Skip to content

GitLab

Unverified Commit ac289b35 authored by Tai-Wang's avatar Tai-Wang Committed by GitHub
Browse files

Bump version to v1.3.0 

Bump version to v1.3.0
parents b0e8ece9 12b595ca
Hide whitespace changes
Inline Side-by-side
Showing with 644 additions and 206 deletions
docs/zh_cn/notes/faq.md
View file @ ac289b35
......@@ -10,12 +10,11 @@
| MMDetection3D 版本 | MMEngine 版本 | MMCV 版本 | MMDetection 版本 |
| ------------------ | :----------------------: | :---------------------: | :----------------------: |
| dev-1.x | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
| main | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
| v1.1.0rc3 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
| v1.1.0rc2 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
| v1.1.0rc1 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
| v1.1.0rc0 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
| dev-1.x | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.2.0 | mmdet>=3.0.0rc5, \<3.3.0 |
| main | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.2.0 | mmdet>=3.0.0rc5, \<3.3.0 |
| v1.3.0 | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.2.0 | mmdet>=3.0.0rc5, \<3.3.0 |
| v1.2.0 | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.2.0 |
| v1.1.1 | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
**注意**：如果你想安装 mmdet3d-v1.0.0rcx，可以在[此处](https://mmdetection3d.readthedocs.io/en/latest/faq.html#mmcv-mmdet-mmdet3d-installation)找到 MMDetection，MMSegmentation 和 MMCV 的兼容版本。请选择正确版本的 MMCV、MMDetection 和 MMSegmentation 以避免安装问题。
......
mmdet3d/__init__.py
View file @ ac289b35
......@@ -7,15 +7,15 @@ from mmengine.utils import digit_version
from .version import __version__, version_info
mmcv_minimum_version = '2.0.0rc4'
mmcv_maximum_version = '2.1.0'
mmcv_maximum_version = '2.2.0'
mmcv_version = digit_version(mmcv.__version__)
mmengine_minimum_version = '0.8.0'
mmengine_maximum_version = '1.0.0'
mmengine_version = digit_version(mmengine.__version__)
mmdet_minimum_version = '3.0.0'
mmdet_maximum_version = '3.2.0'
mmdet_minimum_version = '3.0.0rc5'
mmdet_maximum_version = '3.3.0'
mmdet_version = digit_version(mmdet.__version__)
assert (mmcv_version >= digit_version(mmcv_minimum_version)
......
mmdet3d/apis/inference.py
View file @ ac289b35
......@@ -392,7 +392,8 @@ def inference_segmentor(model: nn.Module, pcds: PointsType):
new_test_pipeline = []
for pipeline in test_pipeline:
if pipeline['type'] != 'LoadAnnotations3D':
if pipeline['type'] != 'LoadAnnotations3D' and pipeline[
'type'] != 'PointSegClassMapping':
new_test_pipeline.append(pipeline)
test_pipeline = Compose(new_test_pipeline)
......
mmdet3d/apis/inferencers/base_3d_inferencer.py
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
import logging
import os.path as osp
from copy import deepcopy
from typing import Dict, List, Optional, Sequence, Tuple, Union
import mmengine
import numpy as np
import torch.nn as nn
from mmengine.fileio import (get_file_backend, isdir, join_path,
list_dir_or_file)
from mmengine import dump, print_log
from mmengine.infer.infer import BaseInferencer, ModelType
from mmengine.model.utils import revert_sync_batchnorm
from mmengine.registry import init_default_scope
from mmengine.runner import load_checkpoint
from mmengine.structures import InstanceData
from mmengine.visualization import Visualizer
from rich.progress import track
from mmdet3d.registry import MODELS
from mmdet3d.registry import DATASETS, MODELS
from mmdet3d.structures import Box3DMode, Det3DDataSample
from mmdet3d.utils import ConfigType
InstanceList = List[InstanceData]
......@@ -44,14 +48,14 @@ class Base3DInferencer(BaseInferencer):
priority is palette -> config -> checkpoint. Defaults to 'none'.
"""
preprocess_kwargs: set = set()
preprocess_kwargs: set = {'cam_type'}
forward_kwargs: set = set()
visualize_kwargs: set = {
'return_vis', 'show', 'wait_time', 'draw_pred', 'pred_score_thr',
'img_out_dir'
'img_out_dir', 'no_save_vis', 'cam_type_dir'
}
postprocess_kwargs: set = {
'print_result', 'pred_out_file', 'return_datasample'
'print_result', 'pred_out_dir', 'return_datasample', 'no_save_pred'
}
def __init__(self,
......@@ -60,10 +64,14 @@ class Base3DInferencer(BaseInferencer):
device: Optional[str] = None,
scope: str = 'mmdet3d',
palette: str = 'none') -> None:
# A global counter tracking the number of frames processed, for
# naming of the output results
self.num_predicted_frames = 0
self.palette = palette
init_default_scope(scope)
super().__init__(
model=model, weights=weights, device=device, scope=scope)
self.model = revert_sync_batchnorm(self.model)
def _convert_syncbn(self, cfg: ConfigType):
"""Convert config's naiveSyncBN to BN.
......@@ -108,56 +116,19 @@ class Base3DInferencer(BaseInferencer):
if 'PALETTE' in checkpoint.get('meta', {}): # 3D Segmentor
model.dataset_meta['palette'] = checkpoint['meta']['PALETTE']
test_dataset_cfg = deepcopy(cfg.test_dataloader.dataset)
# lazy init. We only need the metainfo.
test_dataset_cfg['lazy_init'] = True
metainfo = DATASETS.build(test_dataset_cfg).metainfo
cfg_palette = metainfo.get('palette', None)
if cfg_palette is not None:
model.dataset_meta['palette'] = cfg_palette
model.cfg = cfg # save the config in the model for convenience
model.to(device)
model.eval()
return model
def _inputs_to_list(
self,
inputs: Union[dict, list],
modality_key: Union[str, List[str]] = 'points') -> list:
"""Preprocess the inputs to a list.
