Skip to content

GitLab

"torchvision/models/vscode:/vscode.git/clone" did not exist on "7c95f97a01a0a5f6f434d6b72b18673cace1fbd2"
Unverified Commit 8538177b authored by ChaimZhu's avatar ChaimZhu Committed by GitHub
Browse files

[Feature] Add MonoFlex Head (#1044)

parent 4590418e
Hide whitespace changes
Inline Side-by-side
Showing with 1093 additions and 26 deletions
mmdet3d/core/bbox/coders/monoflex_bbox_coder.py
View file @ 8538177b
......@@ -81,16 +81,16 @@ class MonoFlexCoder(BaseBBoxCoder):
torch.Tensor: Targets of orientations.
"""
local_yaw = gt_bboxes_3d.local_yaw
# encode local yaw (-pi ~ pi) to multibin format
encode_local_yaw = np.zeros(self.num_dir_bins * 2)
encode_local_yaw = local_yaw.new_zeros(
[local_yaw.shape[0], self.num_dir_bins * 2])
bin_size = 2 * np.pi / self.num_dir_bins
margin_size = bin_size * self.bin_margin
bin_centers = self.bin_centers
bin_centers = local_yaw.new_tensor(self.bin_centers)
range_size = bin_size / 2 + margin_size
offsets = local_yaw - bin_centers.unsqueeze(0)
offsets = local_yaw.unsqueeze(1) - bin_centers.unsqueeze(0)
offsets[offsets > np.pi] = offsets[offsets > np.pi] - 2 * np.pi
offsets[offsets < -np.pi] = offsets[offsets < -np.pi] + 2 * np.pi
......@@ -98,7 +98,7 @@ class MonoFlexCoder(BaseBBoxCoder):
offset = offsets[:, i]
inds = abs(offset) < range_size
encode_local_yaw[inds, i] = 1
encode_local_yaw[inds, i + self.num_dir_bins] = offset
encode_local_yaw[inds, i + self.num_dir_bins] = offset[inds]
orientation_target = encode_local_yaw
......@@ -164,7 +164,7 @@ class MonoFlexCoder(BaseBBoxCoder):
pred_direct_depth_uncertainty = bbox[:, 49:50].squeeze(-1)
# 2 dimension of offsets x keypoints (8 corners + top/bottom center)
pred_keypoints2d = bbox[:, 6:26]
pred_keypoints2d = bbox[:, 6:26].reshape(-1, 10, 2)
# 1 dimension for depth offsets
pred_direct_depth_offsets = bbox[:, 48:49].squeeze(-1)
......@@ -273,11 +273,11 @@ class MonoFlexCoder(BaseBBoxCoder):
raise NotImplementedError
# (N, 3)
centers2d_img = \
torch.cat(centers2d_img, depths.unsqueeze(-1), dim=1)
torch.cat((centers2d_img, depths.unsqueeze(-1)), dim=1)
# (N, 4, 1)
centers2d_extend = \
torch.cat((centers2d_img, centers2d_img.new_ones(N, 1)),
dim=1).unqueeze(-1)
dim=1).unsqueeze(-1)
locations = torch.matmul(cam2imgs_inv, centers2d_extend).squeeze(-1)
return locations[:, :3]
......@@ -450,15 +450,15 @@ class MonoFlexCoder(BaseBBoxCoder):
local_yaws = orientations
yaws = local_yaws + rays
larger_idx = (yaws > np.pi).nonzero()
small_idx = (yaws < -np.pi).nonzero()
larger_idx = (yaws > np.pi).nonzero(as_tuple=False)
small_idx = (yaws < -np.pi).nonzero(as_tuple=False)
if len(larger_idx) != 0:
yaws[larger_idx] -= 2 * np.pi
if len(small_idx) != 0:
yaws[small_idx] += 2 * np.pi
larger_idx = (local_yaws > np.pi).nonzero()
small_idx = (local_yaws < -np.pi).nonzero()
larger_idx = (local_yaws > np.pi).nonzero(as_tuple=False)
small_idx = (local_yaws < -np.pi).nonzero(as_tuple=False)
if len(larger_idx) != 0:
local_yaws[larger_idx] -= 2 * np.pi
if len(small_idx) != 0:
......@@ -491,7 +491,7 @@ class MonoFlexCoder(BaseBBoxCoder):
return bboxes2d
def combine_depths(depth, depth_uncertainty):
def combine_depths(self, depth, depth_uncertainty):
"""Combine all the prediced depths with depth uncertainty.
Args:
......
mmdet3d/core/bbox/structures/utils.py
View file @ 8538177b
......@@ -324,8 +324,11 @@ def yaw2local(yaw, loc):
torch.Tensor: local yaw (alpha in kitti).
"""
local_yaw = yaw - torch.atan2(loc[:, 0], loc[:, 2])
while local_yaw > np.pi:
local_yaw -= np.pi * 2
while local_yaw < -np.pi:
local_yaw += np.pi * 2
larger_idx = (local_yaw > np.pi).nonzero(as_tuple=False)
small_idx = (local_yaw < -np.pi).nonzero(as_tuple=False)
if len(larger_idx) != 0:
local_yaw[larger_idx] -= 2 * np.pi
if len(small_idx) != 0:
local_yaw[small_idx] += 2 * np.pi
return local_yaw
mmdet3d/core/utils/__init__.py
View file @ 8538177b
# Copyright (c) OpenMMLab. All rights reserved.
from .array_converter import ArrayConverter, array_converter
from .gaussian import draw_heatmap_gaussian, gaussian_2d, gaussian_radius
from .gaussian import (draw_heatmap_gaussian, ellip_gaussian2D, gaussian_2d,
gaussian_radius, get_ellip_gaussian_2D)
__all__ = [
'gaussian_2d', 'gaussian_radius', 'draw_heatmap_gaussian',
'ArrayConverter', 'array_converter'
'ArrayConverter', 'array_converter', 'ellip_gaussian2D',
'get_ellip_gaussian_2D'
]
mmdet3d/core/utils/gaussian.py
View file @ 8538177b
......@@ -84,3 +84,75 @@ def gaussian_radius(det_size, min_overlap=0.5):
sq3 = torch.sqrt(b3**2 - 4 * a3 * c3)
r3 = (b3 + sq3) / 2
return min(r1, r2, r3)
def get_ellip_gaussian_2D(heatmap, center, radius_x, radius_y, k=1):
"""Generate 2D ellipse gaussian heatmap.
