder
"""Forward of SparseEncoder.
Args:
voxel_features (torch.float32): shape [N, C]
......@@ -113,7 +113,7 @@ class SparseEncoder(nn.Module):
return spatial_features
def make_encoder_layers(self, make_block, norm_cfg, in_channels):
"""make encoder layers using sparse convs
"""make encoder layers using sparse convs.
Args:
make_block (method): a bounded function to build blocks
......
mmdet3d/models/middle_encoders/sparse_unet.py
View file @ d136760c
import torch
import torch.nn as nn
from torch import nn as nn
import mmdet3d.ops.spconv as spconv
from mmdet3d.ops import SparseBasicBlock, make_sparse_convmodule
from mmdet3d.ops import spconv as spconv
from ..registry import MIDDLE_ENCODERS
@MIDDLE_ENCODERS.register_module()
class SparseUNet(nn.Module):
"""SparseUNet for PartA^2
"""SparseUNet for PartA^2.
See https://arxiv.org/abs/1907.03670 for more detials.
......@@ -92,7 +92,7 @@ class SparseUNet(nn.Module):
conv_type='SparseConv3d')
def forward(self, voxel_features, coors, batch_size):
"""Forward of SparseUNet
"""Forward of SparseUNet.
Args:
voxel_features (torch.float32): shape [N, C]
......@@ -184,7 +184,7 @@ class SparseUNet(nn.Module):
return x
def make_encoder_layers(self, make_block, norm_cfg, in_channels):
"""make encoder layers using sparse convs
"""make encoder layers using sparse convs.
Args:
make_block (method): a bounded function to build blocks
......@@ -230,7 +230,7 @@ class SparseUNet(nn.Module):
return out_channels
def make_decoder_layers(self, make_block, norm_cfg, in_channels):
"""make decoder layers using sparse convs
"""make decoder layers using sparse convs.
Args:
make_block (method): a bounded function to build blocks
......
mmdet3d/models/model_utils/vote_module.py
View file @ d136760c
import torch
import torch.nn as nn
from mmcv.cnn import ConvModule
from torch import nn as nn
from mmdet3d.models.builder import build_loss
......
mmdet3d/models/necks/second_fpn.py
View file @ d136760c
import torch
import torch.nn as nn
from mmcv.cnn import (build_norm_layer, build_upsample_layer, constant_init,
is_norm, kaiming_init)
from torch import nn as nn
from mmdet.models import NECKS
@NECKS.register_module()
class SECONDFPN(nn.Module):
"""FPN used in SECOND/PointPillars/PartA2/MVXNet
"""FPN used in SECOND/PointPillars/PartA2/MVXNet.
Args:
in_channels (list[int]): Input channels of multi-scale feature maps
......@@ -46,7 +46,7 @@ class SECONDFPN(nn.Module):
self.deblocks = nn.ModuleList(deblocks)
def init_weights(self):
"""Initialize weights of FPN"""
"""Initialize weights of FPN."""
for m in self.modules():
if isinstance(m, nn.Conv2d):
kaiming_init(m)
......@@ -54,7 +54,7 @@ class SECONDFPN(nn.Module):
constant_init(m, 1)
def forward(self, x):
"""Forward function
"""Forward function.
Args:
x (torch.Tensor): 4D Tensor in (N, C, H, W) shape.
......
mmdet3d/models/roi_heads/base_3droi_head.py
View file @ d136760c
from abc import ABCMeta, abstractmethod
import torch.nn as nn
from torch import nn as nn
class Base3DRoIHead(nn.Module, metaclass=ABCMeta):
"""Base class for 3d RoIHeads"""
"""Base class for 3d RoIHeads."""
def __init__(self,
bbox_head=None,
......@@ -51,7 +50,7 @@ class Base3DRoIHead(nn.Module, metaclass=ABCMeta):
@abstractmethod
def init_assigner_sampler(self):
"""Initialize assigner and sampler"""
"""Initialize assigner and sampler."""
pass
@abstractmethod
......@@ -63,7 +62,7 @@ class Base3DRoIHead(nn.Module, metaclass=ABCMeta):
gt_labels,
gt_bboxes_ignore=None,
**kwargs):
"""Forward function during training
"""Forward function during training.
Args:
x (dict): Contains features from the first stage.
......
mmdet3d/models/roi_heads/bbox_heads/parta2_bbox_head.py
View file @ d136760c
import numpy as np
import torch
import torch.nn as nn
from mmcv.cnn import ConvModule, normal_init, xavier_init
from torch import nn as nn
import mmdet3d.ops.spconv as spconv
from mmdet3d.core.bbox.structures import (LiDARInstance3DBoxes,
rotation_3d_in_axis, xywhr2xyxyr)
from mmdet3d.models.builder import build_loss
from mmdet3d.ops import make_sparse_convmodule
from mmdet3d.ops import spconv as spconv
from mmdet3d.ops.iou3d.iou3d_utils import nms_gpu, nms_normal_gpu
from mmdet.core import build_bbox_coder, multi_apply
from mmdet.models import HEADS
......@@ -223,7 +223,7 @@ class PartA2BboxHead(nn.Module):
self.init_weights()
def init_weights(self):
"""Initialize weights of the bbox head"""
"""Initialize weights of the bbox head."""
for m in self.modules():
if isinstance(m, (nn.Conv2d, nn.Conv1d)):
xavier_init(m, distribution='uniform')
......@@ -556,7 +556,7 @@ class PartA2BboxHead(nn.Module):
nms_thr,
input_meta,
use_rotate_nms=True):
"""Multi-class NMS for box head
"""Multi-class NMS for box head.