Preprocess inputs to a list according to its type:
- list or tuple: return inputs
- dict: the value of key 'points'/`img` is
- Directory path: return all files in the directory
- other cases: return a list containing the string. The string
could be a path to file, a url or other types of string according
to the task.
Args:
inputs (Union[dict, list]): Inputs for the inferencer.
modality_key (Union[str, List[str]]): The key of the modality.
Defaults to 'points'.
Returns:
list: List of input for the :meth:`preprocess`.
"""
if isinstance(modality_key, str):
modality_key = [modality_key]
assert set(modality_key).issubset({'points', 'img'})
for key in modality_key:
if isinstance(inputs, dict) and isinstance(inputs[key], str):
img = inputs[key]
backend = get_file_backend(img)
if hasattr(backend, 'isdir') and isdir(img):
# Backends like HttpsBackend do not implement `isdir`, so
# only those backends that implement `isdir` could accept
# the inputs as a directory
filename_list = list_dir_or_file(img, list_dir=False)
inputs = [{
f'{key}': join_path(img, filename)
} for filename in filename_list]
if not isinstance(inputs, (list, tuple)):
inputs = [inputs]
return list(inputs)
def _get_transform_idx(self, pipeline_cfg: ConfigType, name: str) -> int:
"""Returns the index of the transform in a pipeline.
......@@ -173,64 +144,81 @@ class Base3DInferencer(BaseInferencer):
visualizer.dataset_meta = self.model.dataset_meta
return visualizer
def _dispatch_kwargs(self,
out_dir: str = '',
cam_type: str = '',
**kwargs) -> Tuple[Dict, Dict, Dict, Dict]:
"""Dispatch kwargs to preprocess(), forward(), visualize() and
postprocess() according to the actual demands.
Args:
out_dir (str): Dir to save the inference results.
cam_type (str): Camera type. Defaults to ''.
**kwargs (dict): Key words arguments passed to :meth:`preprocess`,
:meth:`forward`, :meth:`visualize` and :meth:`postprocess`.
Each key in kwargs should be in the corresponding set of
``preprocess_kwargs``, ``forward_kwargs``, ``visualize_kwargs``
and ``postprocess_kwargs``.
Returns:
Tuple[Dict, Dict, Dict, Dict]: kwargs passed to preprocess,
forward, visualize and postprocess respectively.
"""
kwargs['img_out_dir'] = out_dir
kwargs['pred_out_dir'] = out_dir
if cam_type != '':
kwargs['cam_type_dir'] = cam_type
return super()._dispatch_kwargs(**kwargs)
def __call__(self,
inputs: InputsType,
return_datasamples: bool = False,
batch_size: int = 1,
return_vis: bool = False,
show: bool = False,
wait_time: int = 0,
draw_pred: bool = True,
pred_score_thr: float = 0.3,
img_out_dir: str = '',
print_result: bool = False,
pred_out_file: str = '',
**kwargs) -> dict:
return_datasamples: bool = False,
**kwargs) -> Optional[dict]:
"""Call the inferencer.
Args:
inputs (InputsType): Inputs for the inferencer.
batch_size (int): Batch size. Defaults to 1.
return_datasamples (bool): Whether to return results as
:obj:`BaseDataElement`. Defaults to False.
batch_size (int): Inference batch size. Defaults to 1.
return_vis (bool): Whether to return the visualization result.
Defaults to False.
show (bool): Whether to display the visualization results in a
popup window. Defaults to False.
wait_time (float): The interval of show (s). Defaults to 0.
draw_pred (bool): Whether to draw predicted bounding boxes.
Defaults to True.
pred_score_thr (float): Minimum score of bboxes to draw.
Defaults to 0.3.
img_out_dir (str): Output directory of visualization results.
If left as empty, no file will be saved. Defaults to ''.
print_result (bool): Whether to print the inference result w/o
visualization to the console. Defaults to False.
pred_out_file (str): File to save the inference results w/o
visualization. If left as empty, no file will be saved.
Defaults to ''.
**kwargs: Other keyword arguments passed to :meth:`preprocess`,
**kwargs: Key words arguments passed to :meth:`preprocess`,
:meth:`forward`, :meth:`visualize` and :meth:`postprocess`.
Each key in kwargs should be in the corresponding set of
``preprocess_kwargs``, ``forward_kwargs``, ``visualize_kwargs``
and ``postprocess_kwargs``.
Returns:
dict: Inference and visualization results.
"""
return super().__call__(
inputs,
return_datasamples,
batch_size,
return_vis=return_vis,
show=show,
wait_time=wait_time,
draw_pred=draw_pred,
pred_score_thr=pred_score_thr,
img_out_dir=img_out_dir,
print_result=print_result,
pred_out_file=pred_out_file,
**kwargs)
(
preprocess_kwargs,
forward_kwargs,
visualize_kwargs,
postprocess_kwargs,
) = self._dispatch_kwargs(**kwargs)
cam_type = preprocess_kwargs.pop('cam_type', 'CAM2')
ori_inputs = self._inputs_to_list(inputs, cam_type=cam_type)
inputs = self.preprocess(
ori_inputs, batch_size=batch_size, **preprocess_kwargs)
preds = []
results_dict = {'predictions': [], 'visualization': []}
for data in (track(inputs, description='Inference')
if self.show_progress else inputs):
preds.extend(self.forward(data, **forward_kwargs))
visualization = self.visualize(ori_inputs, preds,
**visualize_kwargs)
results = self.postprocess(preds, visualization,
return_datasamples,
**postprocess_kwargs)
results_dict['predictions'].extend(results['predictions'])
if results['visualization'] is not None:
results_dict['visualization'].extend(results['visualization'])
return results_dict
def postprocess(
self,
......@@ -238,7 +226,8 @@ class Base3DInferencer(BaseInferencer):
visualization: Optional[List[np.ndarray]] = None,
return_datasample: bool = False,
print_result: bool = False,
pred_out_file: str = '',
no_save_pred: bool = False,
pred_out_dir: str = '',
) -> Union[ResType, Tuple[ResType, np.ndarray]]:
"""Process the predictions and visualization results from ``forward``
and ``visualize``.
......@@ -258,7 +247,7 @@ class Base3DInferencer(BaseInferencer):
Defaults to False.
print_result (bool): Whether to print the inference result w/o
visualization to the console. Defaults to False.
pred_out_file (str): File to save the inference results w/o
pred_out_dir (str): Directory to save the inference results w/o
visualization. If left as empty, no file will be saved.
Defaults to ''.
......@@ -273,35 +262,56 @@ class Base3DInferencer(BaseInferencer):
json-serializable dict containing only basic data elements such
as strings and numbers.
"""
if no_save_pred is True:
pred_out_dir = ''
result_dict = {}
results = preds
if not return_datasample:
results = []
for pred in preds:
result = self.pred2dict(pred)
result = self.pred2dict(pred, pred_out_dir)
results.append(result)
elif pred_out_dir != '':
print_log(
'Currently does not support saving datasample '
'when return_datasample is set to True. '
'Prediction results are not saved!',
level=logging.WARNING)
# Add img to the results after printing and dumping
result_dict['predictions'] = results
if print_result:
print(result_dict)
if pred_out_file != '':
mmengine.dump(result_dict, pred_out_file)
result_dict['visualization'] = visualization
return result_dict
def pred2dict(self, data_sample: InstanceData) -> Dict:
# TODO: The data format and fields saved in json need further discussion.
# Maybe should include model name, timestamp, filename, image info etc.
def pred2dict(self,
data_sample: Det3DDataSample,
pred_out_dir: str = '') -> Dict:
"""Extract elements necessary to represent a prediction into a
dictionary.
It's better to contain only basic data elements such as strings and
numbers in order to guarantee it's json-serializable.
Args:
data_sample (:obj:`DetDataSample`): Predictions of the model.
pred_out_dir: Dir to save the inference results w/o
visualization. If left as empty, no file will be saved.
Defaults to ''.
Returns:
dict: Prediction results.
"""
result = {}
if 'pred_instances_3d' in data_sample:
pred_instances_3d = data_sample.pred_instances_3d.numpy()
result = {
'bboxes_3d': pred_instances_3d.bboxes_3d.tensor.cpu().tolist(),
'labels_3d': pred_instances_3d.labels_3d.tolist(),
'scores_3d': pred_instances_3d.scores_3d.tolist()
'scores_3d': pred_instances_3d.scores_3d.tolist(),
'bboxes_3d': pred_instances_3d.bboxes_3d.tensor.cpu().tolist()
}
if 'pred_pts_seg' in data_sample:
......@@ -309,4 +319,28 @@ class Base3DInferencer(BaseInferencer):
result['pts_semantic_mask'] = \
pred_pts_seg.pts_semantic_mask.tolist()
if data_sample.box_mode_3d == Box3DMode.LIDAR:
result['box_type_3d'] = 'LiDAR'
elif data_sample.box_mode_3d == Box3DMode.CAM:
result['box_type_3d'] = 'Camera'
elif data_sample.box_mode_3d == Box3DMode.DEPTH:
result['box_type_3d'] = 'Depth'
if pred_out_dir != '':
if 'lidar_path' in data_sample:
lidar_path = osp.basename(data_sample.lidar_path)
lidar_path = osp.splitext(lidar_path)[0]
out_json_path = osp.join(pred_out_dir, 'preds',
lidar_path + '.json')
elif 'img_path' in data_sample:
img_path = osp.basename(data_sample.img_path)
img_path = osp.splitext(img_path)[0]
out_json_path = osp.join(pred_out_dir, 'preds',
img_path + '.json')
else:
out_json_path = osp.join(
pred_out_dir, 'preds',
f'{str(self.num_visualized_imgs).zfill(8)}.json')
dump(result, out_json_path)
return result
mmdet3d/apis/inferencers/lidar_det3d_inferencer.py
View file @ ac289b35
......@@ -4,11 +4,16 @@ from typing import Dict, List, Optional, Sequence, Union
import mmengine
import numpy as np
import torch
from mmengine.dataset import Compose
from mmengine.fileio import (get_file_backend, isdir, join_path,
list_dir_or_file)
from mmengine.infer.infer import ModelType
from mmengine.structures import InstanceData
from mmdet3d.registry import INFERENCERS
from mmdet3d.structures import (CameraInstance3DBoxes, DepthInstance3DBoxes,
Det3DDataSample, LiDARInstance3DBoxes)
from mmdet3d.utils import ConfigType
from .base_3d_inferencer import Base3DInferencer
......@@ -43,16 +48,6 @@ class LidarDet3DInferencer(Base3DInferencer):
priority is palette -> config -> checkpoint. Defaults to 'none'.
"""
preprocess_kwargs: set = set()
forward_kwargs: set = set()
visualize_kwargs: set = {
'return_vis', 'show', 'wait_time', 'draw_pred', 'pred_score_thr',
'img_out_dir'
}
postprocess_kwargs: set = {
'print_result', 'pred_out_file', 'return_datasample'
}
def __init__(self,
model: Union[ModelType, str, None] = None,
weights: Optional[str] = None,
......@@ -69,7 +64,7 @@ class LidarDet3DInferencer(Base3DInferencer):
scope=scope,
palette=palette)
def _inputs_to_list(self, inputs: Union[dict, list]) -> list:
def _inputs_to_list(self, inputs: Union[dict, list], **kwargs) -> list:
"""Preprocess the inputs to a list.
Preprocess inputs to a list according to its type:
......@@ -87,7 +82,22 @@ class LidarDet3DInferencer(Base3DInferencer):
Returns:
list: List of input for the :meth:`preprocess`.
"""
return super()._inputs_to_list(inputs, modality_key='points')
if isinstance(inputs, dict) and isinstance(inputs['points'], str):
pcd = inputs['points']
backend = get_file_backend(pcd)
if hasattr(backend, 'isdir') and isdir(pcd):
# Backends like HttpsBackend do not implement `isdir`, so
# only those backends that implement `isdir` could accept
# the inputs as a directory
filename_list = list_dir_or_file(pcd, list_dir=False)
inputs = [{
'points': join_path(pcd, filename)
} for filename in filename_list]
if not isinstance(inputs, (list, tuple)):
inputs = [inputs]
return list(inputs)
def _init_pipeline(self, cfg: ConfigType) -> Compose:
"""Initialize the test pipeline."""
......@@ -113,9 +123,10 @@ class LidarDet3DInferencer(Base3DInferencer):
preds: PredType,
return_vis: bool = False,
show: bool = False,
wait_time: int = 0,
wait_time: int = -1,
draw_pred: bool = True,
pred_score_thr: float = 0.3,
no_save_vis: bool = False,
img_out_dir: str = '') -> Union[List[np.ndarray], None]:
"""Visualize predictions.
......@@ -126,11 +137,13 @@ class LidarDet3DInferencer(Base3DInferencer):
Defaults to False.
show (bool): Whether to display the image in a popup window.
Defaults to False.
wait_time (float): The interval of show (s). Defaults to 0.
wait_time (float): The interval of show (s). Defaults to -1.
draw_pred (bool): Whether to draw predicted bounding boxes.
Defaults to True.
pred_score_thr (float): Minimum score of bboxes to draw.
Defaults to 0.3.
no_save_vis (bool): Whether to force not to save prediction
vis results. Defaults to False.
img_out_dir (str): Output directory of visualization results.
If left as empty, no file will be saved. Defaults to ''.
......@@ -138,8 +151,10 @@ class LidarDet3DInferencer(Base3DInferencer):
List[np.ndarray] or None: Returns visualization results only if
applicable.
"""
if self.visualizer is None or (not show and img_out_dir == ''
and not return_vis):
if no_save_vis is True:
img_out_dir = ''
if not show and img_out_dir == '' and not return_vis:
return None
if getattr(self, 'visualizer') is None:
......@@ -160,13 +175,16 @@ class LidarDet3DInferencer(Base3DInferencer):
elif isinstance(single_input, np.ndarray):
points = single_input.copy()
pc_num = str(self.num_visualized_frames).zfill(8)
pc_name = f'pc_{pc_num}.png'
pc_name = f'{pc_num}.png'
else:
raise ValueError('Unsupported input type: '
f'{type(single_input)}')
o3d_save_path = osp.join(img_out_dir, pc_name) \
if img_out_dir != '' else None
if img_out_dir != '' and show:
o3d_save_path = osp.join(img_out_dir, 'vis_lidar', pc_name)
mmengine.mkdir_or_exist(osp.dirname(o3d_save_path))
else:
o3d_save_path = None
data_input = dict(points=points)
self.visualizer.add_datasample(
......@@ -185,3 +203,40 @@ class LidarDet3DInferencer(Base3DInferencer):
self.num_visualized_frames += 1
return results
def visualize_preds_fromfile(self, inputs: InputsType, preds: PredType,
**kwargs) -> Union[List[np.ndarray], None]:
"""Visualize predictions from `*.json` files.
Args:
inputs (InputsType): Inputs for the inferencer.
preds (PredType): Predictions of the model.
Returns:
List[np.ndarray] or None: Returns visualization results only if
applicable.
"""
data_samples = []
for pred in preds:
pred = mmengine.load(pred)
data_sample = Det3DDataSample()
data_sample.pred_instances_3d = InstanceData()
data_sample.pred_instances_3d.labels_3d = torch.tensor(
pred['labels_3d'])
data_sample.pred_instances_3d.scores_3d = torch.tensor(
pred['scores_3d'])
if pred['box_type_3d'] == 'LiDAR':
data_sample.pred_instances_3d.bboxes_3d = \
LiDARInstance3DBoxes(pred['bboxes_3d'])
elif pred['box_type_3d'] == 'Camera':
data_sample.pred_instances_3d.bboxes_3d = \
CameraInstance3DBoxes(pred['bboxes_3d'])
elif pred['box_type_3d'] == 'Depth':
data_sample.pred_instances_3d.bboxes_3d = \
DepthInstance3DBoxes(pred['bboxes_3d'])
else:
raise ValueError('Unsupported box type: '
f'{pred["box_type_3d"]}')
data_samples.append(data_sample)
return self.visualize(inputs=inputs, preds=data_samples, **kwargs)
mmdet3d/apis/inferencers/lidar_seg3d_inferencer.py
View file @ ac289b35
......@@ -5,6 +5,8 @@ from typing import Dict, List, Optional, Sequence, Union
import mmengine
import numpy as np
from mmengine.dataset import Compose
from mmengine.fileio import (get_file_backend, isdir, join_path,
list_dir_or_file)
from mmengine.infer.infer import ModelType
from mmengine.structures import InstanceData
......@@ -43,16 +45,6 @@ class LidarSeg3DInferencer(Base3DInferencer):
priority is palette -> config -> checkpoint. Defaults to 'none'.
"""
preprocess_kwargs: set = set()
forward_kwargs: set = set()
visualize_kwargs: set = {
'return_vis', 'show', 'wait_time', 'draw_pred', 'pred_score_thr',
'img_out_dir'
}
postprocess_kwargs: set = {
'print_result', 'pred_out_file', 'return_datasample'
}
def __init__(self,
model: Union[ModelType, str, None] = None,
weights: Optional[str] = None,
......@@ -69,7 +61,7 @@ class LidarSeg3DInferencer(Base3DInferencer):
scope=scope,
palette=palette)
def _inputs_to_list(self, inputs: Union[dict, list]) -> list:
def _inputs_to_list(self, inputs: Union[dict, list], **kwargs) -> list:
"""Preprocess the inputs to a list.
Preprocess inputs to a list according to its type:
......@@ -87,7 +79,22 @@ class LidarSeg3DInferencer(Base3DInferencer):
Returns:
list: List of input for the :meth:`preprocess`.
"""
return super()._inputs_to_list(inputs, modality_key='points')
if isinstance(inputs, dict) and isinstance(inputs['points'], str):
pcd = inputs['points']
backend = get_file_backend(pcd)
if hasattr(backend, 'isdir') and isdir(pcd):
# Backends like HttpsBackend do not implement `isdir`, so
# only those backends that implement `isdir` could accept
# the inputs as a directory
filename_list = list_dir_or_file(pcd, list_dir=False)
inputs = [{
'points': join_path(pcd, filename)
} for filename in filename_list]
if not isinstance(inputs, (list, tuple)):
inputs = [inputs]
return list(inputs)
def _init_pipeline(self, cfg: ConfigType) -> Compose:
"""Initialize the test pipeline."""
......@@ -124,6 +131,7 @@ class LidarSeg3DInferencer(Base3DInferencer):
wait_time: int = 0,
draw_pred: bool = True,
pred_score_thr: float = 0.3,
no_save_vis: bool = False,
img_out_dir: str = '') -> Union[List[np.ndarray], None]:
"""Visualize predictions.
......@@ -139,6 +147,7 @@ class LidarSeg3DInferencer(Base3DInferencer):
Defaults to True.
pred_score_thr (float): Minimum score of bboxes to draw.
Defaults to 0.3.
no_save_vis (bool): Whether to save visualization results.
img_out_dir (str): Output directory of visualization results.
If left as empty, no file will be saved. Defaults to ''.
......@@ -146,8 +155,10 @@ class LidarSeg3DInferencer(Base3DInferencer):
List[np.ndarray] or None: Returns visualization results only if
applicable.
"""
if self.visualizer is None or (not show and img_out_dir == ''
and not return_vis):
if no_save_vis is True:
img_out_dir = ''
if not show and img_out_dir == '' and not return_vis:
return None
if getattr(self, 'visualizer') is None:
......@@ -168,13 +179,16 @@ class LidarSeg3DInferencer(Base3DInferencer):
elif isinstance(single_input, np.ndarray):
points = single_input.copy()
pc_num = str(self.num_visualized_frames).zfill(8)
pc_name = f'pc_{pc_num}.png'
pc_name = f'{pc_num}.png'
else:
raise ValueError('Unsupported input type: '
f'{type(single_input)}')
o3d_save_path = osp.join(img_out_dir, pc_name) \
if img_out_dir != '' else None
if img_out_dir != '' and show:
o3d_save_path = osp.join(img_out_dir, 'vis_lidar', pc_name)
mmengine.mkdir_or_exist(osp.dirname(o3d_save_path))
else:
o3d_save_path = None
data_input = dict(points=points)
self.visualizer.add_datasample(
......
mmdet3d/apis/inferencers/mono_det3d_inferencer.py
View file @ ac289b35
......@@ -6,6 +6,8 @@ import mmcv
import mmengine
import numpy as np
from mmengine.dataset import Compose
from mmengine.fileio import (get_file_backend, isdir, join_path,
list_dir_or_file)
from mmengine.infer.infer import ModelType
from mmengine.structures import InstanceData
......@@ -44,16 +46,6 @@ class MonoDet3DInferencer(Base3DInferencer):
priority is palette -> config -> checkpoint. Defaults to 'none'.
"""
preprocess_kwargs: set = set()
forward_kwargs: set = set()
visualize_kwargs: set = {
'return_vis', 'show', 'wait_time', 'draw_pred', 'pred_score_thr',
'img_out_dir'
}
postprocess_kwargs: set = {
'print_result', 'pred_out_file', 'return_datasample'
}
def __init__(self,
model: Union[ModelType, str, None] = None,
weights: Optional[str] = None,
......@@ -70,7 +62,10 @@ class MonoDet3DInferencer(Base3DInferencer):
scope=scope,
palette=palette)
def _inputs_to_list(self, inputs: Union[dict, list]) -> list:
def _inputs_to_list(self,
inputs: Union[dict, list],
cam_type='CAM2',
**kwargs) -> list:
"""Preprocess the inputs to a list.
Preprocess inputs to a list according to its type:
......@@ -88,7 +83,79 @@ class MonoDet3DInferencer(Base3DInferencer):
Returns:
list: List of input for the :meth:`preprocess`.
"""
return super()._inputs_to_list(inputs, modality_key='img')
if isinstance(inputs, dict):
assert 'infos' in inputs
infos = inputs.pop('infos')
if isinstance(inputs['img'], str):
img = inputs['img']
backend = get_file_backend(img)
if hasattr(backend, 'isdir') and isdir(img):
# Backends like HttpsBackend do not implement `isdir`, so
# only those backends that implement `isdir` could accept
# the inputs as a directory
filename_list = list_dir_or_file(img, list_dir=False)
inputs = [{
'img': join_path(img, filename)
} for filename in filename_list]
if not isinstance(inputs, (list, tuple)):
inputs = [inputs]
# get cam2img, lidar2cam and lidar2img from infos
info_list = mmengine.load(infos)['data_list']
assert len(info_list) == len(inputs)
for index, input in enumerate(inputs):
data_info = info_list[index]
img_path = data_info['images'][cam_type]['img_path']
if isinstance(input['img'], str) and \
osp.basename(img_path) != osp.basename(input['img']):
raise ValueError(
f'the info file of {img_path} is not provided.')
cam2img = np.asarray(
data_info['images'][cam_type]['cam2img'], dtype=np.float32)
lidar2cam = np.asarray(
data_info['images'][cam_type]['lidar2cam'],
dtype=np.float32)
if 'lidar2img' in data_info['images'][cam_type]:
lidar2img = np.asarray(
data_info['images'][cam_type]['lidar2img'],
dtype=np.float32)
else:
lidar2img = cam2img @ lidar2cam
input['cam2img'] = cam2img
input['lidar2cam'] = lidar2cam
input['lidar2img'] = lidar2img
elif isinstance(inputs, (list, tuple)):
# get cam2img, lidar2cam and lidar2img from infos
for input in inputs:
assert 'infos' in input
infos = input.pop('infos')
info_list = mmengine.load(infos)['data_list']
assert len(info_list) == 1, 'Only support single sample info' \
'in `.pkl`, when inputs is a list.'
data_info = info_list[0]
img_path = data_info['images'][cam_type]['img_path']
if isinstance(input['img'], str) and \
osp.basename(img_path) != osp.basename(input['img']):
raise ValueError(
f'the info file of {img_path} is not provided.')
cam2img = np.asarray(
data_info['images'][cam_type]['cam2img'], dtype=np.float32)
lidar2cam = np.asarray(
data_info['images'][cam_type]['lidar2cam'],
dtype=np.float32)
if 'lidar2img' in data_info['images'][cam_type]:
lidar2img = np.asarray(
data_info['images'][cam_type]['lidar2img'],
dtype=np.float32)
else:
lidar2img = cam2img @ lidar2cam
input['cam2img'] = cam2img
input['lidar2cam'] = lidar2cam
input['lidar2img'] = lidar2img
return list(inputs)
def _init_pipeline(self, cfg: ConfigType) -> Compose:
"""Initialize the test pipeline."""
......@@ -110,7 +177,9 @@ class MonoDet3DInferencer(Base3DInferencer):
wait_time: int = 0,
draw_pred: bool = True,
pred_score_thr: float = 0.3,
img_out_dir: str = '') -> Union[List[np.ndarray], None]:
no_save_vis: bool = False,
img_out_dir: str = '',
cam_type_dir: str = 'CAM2') -> Union[List[np.ndarray], None]:
"""Visualize predictions.
Args:
......@@ -125,15 +194,19 @@ class MonoDet3DInferencer(Base3DInferencer):
Defaults to True.
pred_score_thr (float): Minimum score of bboxes to draw.
Defaults to 0.3.
no_save_vis (bool): Whether to save visualization results.
img_out_dir (str): Output directory of visualization results.
If left as empty, no file will be saved. Defaults to ''.
cam_type_dir (str): Camera type directory. Defaults to 'CAM2'.
Returns:
List[np.ndarray] or None: Returns visualization results only if
applicable.
"""
if self.visualizer is None or (not show and img_out_dir == ''
and not return_vis):
if no_save_vis is True:
img_out_dir = ''
if not show and img_out_dir == '' and not return_vis:
return None
if getattr(self, 'visualizer') is None:
......@@ -156,8 +229,8 @@ class MonoDet3DInferencer(Base3DInferencer):
raise ValueError('Unsupported input type: '
f"{type(single_input['img'])}")
out_file = osp.join(img_out_dir, img_name) if img_out_dir != '' \
else None
out_file = osp.join(img_out_dir, 'vis_camera', cam_type_dir,
img_name) if img_out_dir != '' else None
data_input = dict(img=img)
self.visualizer.add_datasample(
......
mmdet3d/apis/inferencers/multi_modality_det3d_inferencer.py
View file @ ac289b35
......@@ -7,6 +7,8 @@ import mmcv
import mmengine
import numpy as np
from mmengine.dataset import Compose
from mmengine.fileio import (get_file_backend, isdir, join_path,
list_dir_or_file)
from mmengine.infer.infer import ModelType
from mmengine.structures import InstanceData
......@@ -44,16 +46,6 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
palette (str): The palette of visualization. Defaults to 'none'.
"""
preprocess_kwargs: set = set()
forward_kwargs: set = set()
visualize_kwargs: set = {
'return_vis', 'show', 'wait_time', 'draw_pred', 'pred_score_thr',
'img_out_dir'
}
postprocess_kwargs: set = {
'print_result', 'pred_out_file', 'return_datasample'
}
def __init__(self,
model: Union[ModelType, str, None] = None,
weights: Optional[str] = None,
......@@ -70,7 +62,10 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
scope=scope,
palette=palette)
def _inputs_to_list(self, inputs: Union[dict, list]) -> list:
def _inputs_to_list(self,
inputs: Union[dict, list],
cam_type: str = 'CAM2',
**kwargs) -> list:
"""Preprocess the inputs to a list.
Preprocess inputs to a list according to its type:
......@@ -88,7 +83,86 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
Returns:
list: List of input for the :meth:`preprocess`.
"""
return super()._inputs_to_list(inputs, modality_key=['points', 'img'])
if isinstance(inputs, dict):
assert 'infos' in inputs
infos = inputs.pop('infos')
if isinstance(inputs['img'], str):
img, pcd = inputs['img'], inputs['points']
backend = get_file_backend(img)
if hasattr(backend, 'isdir') and isdir(img) and isdir(pcd):
# Backends like HttpsBackend do not implement `isdir`, so
# only those backends that implement `isdir` could accept
# the inputs as a directory
img_filename_list = list_dir_or_file(
img, list_dir=False, suffix=['.png', '.jpg'])
pcd_filename_list = list_dir_or_file(
pcd, list_dir=False, suffix='.bin')
assert len(img_filename_list) == len(pcd_filename_list)
inputs = [{
'img': join_path(img, img_filename),
'points': join_path(pcd, pcd_filename)
} for pcd_filename, img_filename in zip(
pcd_filename_list, img_filename_list)]
if not isinstance(inputs, (list, tuple)):
inputs = [inputs]
# get cam2img, lidar2cam and lidar2img from infos
info_list = mmengine.load(infos)['data_list']
assert len(info_list) == len(inputs)
for index, input in enumerate(inputs):
data_info = info_list[index]
img_path = data_info['images'][cam_type]['img_path']
if isinstance(input['img'], str) and \
osp.basename(img_path) != osp.basename(input['img']):
raise ValueError(
f'the info file of {img_path} is not provided.')
cam2img = np.asarray(
data_info['images'][cam_type]['cam2img'], dtype=np.float32)
lidar2cam = np.asarray(
data_info['images'][cam_type]['lidar2cam'],
dtype=np.float32)
if 'lidar2img' in data_info['images'][cam_type]:
lidar2img = np.asarray(
data_info['images'][cam_type]['lidar2img'],
dtype=np.float32)
else:
lidar2img = cam2img @ lidar2cam
input['cam2img'] = cam2img
input['lidar2cam'] = lidar2cam
input['lidar2img'] = lidar2img
elif isinstance(inputs, (list, tuple)):
# get cam2img, lidar2cam and lidar2img from infos
for input in inputs:
assert 'infos' in input
infos = input.pop('infos')
info_list = mmengine.load(infos)['data_list']
assert len(info_list) == 1, 'Only support single sample' \
'info in `.pkl`, when input is a list.'
data_info = info_list[0]
img_path = data_info['images'][cam_type]['img_path']
if isinstance(input['img'], str) and \
osp.basename(img_path) != osp.basename(input['img']):
raise ValueError(
f'the info file of {img_path} is not provided.')
cam2img = np.asarray(
data_info['images'][cam_type]['cam2img'], dtype=np.float32)
lidar2cam = np.asarray(
data_info['images'][cam_type]['lidar2cam'],
dtype=np.float32)
if 'lidar2img' in data_info['images'][cam_type]:
lidar2img = np.asarray(
data_info['images'][cam_type]['lidar2img'],
dtype=np.float32)
else:
lidar2img = cam2img @ lidar2cam
input['cam2img'] = cam2img
input['lidar2cam'] = lidar2cam
input['lidar2img'] = lidar2img
return list(inputs)
def _init_pipeline(self, cfg: ConfigType) -> Compose:
"""Initialize the test pipeline."""
......@@ -144,7 +218,9 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
wait_time: int = 0,
draw_pred: bool = True,
pred_score_thr: float = 0.3,
img_out_dir: str = '') -> Union[List[np.ndarray], None]:
no_save_vis: bool = False,
img_out_dir: str = '',
cam_type_dir: str = 'CAM2') -> Union[List[np.ndarray], None]:
"""Visualize predictions.
Args:
......@@ -157,6 +233,7 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
wait_time (float): The interval of show (s). Defaults to 0.
draw_pred (bool): Whether to draw predicted bounding boxes.
Defaults to True.
no_save_vis (bool): Whether to save visualization results.
pred_score_thr (float): Minimum score of bboxes to draw.
Defaults to 0.3.
img_out_dir (str): Output directory of visualization results.
......@@ -166,8 +243,10 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
List[np.ndarray] or None: Returns visualization results only if
applicable.
"""
if self.visualizer is None or (not show and img_out_dir == ''
and not return_vis):
if no_save_vis is True:
img_out_dir = ''
if not show and img_out_dir == '' and not return_vis:
return None
if getattr(self, 'visualizer') is None:
......@@ -188,13 +267,16 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
elif isinstance(points_input, np.ndarray):
points = points_input.copy()
pc_num = str(self.num_visualized_frames).zfill(8)
pc_name = f'pc_{pc_num}.png'
pc_name = f'{pc_num}.png'
else:
raise ValueError('Unsupported input type: '
f'{type(points_input)}')
o3d_save_path = osp.join(img_out_dir, pc_name) \
if img_out_dir != '' else None
if img_out_dir != '' and show:
o3d_save_path = osp.join(img_out_dir, 'vis_lidar', pc_name)
mmengine.mkdir_or_exist(osp.dirname(o3d_save_path))
else:
o3d_save_path = None
img_input = single_input['img']
if isinstance(single_input['img'], str):
......@@ -210,8 +292,8 @@ class MultiModalityDet3DInferencer(Base3DInferencer):
raise ValueError('Unsupported input type: '
f'{type(img_input)}')
out_file = osp.join(img_out_dir, img_name) if img_out_dir != '' \
else None
out_file = osp.join(img_out_dir, 'vis_camera', cam_type_dir,
img_name) if img_out_dir != '' else None
data_input = dict(points=points, img=img)
self.visualizer.add_datasample(
......
mmdet3d/configs/_base_/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/_base_/datasets/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/_base_/models/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/_base_/models/cylinder3d.py 0 → 100644
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
from mmdet3d.models import Cylinder3D
from mmdet3d.models.backbones import Asymm3DSpconv
from mmdet3d.models.data_preprocessors import Det3DDataPreprocessor
from mmdet3d.models.decode_heads.cylinder3d_head import Cylinder3DHead
from mmdet3d.models.losses import LovaszLoss
from mmdet3d.models.voxel_encoders import SegVFE
grid_shape = [480, 360, 32]
model = dict(
type=Cylinder3D,
data_preprocessor=dict(
type=Det3DDataPreprocessor,
voxel=True,
voxel_type='cylindrical',
voxel_layer=dict(
grid_shape=grid_shape,
point_cloud_range=[0, -3.14159265359, -4, 50, 3.14159265359, 2],
max_num_points=-1,
max_voxels=-1,
),
),
voxel_encoder=dict(
type=SegVFE,
feat_channels=[64, 128, 256, 256],
in_channels=6,
with_voxel_center=True,
feat_compression=16,
return_point_feats=False),
backbone=dict(
type=Asymm3DSpconv,
grid_size=grid_shape,
input_channels=16,
base_channels=32,
norm_cfg=dict(type='BN1d', eps=1e-5, momentum=0.1)),
decode_head=dict(
type=Cylinder3DHead,
channels=128,
num_classes=20,
loss_ce=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=False,
class_weight=None,
loss_weight=1.0),
loss_lovasz=dict(type=LovaszLoss, loss_weight=1.0, reduction='none'),
),
train_cfg=None,
test_cfg=dict(mode='whole'),
)
mmdet3d/configs/_base_/schedules/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/centerpoint/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/centerpoint/centerpoint_pillar02_second_secfpn_8xb4_cyclic_20e_nus_3d.py
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
if '_base_':
from mmengine.config import read_base
with read_base():
from .._base_.datasets.nus_3d import *
from .._base_.models.centerpoint_pillar02_second_secfpn_nus import *
from .._base_.schedules.cyclic_20e import *
......@@ -29,9 +31,9 @@ class_names = [
'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]
data_prefix.merge(
data_prefix.update(
dict(pts='samples/LIDAR_TOP', img='', sweeps='sweeps/LIDAR_TOP'))
model.merge(
model.update(
dict(
data_preprocessor=dict(
voxel_layer=dict(point_cloud_range=point_cloud_range)),
......@@ -167,13 +169,13 @@ train_dataloader.merge(
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR',
backend_args=backend_args))))
test_dataloader.merge(
test_dataloader.update(
dict(
dataset=dict(
pipeline=test_pipeline, metainfo=dict(classes=class_names))))
val_dataloader.merge(
val_dataloader.update(
dict(
dataset=dict(
pipeline=test_pipeline, metainfo=dict(classes=class_names))))
train_cfg.merge(dict(val_interval=20))
train_cfg.update(dict(val_interval=20))
mmdet3d/configs/centerpoint/centerpoint_voxel01_second_secfpn_8xb4_cyclic_20e_nus_3d.py
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
if '_base_':
from mmengine import read_base
with read_base():
from .._base_.datasets.nus_3d import *
from .._base_.models.centerpoint_voxel01_second_secfpn_nus import *
from .._base_.schedules.cyclic_20e import *
......@@ -29,9 +31,9 @@ class_names = [
'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]
data_prefix.merge(
data_prefix.update(
dict(pts='samples/LIDAR_TOP', img='', sweeps='sweeps/LIDAR_TOP'))
model.merge(
model.update(
dict(
data_preprocessor=dict(
voxel_layer=dict(point_cloud_range=point_cloud_range)),
......@@ -167,13 +169,13 @@ train_dataloader.merge(
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR',
backend_args=backend_args))))
test_dataloader.merge(
test_dataloader.update(
dict(
dataset=dict(
pipeline=test_pipeline, metainfo=dict(classes=class_names))))
val_dataloader.merge(
val_dataloader.update(
dict(
dataset=dict(
pipeline=test_pipeline, metainfo=dict(classes=class_names))))
train_cfg.merge(dict(val_interval=20))
train_cfg.update(dict(val_interval=20))
mmdet3d/configs/cylinder3d/cylinder3d_4xb4-3x_semantickitti.py 0 → 100644
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine import read_base
with read_base():
from .._base_.datasets.semantickitti import *
from .._base_.models.cylinder3d import *
from .._base_.default_runtime import *
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim import AdamW
# optimizer
lr = 0.001
optim_wrapper = dict(
type=OptimWrapper, optimizer=dict(type=AdamW, lr=lr, weight_decay=0.01))
train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=36, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=36,
by_epoch=True,
milestones=[30],
gamma=0.1)
]
train_dataloader.update(dict(batch_size=4, ))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (4 samples per GPU).
# auto_scale_lr = dict(enable=False, base_batch_size=32)
default_hooks.update(dict(checkpoint=dict(type=CheckpointHook, interval=5)))
mmdet3d/configs/cylinder3d/cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py 0 → 100644
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine import read_base
with read_base():
from .._base_.datasets.semantickitti import *
from .._base_.default_runtime import *
from .._base_.models.cylinder3d import *
from .._base_.schedules.schedule_3x import *
from mmcv.transforms.wrappers import RandomChoice
from mmdet3d.datasets.transforms.transforms_3d import LaserMix, PolarMix
train_pipeline = [
dict(type=LoadPointsFromFile, coord_type='LIDAR', load_dim=4, use_dim=4),
dict(
type=LoadAnnotations3D,
with_bbox_3d=False,
with_label_3d=False,
with_seg_3d=True,
seg_3d_dtype='np.int32',
seg_offset=2**16,
dataset_type='semantickitti'),
dict(type=PointSegClassMapping),
dict(
type=RandomChoice,
transforms=[
[
dict(
type=LaserMix,
num_areas=[3, 4, 5, 6],
pitch_angles=[-25, 3],
pre_transform=[
dict(
type=LoadPointsFromFile,
coord_type='LIDAR',
load_dim=4,
use_dim=4),
dict(
type=LoadAnnotations3D,
with_bbox_3d=False,
with_label_3d=False,
with_seg_3d=True,
seg_3d_dtype='np.int32',
seg_offset=2**16,
dataset_type='semantickitti'),
dict(type=PointSegClassMapping)
],
prob=1)
],
[
dict(
type=PolarMix,
instance_classes=[0, 1, 2, 3, 4, 5, 6, 7],
swap_ratio=0.5,
rotate_paste_ratio=1.0,
pre_transform=[
dict(
type=LoadPointsFromFile,
coord_type='LIDAR',
load_dim=4,
use_dim=4),
dict(
type=LoadAnnotations3D,
with_bbox_3d=False,
with_label_3d=False,
with_seg_3d=True,
seg_3d_dtype='np.int32',
seg_offset=2**16,
dataset_type='semantickitti'),
dict(type=PointSegClassMapping)
],
prob=1)
],
],
prob=[0.5, 0.5]),
dict(
type=GlobalRotScaleTrans,
rot_range=[0., 6.28318531],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0],
),
dict(type=Pack3DDetInputs, keys=['points', 'pts_semantic_mask'])
]
train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
default_hooks.update(dict(checkpoint=dict(type=CheckpointHook, interval=1)))
mmdet3d/configs/minkunet/__init__.py deleted 100644 → 0
View file @ b0e8ece9
# Copyright (c) OpenMMLab. All rights reserved.
mmdet3d/configs/minkunet/minkunet34_w32_torchsparse_8xb2_laser_polar_mix_3x_semantickitti.py
View file @ ac289b35
# Copyright (c) OpenMMLab. All rights reserved.
if '_base_':
from mmengine import read_base
with read_base():
from .._base_.datasets.semantickitti import *
from .._base_.models.minkunet import *
from .._base_.schedules.schedule_3x import *
......@@ -15,7 +17,7 @@ from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
from mmdet3d.datasets.transforms.transforms_3d import (GlobalRotScaleTrans,
LaserMix, PolarMix)
model.merge(
model.update(
dict(
data_preprocessor=dict(max_voxels=None),
backbone=dict(encoder_blocks=[2, 3, 4, 6])))
......@@ -92,6 +94,6 @@ train_pipeline = [
dict(type=Pack3DDetInputs, keys=['points', 'pts_semantic_mask'])
]
train_dataloader.merge(dict(dataset=dict(pipeline=train_pipeline)))
train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
default_hooks.merge(dict(checkpoint=dict(type=CheckpointHook, interval=1)))
default_hooks.update(dict(checkpoint=dict(type=CheckpointHook, interval=1)))
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