Args:
heatmap (Tensor): Input heatmap, the gaussian kernel will cover on
it and maintain the max value.
center (list[int]): Coord of gaussian kernel's center.
radius_x (int): X-axis radius of gaussian kernel.
radius_y (int): Y-axis radius of gaussian kernel.
k (int, optional): Coefficient of gaussian kernel. Default: 1.
Returns:
out_heatmap (Tensor): Updated heatmap covered by gaussian kernel.
"""
diameter_x, diameter_y = 2 * radius_x + 1, 2 * radius_y + 1
gaussian_kernel = ellip_gaussian2D((radius_x, radius_y),
sigma_x=diameter_x / 6,
sigma_y=diameter_y / 6,
dtype=heatmap.dtype,
device=heatmap.device)
x, y = int(center[0]), int(center[1])
height, width = heatmap.shape[0:2]
left, right = min(x, radius_x), min(width - x, radius_x + 1)
top, bottom = min(y, radius_y), min(height - y, radius_y + 1)
masked_heatmap = heatmap[y - top:y + bottom, x - left:x + right]
masked_gaussian = gaussian_kernel[radius_y - top:radius_y + bottom,
radius_x - left:radius_x + right]
out_heatmap = heatmap
torch.max(
masked_heatmap,
masked_gaussian * k,
out=out_heatmap[y - top:y + bottom, x - left:x + right])
return out_heatmap
def ellip_gaussian2D(radius,
sigma_x,
sigma_y,
dtype=torch.float32,
device='cpu'):
"""Generate 2D ellipse gaussian kernel.
Args:
radius (tuple(int)): Ellipse radius (radius_x, radius_y) of gaussian
kernel.
sigma_x (int): X-axis sigma of gaussian function.
sigma_y (int): Y-axis sigma of gaussian function.
dtype (torch.dtype, optional): Dtype of gaussian tensor.
Default: torch.float32.
device (str, optional): Device of gaussian tensor.
Default: 'cpu'.
Returns:
h (Tensor): Gaussian kernel with a
``(2 * radius_y + 1) * (2 * radius_x + 1)`` shape.
"""
x = torch.arange(
-radius[0], radius[0] + 1, dtype=dtype, device=device).view(1, -1)
y = torch.arange(
-radius[1], radius[1] + 1, dtype=dtype, device=device).view(-1, 1)
h = (-(x * x) / (2 * sigma_x * sigma_x) - (y * y) /
(2 * sigma_y * sigma_y)).exp()
h[h < torch.finfo(h.dtype).eps * h.max()] = 0
return h
mmdet3d/models/dense_heads/__init__.py
View file @ 8538177b
......@@ -7,6 +7,7 @@ from .centerpoint_head import CenterHead
from .fcos_mono3d_head import FCOSMono3DHead
from .free_anchor3d_head import FreeAnchor3DHead
from .groupfree3d_head import GroupFree3DHead
from .monoflex_head import MonoFlexHead
from .parta2_rpn_head import PartA2RPNHead
from .pgd_head import PGDHead
from .point_rpn_head import PointRPNHead
......@@ -19,5 +20,6 @@ __all__ = [
'Anchor3DHead', 'FreeAnchor3DHead', 'PartA2RPNHead', 'VoteHead',
'SSD3DHead', 'BaseConvBboxHead', 'CenterHead', 'ShapeAwareHead',
'BaseMono3DDenseHead', 'AnchorFreeMono3DHead', 'FCOSMono3DHead',
'GroupFree3DHead', 'PointRPNHead', 'SMOKEMono3DHead', 'PGDHead'
'GroupFree3DHead', 'PointRPNHead', 'SMOKEMono3DHead', 'PGDHead',
'MonoFlexHead'
]
mmdet3d/models/dense_heads/monoflex_head.py 0 → 100644
View file @ 8538177b
import torch
from mmcv.cnn import xavier_init
from torch import nn as nn
from mmdet3d.core.utils import get_ellip_gaussian_2D
from mmdet3d.models.model_utils import EdgeFusionModule
from mmdet3d.models.utils import (filter_outside_objs, get_edge_indices,
get_keypoints, handle_proj_objs)
from mmdet.core import multi_apply
from mmdet.core.bbox.builder import build_bbox_coder
from mmdet.models.builder import HEADS, build_loss
from mmdet.models.utils import gaussian_radius, gen_gaussian_target
from mmdet.models.utils.gaussian_target import (get_local_maximum,
get_topk_from_heatmap,
transpose_and_gather_feat)
from .anchor_free_mono3d_head import AnchorFreeMono3DHead
@HEADS.register_module()
class MonoFlexHead(AnchorFreeMono3DHead):
r"""MonoFlex head used in `MonoFlex <https://arxiv.org/abs/2104.02323>`_
.. code-block:: none
/ --> 3 x 3 conv --> 1 x 1 conv --> [edge fusion] --> cls
|
| --> 3 x 3 conv --> 1 x 1 conv --> 2d bbox
|
| --> 3 x 3 conv --> 1 x 1 conv --> [edge fusion] --> 2d offsets
|
| --> 3 x 3 conv --> 1 x 1 conv --> keypoints offsets
|
| --> 3 x 3 conv --> 1 x 1 conv --> keypoints uncertainty
feature
| --> 3 x 3 conv --> 1 x 1 conv --> keypoints uncertainty
|
| --> 3 x 3 conv --> 1 x 1 conv --> 3d dimensions
|
| |--- 1 x 1 conv --> ori cls
| --> 3 x 3 conv --|
| |--- 1 x 1 conv --> ori offsets
|
| --> 3 x 3 conv --> 1 x 1 conv --> depth
|
\ --> 3 x 3 conv --> 1 x 1 conv --> depth uncertainty
Args:
use_edge_fusion (bool): Whether to use edge fusion module while
feature extraction.
edge_fusion_inds (list[tuple]): Indices of feature to use edge fusion.
edge_heatmap_ratio (float): Ratio of generating target heatmap.
filter_outside_objs (bool, optional): Whether to filter the
outside objects. Default: True.
loss_cls (dict, optional): Config of classification loss.
Default: loss_cls=dict(type='GaussionFocalLoss', loss_weight=1.0).
loss_bbox (dict, optional): Config of localization loss.
Default: loss_bbox=dict(type='IOULoss', loss_weight=10.0).
loss_dir (dict, optional): Config of direction classification loss.
Default: dict(type='MultibinLoss', loss_weight=0.1).
loss_keypoints (dict, optional): Config of keypoints loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_dims: (dict, optional): Config of dimensions loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_offsets2d: (dict, optional): Config of offsets2d loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_direct_depth: (dict, optional): Config of directly regression depth loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_keypoints_depth: (dict, optional): Config of keypoints decoded depth loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_combined_depth: (dict, optional): Config of combined depth loss.
Default: dict(type='L1Loss', loss_weight=0.1).
loss_attr (dict, optional): Config of attribute classification loss.
In MonoFlex, Default: None.
bbox_coder (dict, optional): Bbox coder for encoding and decoding boxes.
Default: dict(type='MonoFlexCoder', code_size=7).
norm_cfg (dict, optional): Dictionary to construct and config norm layer.
Default: norm_cfg=dict(type='GN', num_groups=32, requires_grad=True).
init_cfg (dict): Initialization config dict. Default: None.
""" # noqa: E501
def __init__(self,
num_classes,
in_channels,
use_edge_fusion,
edge_fusion_inds,
edge_heatmap_ratio,
filter_outside_objs=True,
loss_cls=dict(type='GaussianFocalLoss', loss_weight=1.0),
loss_bbox=dict(type='IoULoss', loss_weight=0.1),
loss_dir=dict(type='MultiBinLoss', loss_weight=0.1),
loss_keypoints=dict(type='L1Loss', loss_weight=0.1),
loss_dims=dict(type='L1Loss', loss_weight=0.1),
loss_offsets2d=dict(type='L1Loss', loss_weight=0.1),
loss_direct_depth=dict(type='L1Loss', loss_weight=0.1),
loss_keypoints_depth=dict(type='L1Loss', loss_weight=0.1),
loss_combined_depth=dict(type='L1Loss', loss_weight=0.1),
loss_attr=None,
bbox_coder=dict(type='MonoFlexCoder', code_size=7),
norm_cfg=dict(type='BN'),
init_cfg=None,
init_bias=-2.19,
**kwargs):
self.use_edge_fusion = use_edge_fusion
self.edge_fusion_inds = edge_fusion_inds
super().__init__(
num_classes,
in_channels,
loss_cls=loss_cls,
loss_bbox=loss_bbox,
loss_dir=loss_dir,
loss_attr=loss_attr,
norm_cfg=norm_cfg,
init_cfg=init_cfg,
**kwargs)
self.filter_outside_objs = filter_outside_objs
self.edge_heatmap_ratio = edge_heatmap_ratio
self.init_bias = init_bias
self.loss_dir = build_loss(loss_dir)
self.loss_keypoints = build_loss(loss_keypoints)
self.loss_dims = build_loss(loss_dims)
self.loss_offsets2d = build_loss(loss_offsets2d)
self.loss_direct_depth = build_loss(loss_direct_depth)
self.loss_keypoints_depth = build_loss(loss_keypoints_depth)
self.loss_combined_depth = build_loss(loss_combined_depth)
self.bbox_coder = build_bbox_coder(bbox_coder)
def _init_edge_module(self):
"""Initialize edge fusion module for feature extraction."""
self.edge_fuse_cls = EdgeFusionModule(self.num_classes, 256)
for i in range(len(self.edge_fusion_inds)):
reg_inds, out_inds = self.edge_fusion_inds[i]
out_channels = self.group_reg_dims[reg_inds][out_inds]
fusion_layer = EdgeFusionModule(out_channels, 256)
layer_name = f'edge_fuse_reg_{reg_inds}_{out_inds}'
self.add_module(layer_name, fusion_layer)
def init_weights(self):
"""Initialize weights."""
super().init_weights()
self.conv_cls.bias.data.fill_(self.init_bias)
xavier_init(self.conv_regs[4][0], gain=0.01)
xavier_init(self.conv_regs[7][0], gain=0.01)
for m in self.conv_regs.modules():
if isinstance(m, nn.Conv2d):
if m.bias is not None:
nn.init.constant_(m.bias, 0)
def _init_predictor(self):
"""Initialize predictor layers of the head."""
self.conv_cls_prev = self._init_branch(
conv_channels=self.cls_branch,
conv_strides=(1, ) * len(self.cls_branch))
self.conv_cls = nn.Conv2d(self.cls_branch[-1], self.cls_out_channels,
1)
# init regression head
self.conv_reg_prevs = nn.ModuleList()
# init output head
self.conv_regs = nn.ModuleList()
# group_reg_dims:
# ((4, ), (2, ), (20, ), (3, ), (3, ), (8, 8), (1, ), (1, ))
for i in range(len(self.group_reg_dims)):
reg_dims = self.group_reg_dims[i]
reg_branch_channels = self.reg_branch[i]
out_channel = self.out_channels[i]
reg_list = nn.ModuleList()
if len(reg_branch_channels) > 0:
self.conv_reg_prevs.append(
self._init_branch(
conv_channels=reg_branch_channels,
conv_strides=(1, ) * len(reg_branch_channels)))
for reg_dim in reg_dims:
reg_list.append(nn.Conv2d(out_channel, reg_dim, 1))
self.conv_regs.append(reg_list)
else:
self.conv_reg_prevs.append(None)
for reg_dim in reg_dims:
reg_list.append(nn.Conv2d(self.feat_channels, reg_dim, 1))
self.conv_regs.append(reg_list)
def _init_layers(self):
"""Initialize layers of the head."""
self._init_predictor()
if self.use_edge_fusion:
self._init_edge_module()
def forward_train(self, x, input_metas, gt_bboxes, gt_labels, gt_bboxes_3d,
gt_labels_3d, centers2d, depths, attr_labels,
gt_bboxes_ignore, proposal_cfg, **kwargs):
"""
Args:
x (list[Tensor]): Features from FPN.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes (list[Tensor]): Ground truth bboxes of the image,
shape (num_gts, 4).
gt_labels (list[Tensor]): Ground truth labels of each box,
shape (num_gts,).
gt_bboxes_3d (list[Tensor]): 3D ground truth bboxes of the image,
shape (num_gts, self.bbox_code_size).
gt_labels_3d (list[Tensor]): 3D ground truth labels of each box,
shape (num_gts,).
centers2d (list[Tensor]): Projected 3D center of each box,
shape (num_gts, 2).
depths (list[Tensor]): Depth of projected 3D center of each box,
shape (num_gts,).
attr_labels (list[Tensor]): Attribute labels of each box,
shape (num_gts,).
gt_bboxes_ignore (list[Tensor]): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
proposal_cfg (mmcv.Config): Test / postprocessing configuration,
if None, test_cfg would be used
Returns:
tuple:
losses: (dict[str, Tensor]): A dictionary of loss components.
proposal_list (list[Tensor]): Proposals of each image.
"""
outs = self(x, input_metas)
if gt_labels is None:
loss_inputs = outs + (gt_bboxes, gt_bboxes_3d, centers2d, depths,
attr_labels, input_metas)
else:
loss_inputs = outs + (gt_bboxes, gt_labels, gt_bboxes_3d,
gt_labels_3d, centers2d, depths, attr_labels,
input_metas)
losses = self.loss(*loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
if proposal_cfg is None:
return losses
else:
proposal_list = self.get_bboxes(
*outs, input_metas, cfg=proposal_cfg)
return losses, proposal_list
def forward(self, feats, input_metas):
"""Forward features from the upstream network.
Args:
feats (list[Tensor]): Features from the upstream network, each is
a 4D-tensor.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
Returns:
tuple:
cls_scores (list[Tensor]): Box scores for each scale level,
each is a 4D-tensor, the channel number is
num_points * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level, each is a 4D-tensor, the channel number is
num_points * bbox_code_size.
"""
mlvl_input_metas = [input_metas for i in range(len(feats))]
return multi_apply(self.forward_single, feats, mlvl_input_metas)
def forward_single(self, x, input_metas):
"""Forward features of a single scale level.
Args:
x (Tensor): Feature maps from a specific FPN feature level.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
Returns:
tuple: Scores for each class, bbox predictions.
"""
img_h, img_w = input_metas[0]['pad_shape'][:2]
batch_size, _, feat_h, feat_w = x.shape
downsample_ratio = img_h / feat_h
for conv_cls_prev_layer in self.conv_cls_prev:
cls_feat = conv_cls_prev_layer(x)
out_cls = self.conv_cls(cls_feat)
if self.use_edge_fusion:
# calculate the edge indices for the batch data
edge_indices_list = get_edge_indices(
input_metas, downsample_ratio, device=x.device)
edge_lens = [
edge_indices.shape[0] for edge_indices in edge_indices_list
]
max_edge_len = max(edge_lens)
edge_indices = x.new_zeros((batch_size, max_edge_len, 2),
dtype=torch.long)
for i in range(batch_size):
edge_indices[i, :edge_lens[i]] = edge_indices_list[i]
# cls feature map edge fusion
out_cls = self.edge_fuse_cls(cls_feat, out_cls, edge_indices,
edge_lens, feat_h, feat_w)
bbox_pred = []
for i in range(len(self.group_reg_dims)):
reg_feat = x.clone()
# feature regression head
if len(self.reg_branch[i]) > 0:
for conv_reg_prev_layer in self.conv_reg_prevs[i]:
reg_feat = conv_reg_prev_layer(reg_feat)
for j, conv_reg in enumerate(self.conv_regs[i]):
out_reg = conv_reg(reg_feat)
# Use Edge Fusion Module
if self.use_edge_fusion and (i, j) in self.edge_fusion_inds:
# reg feature map edge fusion
out_reg = getattr(self, 'edge_fuse_reg_{}_{}'.format(
i, j))(reg_feat, out_reg, edge_indices, edge_lens,
feat_h, feat_w)
bbox_pred.append(out_reg)
bbox_pred = torch.cat(bbox_pred, dim=1)
cls_score = out_cls.sigmoid() # turn to 0-1
cls_score = cls_score.clamp(min=1e-4, max=1 - 1e-4)
return cls_score, bbox_pred
def get_bboxes(self, cls_scores, bbox_preds, input_metas):
"""Generate bboxes from bbox head predictions.
Args:
cls_scores (list[Tensor]): Box scores for each scale level.
bbox_preds (list[Tensor]): Box regression for each scale.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
rescale (bool): If True, return boxes in original image space.
Returns:
list[tuple[:obj:`CameraInstance3DBoxes`, Tensor, Tensor, None]]:
Each item in result_list is 4-tuple.
"""
assert len(cls_scores) == len(bbox_preds) == 1
cam2imgs = torch.stack([
cls_scores[0].new_tensor(input_meta['cam2img'])
for input_meta in input_metas
])
batch_bboxes, batch_scores, batch_topk_labels = self.decode_heatmap(
cls_scores[0],
bbox_preds[0],
input_metas,
cam2imgs=cam2imgs,
topk=100,
kernel=3)
result_list = []
for img_id in range(len(input_metas)):
bboxes = batch_bboxes[img_id]
scores = batch_scores[img_id]
labels = batch_topk_labels[img_id]
keep_idx = scores > 0.25
bboxes = bboxes[keep_idx]
scores = scores[keep_idx]
labels = labels[keep_idx]
bboxes = input_metas[img_id]['box_type_3d'](
bboxes, box_dim=self.bbox_code_size, origin=(0.5, 0.5, 0.5))
attrs = None
result_list.append((bboxes, scores, labels, attrs))
return result_list
def decode_heatmap(self,
cls_score,
reg_pred,
input_metas,
cam2imgs,
topk=100,
kernel=3):
"""Transform outputs into detections raw bbox predictions.
Args:
class_score (Tensor): Center predict heatmap,
shape (B, num_classes, H, W).
reg_pred (Tensor): Box regression map.
shape (B, channel, H , W).
input_metas (List[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
cam2imgs (Tensor): Camera intrinsic matrix.
shape (N, 4, 4)
topk (int, optional): Get top k center keypoints from heatmap.
Default 100.
kernel (int, optional): Max pooling kernel for extract local
maximum pixels. Default 3.
Returns:
tuple[torch.Tensor]: Decoded output of SMOKEHead, containing
the following Tensors:
- batch_bboxes (Tensor): Coords of each 3D box.
shape (B, k, 7)
- batch_scores (Tensor): Scores of each 3D box.
shape (B, k)
- batch_topk_labels (Tensor): Categories of each 3D box.
shape (B, k)
"""
img_h, img_w = input_metas[0]['pad_shape'][:2]
batch_size, _, feat_h, feat_w = cls_score.shape
downsample_ratio = img_h / feat_h
center_heatmap_pred = get_local_maximum(cls_score, kernel=kernel)
*batch_dets, topk_ys, topk_xs = get_topk_from_heatmap(
center_heatmap_pred, k=topk)
batch_scores, batch_index, batch_topk_labels = batch_dets
regression = transpose_and_gather_feat(reg_pred, batch_index)
regression = regression.view(-1, 8)
pred_base_centers2d = torch.cat(
[topk_xs.view(-1, 1),
topk_ys.view(-1, 1).float()], dim=1)
preds = self.bbox_coder.decode(regression, batch_topk_labels,
downsample_ratio, cam2imgs)
pred_locations = self.bbox_coder.decode_location(
pred_base_centers2d, preds['offsets2d'], preds['combined_depth'],
cam2imgs, downsample_ratio)
pred_yaws = self.bbox_coder.decode_orientation(
preds['orientations']).unsqueeze(-1)
pred_dims = preds['dimensions']
batch_bboxes = torch.cat((pred_locations, pred_dims, pred_yaws), dim=1)
batch_bboxes = batch_bboxes.view(batch_size, -1, self.bbox_code_size)
return batch_bboxes, batch_scores, batch_topk_labels
def get_predictions(self, pred_reg, labels3d, centers2d, reg_mask,
batch_indices, input_metas, downsample_ratio):
"""Prepare predictions for computing loss.
Args:
pred_reg (Tensor): Box regression map.
shape (B, channel, H , W).
labels3d (Tensor): Labels of each 3D box.
shape (B * max_objs, )
centers2d (Tensor): Coords of each projected 3D box
center on image. shape (N, 2)
reg_mask (Tensor): Indexes of the existence of the 3D box.
shape (B * max_objs, )
batch_indices (Tenosr): Batch indices of the 3D box.
shape (N, 3)
input_metas (list[dict]): Meta information of each image,
e.g., image size, scaling factor, etc.
downsample_ratio (int): The stride of feature map.
Returns:
dict: The predictions for computing loss.
"""
batch, channel = pred_reg.shape[0], pred_reg.shape[1]
w = pred_reg.shape[3]
cam2imgs = torch.stack([
centers2d.new_tensor(input_meta['cam2img'])
for input_meta in input_metas
])
# (batch_size, 4, 4) -> (N, 4, 4)
cam2imgs = cam2imgs[batch_indices, :, :]
centers2d_inds = centers2d[:, 1] * w + centers2d[:, 0]
centers2d_inds = centers2d_inds.view(batch, -1)
pred_regression = transpose_and_gather_feat(pred_reg, centers2d_inds)
pred_regression_pois = pred_regression.view(-1, channel)[reg_mask]
preds = self.bbox_coder.decode(pred_regression_pois, labels3d,
downsample_ratio, cam2imgs)
return preds
def get_targets(self, gt_bboxes_list, gt_labels_list, gt_bboxes_3d_list,
gt_labels_3d_list, centers2d_list, depths_list, feat_shape,
img_shape, input_metas):
"""Get training targets for batch images.
``
Args:
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each
image, shape (num_gt, 4).
gt_labels_list (list[Tensor]): Ground truth labels of each
box, shape (num_gt,).
gt_bboxes_3d_list (list[:obj:`CameraInstance3DBoxes`]): 3D
Ground truth bboxes of each image,
shape (num_gt, bbox_code_size).
gt_labels_3d_list (list[Tensor]): 3D Ground truth labels of
each box, shape (num_gt,).
centers2d_list (list[Tensor]): Projected 3D centers onto 2D
image, shape (num_gt, 2).
depths_list (list[Tensor]): Depth of projected 3D centers onto 2D
image, each has shape (num_gt, 1).
feat_shape (tuple[int]): Feature map shape with value,
shape (B, _, H, W).
img_shape (tuple[int]): Image shape in [h, w] format.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
Returns:
tuple[Tensor, dict]: The Tensor value is the targets of
center heatmap, the dict has components below:
- base_centers2d_target (Tensor): Coords of each projected 3D box
center on image. shape (B * max_objs, 2), [dtype: int]
- labels3d (Tensor): Labels of each 3D box.
shape (N, )
- reg_mask (Tensor): Mask of the existence of the 3D box.
shape (B * max_objs, )
- batch_indices (Tensor): Batch id of the 3D box.
shape (N, )
- depth_target (Tensor): Depth target of each 3D box.
shape (N, )
- keypoints2d_target (Tensor): Keypoints of each projected 3D box
on image. shape (N, 10, 2)
- keypoints_mask (Tensor): Keypoints mask of each projected 3D
box on image. shape (N, 10)
- keypoints_depth_mask (Tensor): Depths decoded from keypoints
of each 3D box. shape (N, 3)
- orientations_target (Tensor): Orientation (encoded local yaw)
target of each 3D box. shape (N, )
- offsets2d_target (Tensor): Offsets target of each projected
3D box. shape (N, 2)
- dimensions_target (Tensor): Dimensions target of each 3D box.
shape (N, 3)
- downsample_ratio (int): The stride of feature map.
"""
img_h, img_w = img_shape[:2]
batch_size, _, feat_h, feat_w = feat_shape
width_ratio = float(feat_w / img_w) # 1/4
height_ratio = float(feat_h / img_h) # 1/4
assert width_ratio == height_ratio
# Whether to filter the objects which are not in FOV.
if self.filter_outside_objs:
filter_outside_objs(gt_bboxes_list, gt_labels_list,
gt_bboxes_3d_list, gt_labels_3d_list,
centers2d_list, input_metas)
# transform centers2d to base centers2d for regression and
# heatmap generation.
# centers2d = int(base_centers2d) + offsets2d
base_centers2d_list, offsets2d_list, trunc_mask_list = \
handle_proj_objs(centers2d_list, gt_bboxes_list, input_metas)
keypoints2d_list, keypoints_mask_list, keypoints_depth_mask_list = \
get_keypoints(gt_bboxes_3d_list, centers2d_list, input_metas)
center_heatmap_target = gt_bboxes_list[-1].new_zeros(
[batch_size, self.num_classes, feat_h, feat_w])
for batch_id in range(batch_size):
# project gt_bboxes from input image to feat map
gt_bboxes = gt_bboxes_list[batch_id] * width_ratio
gt_labels = gt_labels_list[batch_id]
# project base centers2d from input image to feat map
gt_base_centers2d = base_centers2d_list[batch_id] * width_ratio
trunc_masks = trunc_mask_list[batch_id]
for j, base_center2d in enumerate(gt_base_centers2d):
if trunc_masks[j]:
# for outside objects, generate ellipse heatmap
base_center2d_x_int, base_center2d_y_int = \
base_center2d.int()
scale_box_w = min(base_center2d_x_int - gt_bboxes[j][0],
gt_bboxes[j][2] - base_center2d_x_int)
scale_box_h = min(base_center2d_y_int - gt_bboxes[j][1],
gt_bboxes[j][3] - base_center2d_y_int)
radius_x = scale_box_w * self.edge_heatmap_ratio
radius_y = scale_box_h * self.edge_heatmap_ratio
radius_x, radius_y = max(0, int(radius_x)), max(
0, int(radius_y))
assert min(radius_x, radius_y) == 0
ind = gt_labels[j]
get_ellip_gaussian_2D(
center_heatmap_target[batch_id, ind],
[base_center2d_x_int, base_center2d_y_int], radius_x,
radius_y)
else:
base_center2d_x_int, base_center2d_y_int = \
base_center2d.int()
scale_box_h = (gt_bboxes[j][3] - gt_bboxes[j][1])
scale_box_w = (gt_bboxes[j][2] - gt_bboxes[j][0])
radius = gaussian_radius([scale_box_h, scale_box_w],
min_overlap=0.7)
radius = max(0, int(radius))
ind = gt_labels[j]
gen_gaussian_target(
center_heatmap_target[batch_id, ind],
[base_center2d_x_int, base_center2d_y_int], radius)
avg_factor = max(1, center_heatmap_target.eq(1).sum())
num_ctrs = [centers2d.shape[0] for centers2d in centers2d_list]
max_objs = max(num_ctrs)
batch_indices = [
centers2d_list[0].new_full((num_ctrs[i], ), i)
for i in range(batch_size)
]
batch_indices = torch.cat(batch_indices, dim=0)
reg_mask = torch.zeros(
(batch_size, max_objs),
dtype=torch.bool).to(base_centers2d_list[0].device)
gt_bboxes_3d = input_metas['box_type_3d'].cat(gt_bboxes_3d_list)
gt_bboxes_3d = gt_bboxes_3d.to(base_centers2d_list[0].device)
# encode original local yaw to multibin format
orienations_target = self.bbox_coder.encode(gt_bboxes_3d)
batch_base_centers2d = base_centers2d_list[0].new_zeros(
(batch_size, max_objs, 2))
for i in range(batch_size):
reg_mask[i, :num_ctrs[i]] = 1
batch_base_centers2d[i, :num_ctrs[i]] = base_centers2d_list[i]
flatten_reg_mask = reg_mask.flatten()
# transform base centers2d from input scale to output scale
batch_base_centers2d = batch_base_centers2d.view(-1, 2) * width_ratio
dimensions_target = gt_bboxes_3d.tensor[:, 3:6]
labels_3d = torch.cat(gt_labels_3d_list)
keypoints2d_target = torch.cat(keypoints2d_list)
keypoints_mask = torch.cat(keypoints_mask_list)
keypoints_depth_mask = torch.cat(keypoints_depth_mask_list)
offsets2d_target = torch.cat(offsets2d_list)
bboxes2d = torch.cat(gt_bboxes_list)
# transform FCOS style bbox into [x1, y1, x2, y2] format.
bboxes2d_target = torch.cat([bboxes2d[:, 0:2] * -1, bboxes2d[:, 2:]],
dim=-1)
depths = torch.cat(depths_list)
target_labels = dict(
base_centers2d_target=batch_base_centers2d.int(),
labels3d=labels_3d,
reg_mask=flatten_reg_mask,
batch_indices=batch_indices,
bboxes2d_target=bboxes2d_target,
depth_target=depths,
keypoints2d_target=keypoints2d_target,
keypoints_mask=keypoints_mask,
keypoints_depth_mask=keypoints_depth_mask,
orienations_target=orienations_target,
offsets2d_target=offsets2d_target,
dimensions_target=dimensions_target,
downsample_ratio=1 / width_ratio)
return center_heatmap_target, avg_factor, target_labels
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
gt_bboxes_3d,
gt_labels_3d,
centers2d,
depths,
attr_labels,
input_metas,
gt_bboxes_ignore=None):
"""Compute loss of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level.
shape (num_gt, 4).
bbox_preds (list[Tensor]): Box dims is a 4D-tensor, the channel
number is bbox_code_size.
shape (B, 7, H, W).
gt_bboxes (list[Tensor]): Ground truth bboxes for each image.
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): Class indices corresponding to each box.
shape (num_gts, ).
gt_bboxes_3d (list[:obj:`CameraInstance3DBoxes`]): 3D boxes ground
truth. it is the flipped gt_bboxes
gt_labels_3d (list[Tensor]): Same as gt_labels.
centers2d (list[Tensor]): 2D centers on the image.
shape (num_gts, 2).
depths (list[Tensor]): Depth ground truth.
shape (num_gts, ).
attr_labels (list[Tensor]): Attributes indices of each box.
In kitti it's None.
input_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (None | list[Tensor]): Specify which bounding
boxes can be ignored when computing the loss.
Default: None.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
assert len(cls_scores) == len(bbox_preds) == 1
assert attr_labels is None
assert gt_bboxes_ignore is None
center2d_heatmap = cls_scores[0]
pred_reg = bbox_preds[0]
center2d_heatmap_target, avg_factor, target_labels = \
self.get_targets(gt_bboxes, gt_labels, gt_bboxes_3d,
gt_labels_3d, centers2d, depths,
center2d_heatmap.shape,
input_metas[0]['pad_shape'],
input_metas)
preds = self.get_predictions(
pred_reg=pred_reg,
labels3d=target_labels['labels3d'],
centers2d=target_labels['base_centers2d_target'],
reg_mask=target_labels['reg_mask'],
batch_indices=target_labels['batch_indices'],
input_metas=input_metas,
downsample_ratio=target_labels['downsample_ratio'])
# heatmap loss
loss_cls = self.loss_cls(
center2d_heatmap, center2d_heatmap_target, avg_factor=avg_factor)
# bbox2d regression loss
loss_bbox = self.loss_bbox(preds['bboxes2d'],
target_labels['bboxes2d_target'])
# keypoints loss, the keypoints in predictions and target are all
# local coordinates. Check the mask dtype should be bool, not int
# or float to ensure the indexing is bool index
keypoints2d_mask = target_labels['keypoints2d_mask']
loss_keypoints = self.loss_keypoints(
preds['keypoints2d'][keypoints2d_mask],
target_labels['keypoints2d_target'][keypoints2d_mask])
# orientations loss
loss_dir = self.loss_dir(preds['orientations'],
target_labels['orientations_target'])
# dimensions loss
loss_dims = self.loss_dims(preds['dimensions'],
target_labels['dimensions_target'])
# offsets for center heatmap
loss_offsets2d = self.loss_offsets2d(preds['offsets2d'],
target_labels['offsets2d_target'])
# directly regressed depth loss with direct depth uncertainty loss
direct_depth_weights = torch.exp(-preds['direct_depth_uncertainty'])
loss_weight_1 = self.loss_direct_depth.loss_weight
loss_direct_depth = self.loss_direct_depth(
preds['direct_depth'], target_labels['depth_target'],
direct_depth_weights)
loss_uncertainty_1 =\
preds['direct_depth_uncertainty'] * loss_weight_1
loss_direct_depth = loss_direct_depth + loss_uncertainty_1.mean()
# keypoints decoded depth loss with keypoints depth uncertainty loss
depth_mask = target_labels['keypoints_depth_mask']
depth_target = target_labels['depth_target'].unsqueeze(-1).repeat(1, 3)
valid_keypoints_depth_uncertainty = preds[
'keypoints_depth_uncertainty'][depth_mask]
valid_keypoints_depth_weights = torch.exp(
-valid_keypoints_depth_uncertainty)
loss_keypoints_depth = self.loss_keypoint_depth(
preds['keypoints_depth'][depth_mask], depth_target[depth_mask],
valid_keypoints_depth_weights)
loss_weight_2 = self.loss_keypoints_depth.loss_weight
loss_uncertainty_2 =\
valid_keypoints_depth_uncertainty * loss_weight_2
loss_keypoints_depth = loss_keypoints_depth + loss_uncertainty_2.mean()
# combined depth loss for optimiaze the uncertainty
loss_combined_depth = self.loss_combined_depth(
preds['combined_depth'], target_labels['depth_target'])
loss_dict = dict(
loss_cls=loss_cls,
loss_bbox=loss_bbox,
loss_keypoints=loss_keypoints,
loss_dir=loss_dir,
loss_dims=loss_dims,
loss_offsets2d=loss_offsets2d,
loss_direct_depth=loss_direct_depth,
loss_keypoints_depth=loss_keypoints_depth,
loss_combined_depth=loss_combined_depth)
return loss_dict
mmdet3d/models/model_utils/__init__.py
View file @ 8538177b
# Copyright (c) OpenMMLab. All rights reserved.
from .edge_fusion_module import EdgeFusionModule
from .transformer import GroupFree3DMHA
from .vote_module import VoteModule
__all__ = ['VoteModule', 'GroupFree3DMHA']
__all__ = ['VoteModule', 'GroupFree3DMHA', 'EdgeFusionModule']
mmdet3d/models/model_utils/edge_fusion_module.py 0 → 100644
View file @ 8538177b
from mmcv.cnn import ConvModule
from mmcv.runner import BaseModule
from torch import nn as nn
from torch.nn import functional as F
class EdgeFusionModule(BaseModule):
"""Edge Fusion Module for feature map.
Args:
out_channels (int): The number of output channels.
feat_channels (int): The number of channels in feature map
during edge feature fusion.
kernel_size (int, optional): Kernel size of convolution.
Default: 3.
act_cfg (dict, optional): Config of activation.
Default: dict(type='ReLU').
norm_cfg (dict, optional): Config of normalization.
Default: dict(type='BN1d')).
"""
def __init__(self,
out_channels,
feat_channels,
kernel_size=3,
act_cfg=dict(type='ReLU'),
norm_cfg=dict(type='BN1d')):
super().__init__()
self.edge_convs = nn.Sequential(
ConvModule(
feat_channels,
feat_channels,
kernel_size=kernel_size,
padding=kernel_size // 2,
conv_cfg=dict(type='Conv1d'),
norm_cfg=norm_cfg,
act_cfg=act_cfg),
nn.Conv1d(feat_channels, out_channels, kernel_size=1))
self.feat_channels = feat_channels
def forward(self, features, fused_features, edge_indices, edge_lens,
output_h, output_w):
"""Forward pass.
Args:
features (torch.Tensor): Different representative features
for fusion.
fused_features (torch.Tensor): Different representative
features to be fused.
edge_indices (torch.Tensor): Batch image edge indices.
edge_lens (list[int]): List of edge length of each image.
output_h (int): Height of output feature map.
output_w (int): Width of output feature map.
Returns:
torch.Tensor: Fused feature maps.
"""
batch_size = features.shape[0]
# normalize
grid_edge_indices = edge_indices.view(batch_size, -1, 1, 2).float()
grid_edge_indices[..., 0] = \
grid_edge_indices[..., 0] / (output_w - 1) * 2 - 1
grid_edge_indices[..., 1] = \
grid_edge_indices[..., 1] / (output_h - 1) * 2 - 1
# apply edge fusion
edge_features = F.grid_sample(
features, grid_edge_indices, align_corners=True).squeeze(-1)
edge_output = self.edge_convs(edge_features)
for k in range(batch_size):
edge_indice_k = edge_indices[k, :edge_lens[k]]
fused_features[k, :, edge_indice_k[:, 1],
edge_indice_k[:, 0]] += edge_output[
k, :, :edge_lens[k]]
return fused_features
mmdet3d/models/utils/edge_indices.py
View file @ 8538177b
......@@ -4,6 +4,7 @@ import torch
def get_edge_indices(img_metas,
downsample_ratio,
step=1,
pad_mode='default',
dtype=np.float32,
......@@ -17,6 +18,7 @@ def get_edge_indices(img_metas,
Args:
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
downsample_ratio (int): Downsample ratio of output feature,
step (int, optional): Step size used for generateing
edge indices. Default: 1.
pad_mode (str, optional): Padding mode during data pipeline.
......@@ -32,13 +34,21 @@ def get_edge_indices(img_metas,
edge_indices_list = []
for i in range(len(img_metas)):
img_shape = img_metas[i]['img_shape']
pad_shape = img_metas[i]['pad_shape']
h, w = img_shape[:2]
pad_h, pad_w = pad_shape
edge_indices = []
if pad_mode == 'default':
x_min = 0
y_min = 0
x_max, y_max = w - 1, h - 1
x_max = (w - 1) // downsample_ratio
y_max = (h - 1) // downsample_ratio
elif pad_mode == 'center':
x_min = np.ceil((pad_w - w) / 2 * downsample_ratio)
y_min = np.ceil((pad_h - h) / 2 * downsample_ratio)
x_max = x_min + w // downsample_ratio
y_max = y_min + h // downsample_ratio
else:
raise NotImplementedError
......
tests/test_models/test_heads/test_heads.py
View file @ 8538177b
......@@ -1505,3 +1505,62 @@ def test_pgd_head():
assert results[0][2].shape == torch.Size([20])
assert results[0][3] is None
assert results[0][4].shape == torch.Size([20, 5])
def test_monoflex_head():
head_cfg = dict(
type='MonoFlexHead',
num_classes=3,
in_channels=64,
use_edge_fusion=True,
edge_fusion_inds=[(1, 0)],
edge_heatmap_ratio=1 / 8,
stacked_convs=0,
feat_channels=64,
use_direction_classifier=False,
diff_rad_by_sin=False,
pred_attrs=False,
pred_velo=False,
dir_offset=0,
strides=None,
group_reg_dims=((4, ), (2, ), (20, ), (3, ), (3, ), (8, 8), (1, ),
(1, )),
cls_branch=(256, ),
reg_branch=((256, ), (256, ), (256, ), (256, ), (256, ), (256, ),
(256, ), (256, )),
num_attrs=0,
bbox_code_size=7,
dir_branch=(),
attr_branch=(),
bbox_coder=dict(
type='MonoFlexCoder',
depth_mode='exp',
base_depth=(26.494627, 16.05988),
depth_range=[0.1, 100],
combine_depth=True,
uncertainty_range=[-10, 10],
base_dims=((3.8840, 1.5261, 1.6286, 0.4259, 0.1367, 0.1022),
(0.8423, 1.7607, 0.6602, 0.2349, 0.1133, 0.1427),
(1.7635, 1.7372, 0.5968, 0.1766, 0.0948, 0.1242)),
dims_mode='linear',
multibin=True,
num_dir_bins=4,
bin_centers=[0, np.pi / 2, np.pi, -np.pi / 2],
bin_margin=np.pi / 6,
code_size=7),
conv_bias=True,
dcn_on_last_conv=False)
self = build_head(head_cfg)
feats = [torch.rand([2, 64, 32, 32], dtype=torch.float32)]
input_metas = [
dict(img_shape=(110, 110), pad_shape=(128, 128)),
dict(img_shape=(98, 110), pad_shape=(128, 128))
]
cls_score, out_reg = self(feats, input_metas)
assert cls_score[0].shape == torch.Size([2, 3, 32, 32])
assert out_reg[0].shape == torch.Size([2, 50, 32, 32])
tests/test_utils/test_bbox_coders.py
View file @ 8538177b
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import torch
from mmcv.cnn import Scale
from torch import nn as nn
......@@ -596,3 +597,69 @@ def test_smoke_bbox_coder():
locations = torch.tensor([[15., 2., 1.], [15., 2., -1.]])
orientations = bbox_coder._decode_orientation(ori_vector, locations)
assert orientations.shape == torch.Size([2, 1])
def test_monoflex_bbox_coder():
bbox_coder_cfg = dict(
type='MonoFlexCoder',
depth_mode='exp',
base_depth=(26.494627, 16.05988),
depth_range=[0.1, 100],
combine_depth=True,
uncertainty_range=[-10, 10],
base_dims=((3.8840, 1.5261, 1.6286, 0.4259, 0.1367,
0.1022), (0.8423, 1.7607, 0.6602, 0.2349, 0.1133, 0.1427),
(1.7635, 1.7372, 0.5968, 0.1766, 0.0948, 0.1242)),
dims_mode='linear',
multibin=True,
num_dir_bins=4,
bin_centers=[0, np.pi / 2, np.pi, -np.pi / 2],
bin_margin=np.pi / 6,
code_size=7)
bbox_coder = build_bbox_coder(bbox_coder_cfg)
gt_bboxes_3d = CameraInstance3DBoxes(torch.rand([6, 7]))
orientation_target = bbox_coder.encode(gt_bboxes_3d)
assert orientation_target.shape == torch.Size([6, 8])
regression = torch.rand([100, 50])
base_centers2d = torch.rand([100, 2])
labels = torch.ones([100])
downsample_ratio = 4
cam2imgs = torch.rand([100, 4, 4])
preds = bbox_coder.decode(regression, base_centers2d, labels,
downsample_ratio, cam2imgs)
assert preds['bboxes2d'].shape == torch.Size([100, 4])
assert preds['dimensions'].shape == torch.Size([100, 3])
assert preds['offsets2d'].shape == torch.Size([100, 2])
assert preds['keypoints2d'].shape == torch.Size([100, 10, 2])
assert preds['orientations'].shape == torch.Size([100, 16])
assert preds['direct_depth'].shape == torch.Size([
100,
])
assert preds['keypoints_depth'].shape == torch.Size([100, 3])
assert preds['combined_depth'].shape == torch.Size([
100,
])
assert preds['direct_depth_uncertainty'].shape == torch.Size([
100,
])
assert preds['keypoints_depth_uncertainty'].shape == torch.Size([100, 3])
offsets_2d = torch.randn([100, 2])
depths = torch.randn([
100,
])
locations = bbox_coder.decode_location(base_centers2d, offsets_2d, depths,
cam2imgs, downsample_ratio)
assert locations.shape == torch.Size([100, 3])
orientations = torch.randn([100, 16])
yaws, local_yaws = bbox_coder.decode_orientation(orientations, locations)
assert yaws.shape == torch.Size([
100,
])
assert local_yaws.shape == torch.Size([
100,
])
tests/test_utils/test_utils.py
View file @ 8538177b
......@@ -195,11 +195,15 @@ def test_points_img2cam():
def test_generate_edge_indices():
img_metas = [dict(img_shape=[300, 400]), dict(img_shape=[500, 450])]
edge_indices_list = get_edge_indices(img_metas)
input_metas = [
dict(img_shape=(110, 110), pad_shape=(128, 128)),
dict(img_shape=(98, 110), pad_shape=(128, 128))
]
downsample_ratio = 4
edge_indices_list = get_edge_indices(input_metas, downsample_ratio)
assert edge_indices_list[0].shape[0] == 1396
assert edge_indices_list[1].shape[0] == 1896
assert edge_indices_list[0].shape[0] == 108
assert edge_indices_list[1].shape[0] == 102
def test_truncation_hanlde():
......
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