Note:
This function has large overlap with the `box3d_multiclass_nms`
......
mmdet3d/models/roi_heads/mask_heads/pointwise_semantic_head.py
View file @ d136760c
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch import nn as nn
from torch.nn import functional as F
from mmdet3d.core.bbox.structures import rotation_3d_in_axis
from mmdet3d.models.builder import build_loss
......@@ -57,7 +57,6 @@ class PointwiseSemanticHead(nn.Module):
Returns:
dict: part features, segmentation and part predictions.
"""
seg_preds = self.seg_cls_layer(x) # (N, 1)
part_preds = self.seg_reg_layer(x) # (N, 3)
......@@ -73,7 +72,8 @@ class PointwiseSemanticHead(nn.Module):
seg_preds=seg_preds, part_preds=part_preds, part_feats=part_feats)
def get_targets_single(self, voxel_centers, gt_bboxes_3d, gt_labels_3d):
"""generate segmentation and part prediction targets for a single sample
"""generate segmentation and part prediction targets for a single
sample.
Args:
voxel_centers (torch.Tensor): shape [voxel_num, 3],
......@@ -120,7 +120,7 @@ class PointwiseSemanticHead(nn.Module):
return seg_targets, part_targets
def get_targets(self, voxels_dict, gt_bboxes_3d, gt_labels_3d):
"""generate segmentation and part prediction targets
"""generate segmentation and part prediction targets.
Args:
voxel_centers (torch.Tensor): shape [voxel_num, 3],
......
mmdet3d/models/roi_heads/part_aggregation_roi_head.py
View file @ d136760c
import torch.nn.functional as F
from torch.nn import functional as F
from mmdet3d.core import AssignResult
from mmdet3d.core.bbox import bbox3d2result, bbox3d2roi
......@@ -10,7 +10,7 @@ from .base_3droi_head import Base3DRoIHead
@HEADS.register_module()
class PartAggregationROIHead(Base3DRoIHead):
"""Part aggregation roi head for PartA2
"""Part aggregation roi head for PartA2.
Args:
semantic_head (ConfigDict): Config of semantic head.
......@@ -44,21 +44,21 @@ class PartAggregationROIHead(Base3DRoIHead):
self.init_assigner_sampler()
def init_weights(self, pretrained):
"""Initialize weights, skip since ``PartAggregationROIHead``
does not need to initialize weights"""
"""Initialize weights, skip since ``PartAggregationROIHead`` does not
need to initialize weights."""
pass
def init_mask_head(self):
"""Initialize mask head, skip since ``PartAggregationROIHead``
does not have one."""
"""Initialize mask head, skip since ``PartAggregationROIHead`` does not
have one."""
pass
def init_bbox_head(self, bbox_head):
"""Initialize box head"""
"""Initialize box head."""
self.bbox_head = build_head(bbox_head)
def init_assigner_sampler(self):
"""Initialize assigner and sampler"""
"""Initialize assigner and sampler."""
self.bbox_assigner = None
self.bbox_sampler = None
if self.train_cfg:
......@@ -78,7 +78,7 @@ class PartAggregationROIHead(Base3DRoIHead):
def forward_train(self, feats_dict, voxels_dict, img_metas, proposal_list,
gt_bboxes_3d, gt_labels_3d):
"""Training forward function of PartAggregationROIHead
"""Training forward function of PartAggregationROIHead.
Args:
feats_dict (dict): Contains features from the first stage.
......@@ -116,7 +116,7 @@ class PartAggregationROIHead(Base3DRoIHead):
def simple_test(self, feats_dict, voxels_dict, img_metas, proposal_list,
**kwargs):
"""Simple testing forward function of PartAggregationROIHead
"""Simple testing forward function of PartAggregationROIHead.
Note:
This function assumes that the batch size is 1
......@@ -216,7 +216,7 @@ class PartAggregationROIHead(Base3DRoIHead):
return bbox_results
def _assign_and_sample(self, proposal_list, gt_bboxes_3d, gt_labels_3d):
"""Assign and sample proposals for training
"""Assign and sample proposals for training.
Args:
proposal_list (list[dict]): Proposals produced by RPN.
......@@ -290,7 +290,7 @@ class PartAggregationROIHead(Base3DRoIHead):
def _semantic_forward_train(self, x, voxels_dict, gt_bboxes_3d,
gt_labels_3d):
"""Train semantic head
"""Train semantic head.
Args:
x (torch.Tensor): Point-wise semantic features for segmentation
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment