Skip to content

GitLab

Commit 4cd43886 authored by lishj6's avatar lishj6 🏸
Browse files

init

parent a9a1fe81
Hide whitespace changes
Inline Side-by-side
Showing with 1870 additions and 0 deletions
.gitignore 0 → 100644
View file @ 4cd43886
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
ckpts/
data/
ckpts
data
test/
val/
work_dirs/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
.python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
100_epoch.py 0 → 100644
View file @ 4cd43886
import json
# 初始化变量
total_time = 0.0
total_data = 0
count = 0
# 读取文件并计算100-200次迭代的耗时
with open('/home/BEVFormer/work_dirs/bevformer_tiny/20250725_143253.log.json', 'r') as f: # 替换为你的文件名
for line in f:
# 解析 JSON 行
log_entry = json.loads(line.strip())
# 检查是否是训练模式且有有效的iter值
if log_entry.get('mode') == 'train' and 'iter' in log_entry:
iter_num = log_entry['iter']
# 只处理100到200次迭代（包含100和200）
if 101 <= iter_num <= 200:
total_time += log_entry['time']
total_data += log_entry['data_time']
count += 1
# 超过200次迭代后停止读取
if iter_num > 200:
break
# 输出结果
if count > 0:
print(f"第101到第200次迭代的耗时总和: {total_time:.4f} 秒")
print(f"第101到第200次迭代的处理数据耗时总和: {total_data:.4f} 秒")
print(f"涉及迭代次数: {count} 次")
print(f"平均每次迭代耗时: {total_time/count:.4f} 秒")
else:
print("未找到101-200次迭代的记录")
\ No newline at end of file
LICENSE 0 → 100644
View file @ 4cd43886
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
check_soruce.py 0 → 100644
View file @ 4cd43886
import subprocess
import json
import time
import sys
def run_hy_smi():
"""运行hy-smi命令并返回JSON格式的输出"""
try:
# 使用JSON格式获取数据，提高解析可靠性
result = subprocess.run(
['hy-smi', '--showtemp', '--showpower', '--showuse', '--showmemuse', '--json'],
capture_output=True,
text=True,
timeout=10
)
if result.returncode != 0:
print(f"命令执行错误: {result.stderr}")
return None
return json.loads(result.stdout)
except subprocess.TimeoutExpired:
print("命令执行超时")
return None
except json.JSONDecodeError as e:
print(f"JSON解析错误: {e}")
return None
except Exception as e:
print(f"意外错误: {e}")
return None
def parse_data(data):
"""解析hy-smi输出数据"""
metrics = []
# 根据实际JSON结构提取数据
for card_key, card_data in data.items():
try:
# 使用结温作为温度指标
temperature = float(card_data.get("Temperature (Sensor junction) (C)", 0))
# 提取功耗
power = float(card_data.get("Average Graphics Package Power (W)", 0))
# 提取利用率
utilization = float(card_data.get("HCU use (%)", 0))
# 提取内存使用百分比
mem_usage_percent = float(card_data.get("HCU memory use (%)", 0))
metric = {
'card': card_key,
'temperature': temperature,
'power': power,
'utilization': utilization,
'mem_usage_percent': mem_usage_percent
}
metrics.append(metric)
except (ValueError, TypeError) as e:
print(f"解析数据时出错: {e}")
continue
return metrics
def main():
"""主函数"""
print("开始收集DCU指标，按Ctrl+C停止...")
print("{:<10} {:<8} {:<10} {:<10} {:<15} {:<15}".format(
"时间", "卡号", "温度(℃)", "功耗(W)", "利用率(%)", "内存使用(%)"))
data_points = []
try:
while True:
raw_data = run_hy_smi()
if raw_data:
current_metrics = parse_data(raw_data)
if current_metrics:
for metric in current_metrics:
print("{:<10} {:<8} {:<10.1f} {:<10.1f} {:<15.1f} {:<15.0f}".format(
time.strftime("%H:%M:%S"),
metric['card'],
metric['temperature'],
metric['power'],
metric['utilization'],
metric['mem_usage_percent']
))
data_points.extend(current_metrics)
time.sleep(1)
except KeyboardInterrupt:
print("\n正在计算平均值...")
if data_points:
# 计算所有卡的平均值
avg_temp = sum(m['temperature'] for m in data_points) / len(data_points)
avg_power = sum(m['power'] for m in data_points) / len(data_points)
avg_util = sum(m['utilization'] for m in data_points) / len(data_points)
avg_mem_percent = sum(m['mem_usage_percent'] for m in data_points) / len(data_points)
print("\n所有卡的平均值统计:")
print("平均温度: {:.1f}℃".format(avg_temp))
print("平均功耗: {:.1f}W".format(avg_power))
print("平均利用率: {:.1f}%".format(avg_util))
print("平均内存使用: {:.1f}%".format(avg_mem_percent))
# 计算每张卡的平均值
card_stats = {}
for metric in data_points:
card = metric['card']
if card not in card_stats:
card_stats[card] = {'temp': [], 'power': [], 'util': [], 'mem': []}
card_stats[card]['temp'].append(metric['temperature'])
card_stats[card]['power'].append(metric['power'])
card_stats[card]['util'].append(metric['utilization'])
card_stats[card]['mem'].append(metric['mem_usage_percent'])
print("\n每张卡的平均值统计:")
print("平均温度: {:.1f}℃".format(avg_temp))
print("平均功耗: {:.1f}W".format(avg_power))
print("平均利用率: {:.1f}%".format(avg_util))
print("平均内存使用: {:.1f}%".format(avg_mem_percent))
for card, stats in card_stats.items():
avg_card_temp = sum(stats['temp']) / len(stats['temp'])
avg_card_power = sum(stats['power']) / len(stats['power'])
avg_card_util = sum(stats['util']) / len(stats['util'])
avg_card_mem = sum(stats['mem']) / len(stats['mem'])
print("{:<8} {:<10.1f} {:<10.1f} {:<15.1f} {:<15.1f}".format(
card, avg_card_temp, avg_card_power, avg_card_util, avg_card_mem))
else:
print("未收集到有效数据")
if __name__ == "__main__":
main()
\ No newline at end of file
docs/can_bus.ipynb 0 → 100644
View file @ 4cd43886
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from nuscenes.can_bus.can_bus_api import NuScenesCanBus\n",
"nusc_can = NuScenesCanBus(dataroot='can_bus')"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"The CAN bus is a vehicle bus over which information such as position, velocity, acceleration, steering, lights, battery and many more are submitted. We recommend you start by reading the [README](https://github.com/nutonomy/nuscenes-devkit/tree/master/python-sdk/nuscenes/can_bus/README.md)\n",
"In BEVFormer, we only use the `pose` fields."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"scene_name = 'scene-0001'\n",
"pose_list = nusc_can.get_messages(scene_name, 'pose')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Each value of `pose_list` contains: \n",
"- `orientation`: a Quaternion representation of orientation\n",
"- `pos`: a global postion of ego-car\n",
"- `vel`: the velocity of ego-car\n",
"- `rotation_rate`: rotation rate"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'accel': [0.05252802768009661, 0.9291747528573647, 9.513756543139106],\n",
" 'orientation': [0.7479305678167669, 0.0, 0.0, 0.6637769698666026],\n",
" 'pos': [1010.1436201720262, 610.8882352282457, 0.0],\n",
" 'rotation_rate': [0.040320225059986115,\n",
" -0.002563952235504985,\n",
" 0.28492140769958496],\n",
" 'utime': 1531883530467511,\n",
" 'vel': [4.1688763951334185, 0.0, 0.0]}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pose_list[0] # one example"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"dict_keys(['accel', 'orientation', 'pos', 'rotation_rate', 'utime', 'vel'])"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pose_list[0].keys()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In [data_converter](https://github.com/zhiqi-li/BEVFormer/blob/master/tools/data_converter/nuscenes_converter.py), we use the following function to obatain the can bus information for each sample."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def _get_can_bus_info(nusc, nusc_can_bus, sample):\n",
" scene_name = nusc.get('scene', sample['scene_token'])['name']\n",
" sample_timestamp = sample['timestamp']\n",
" try:\n",
" pose_list = nusc_can_bus.get_messages(scene_name, 'pose')\n",
" except:\n",
" return np.zeros(18) # serveral scenes do not have can bus information.\n",
" can_bus = []\n",
" # during each scene, the first timestamp of can_bus may be large than the first sample's timestamp\n",
" last_pose = pose_list[0]\n",
" for i, pose in enumerate(pose_list):\n",
" if pose['utime'] > sample_timestamp:\n",
" break\n",
" last_pose = pose # we obtain the can_bus information which is recorded before the sample recorded.\n",
" \n",
" _ = last_pose.pop('utime') # useless\n",
" pos = last_pose.pop('pos') \n",
" rotation = last_pose.pop('orientation')\n",
" \n",
" # one can_bus record contains 18 numbers\n",
" can_bus.extend(pos) # [0:3] is the position\n",
" can_bus.extend(rotation) # [3:7] is the orientation\n",
" \n",
" for key in last_pose.keys():\n",
" can_bus.extend(pose[key]) # accel: [7, 10], rotation_rate: [10: 13], velocity: [13: 16]\n",
" \n",
" # the last two numbers are reserved for later calculation of rotation angle.\n",
" can_bus.extend([0., 0.])\n",
" \n",
" \n",
" return np.array(can_bus)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In [dataset](https://github.com/zhiqi-li/BEVFormer/blob/master/projects/mmdet3d_plugin/datasets/nuscenes_dataset.py#L174), we reorganize the can_bus."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
" # actually, the nuScenes provides the rotation and translation of each sample, which is more accurate than we obtained from can bus. \n",
" rotation = Quaternion(input_dict['ego2global_rotation'])\n",
" translation = input_dict['ego2global_translation']\n",
" \n",
" can_bus = input_dict['can_bus']\n",
" can_bus[:3] = translation # We use the provided translation and rotation to repalce the original translation and rotation in can bus\n",
" can_bus[3:7] = rotation\n",
" \n",
" patch_angle = quaternion_yaw(rotation) / np.pi * 180 # we get the yaw angle of ego car\n",
" can_bus[-2] = patch_angle / 180 * np.pi # this angle is kept unchanged.\n",
" can_bus[-1] = patch_angle # this angle is used to compute the detal of adjacent timestamps."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In [dataset](https://github.com/zhiqi-li/BEVFormer/blob/master/projects/mmdet3d_plugin/datasets/nuscenes_dataset.py#L93), we compute the delta orientation and position of adjacent timestamps"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
" prev_pos = None\n",
" prev_angle = None\n",
" for i, each in enumerate(queue):\n",
" metas_map[i] = each['img_metas'].data\n",
" if i == 0:\n",
" metas_map[i]['prev_bev'] = False\n",
" prev_pos = copy.deepcopy(metas_map[i]['can_bus'][:3])\n",
" prev_angle = copy.deepcopy(metas_map[i]['can_bus'][-1])\n",
" metas_map[i]['can_bus'][:3] = 0\n",
" metas_map[i]['can_bus'][-1] = 0\n",
" else:\n",
" metas_map[i]['prev_bev'] = True\n",
" tmp_pos = copy.deepcopy(metas_map[i]['can_bus'][:3])\n",
" tmp_angle = copy.deepcopy(metas_map[i]['can_bus'][-1])\n",
" metas_map[i]['can_bus'][:3] -= prev_pos\n",
" metas_map[i]['can_bus'][-1] -= prev_angle\n",
" prev_pos = copy.deepcopy(tmp_pos)\n",
" prev_angle = copy.deepcopy(tmp_angle)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.13"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
docs/getting_started.md 0 → 100644
View file @ 4cd43886
# Prerequisites
**Please ensure you have prepared the environment and the nuScenes dataset.**
# Train and Test
Train BEVFormer with 8 GPUs
```
./tools/dist_train.sh ./projects/configs/bevformer/bevformer_base.py 8
```
Eval BEVFormer with 8 GPUs
```
./tools/dist_test.sh ./projects/configs/bevformer/bevformer_base.py ./path/to/ckpts.pth 8
```
Note: using 1 GPU to eval can obtain slightly higher performance because continuous video may be truncated with multiple GPUs. By default we report the score evaled with 8 GPUs.
# Using FP16 to train the model.
The above training script can not support FP16 training,
and we provide another script to train BEVFormer with FP16.
```
./tools/fp16/dist_train.sh ./projects/configs/bevformer_fp16/bevformer_tiny_fp16.py 8
```
# Visualization
see [visual.py](../tools/analysis_tools/visual.py)
\ No newline at end of file
docs/install.md 0 → 100644
View file @ 4cd43886
# Step-by-step installation instructions
Following https://mmdetection3d.readthedocs.io/en/latest/getting_started.html#installation
**a. Create a conda virtual environment and activate it.**
```shell
conda create -n open-mmlab python=3.8 -y
conda activate open-mmlab
```
**b. Install PyTorch and torchvision following the [official instructions](https://pytorch.org/).**
```shell
pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html
# Recommended torch>=1.9
```
**c. Install gcc>=5 in conda env (optional).**
```shell
conda install -c omgarcia gcc-6 # gcc-6.2
```
**c. Install mmcv-full.**
```shell
pip install mmcv-full==1.4.0
# pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html
```
**d. Install mmdet and mmseg.**
```shell
pip install mmdet==2.14.0
pip install mmsegmentation==0.14.1
```
**e. Install mmdet3d from source code.**
```shell
git clone https://github.com/open-mmlab/mmdetection3d.git
cd mmdetection3d
git checkout v0.17.1 # Other versions may not be compatible.
python setup.py install
```
**f. Install Detectron2 and Timm.**
```shell
pip install einops fvcore seaborn iopath==0.1.9 timm==0.6.13 typing-extensions==4.5.0 pylint ipython==8.12 numpy==1.19.5 matplotlib==3.5.2 numba==0.48.0 pandas==1.4.4 scikit-image==0.19.3 setuptools==59.5.0
python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
```
**g. Clone BEVFormer.**
```
git clone https://github.com/fundamentalvision/BEVFormer.git
```
**h. Prepare pretrained models.**
```shell
cd bevformer
mkdir ckpts
cd ckpts & wget https://github.com/zhiqi-li/storage/releases/download/v1.0/r101_dcn_fcos3d_pretrain.pth
```
note: this pretrained model is the same model used in [detr3d](https://github.com/WangYueFt/detr3d)
docs/prepare_dataset.md 0 → 100644
View file @ 4cd43886
## NuScenes
Download nuScenes V1.0 full dataset data and CAN bus expansion data [HERE](https://www.nuscenes.org/download). Prepare nuscenes data by running
**Download CAN bus expansion**
```
# download 'can_bus.zip'
unzip can_bus.zip
# move can_bus to data dir
```
**Prepare nuScenes data**
*We genetate custom annotation files which are different from mmdet3d's*
```
python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0 --canbus ./data
```
Using the above code will generate `nuscenes_infos_temporal_{train,val}.pkl`.
**Folder structure**
```
bevformer
├── projects/
├── tools/
├── configs/
├── ckpts/
│ ├── r101_dcn_fcos3d_pretrain.pth
├── data/
│ ├── can_bus/
│ ├── nuscenes/
│ │ ├── maps/
│ │ ├── samples/
│ │ ├── sweeps/
│ │ ├── v1.0-test/
| | ├── v1.0-trainval/
| | ├── nuscenes_infos_temporal_train.pkl
| | ├── nuscenes_infos_temporal_val.pkl
```
projects/configs/_base_/datasets/coco_instance.py 0 → 100644
View file @ 4cd43886
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
projects/configs/_base_/datasets/kitti-3d-3class.py 0 → 100644
View file @ 4cd43886
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
classes=class_names,
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6))
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR')),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'))
evaluation = dict(interval=1, pipeline=eval_pipeline)
projects/configs/_base_/datasets/kitti-3d-car.py 0 → 100644
View file @ 4cd43886
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
classes=class_names,
sample_groups=dict(Car=15))
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR')),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'))
evaluation = dict(interval=1, pipeline=eval_pipeline)
projects/configs/_base_/datasets/lyft-3d.py 0 → 100644
View file @ 4cd43886
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-80, -80, -5, 80, 80, 3]
# For Lyft we usually do 9-class detection
class_names = [
'car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle', 'motorcycle',
'bicycle', 'pedestrian', 'animal'
]
dataset_type = 'LyftDataset'
data_root = 'data/lyft/'
# Input modality for Lyft dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/lyft/': 's3://lyft/lyft/',
# 'data/lyft/': 's3://lyft/lyft/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_test.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True))
# For Lyft dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 24. Please change the interval accordingly if you do not
# use a default schedule.
evaluation = dict(interval=24, pipeline=eval_pipeline)
projects/configs/_base_/datasets/nuim_instance.py 0 → 100644
View file @ 4cd43886
dataset_type = 'CocoDataset'
data_root = 'data/nuimages/'
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='Resize',
img_scale=[(1280, 720), (1920, 1080)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1600, 900),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/nuimages_v1.0-train.json',
img_prefix=data_root,
classes=class_names,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/nuimages_v1.0-val.json',
img_prefix=data_root,
classes=class_names,
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/nuimages_v1.0-val.json',
img_prefix=data_root,
classes=class_names,
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
projects/configs/_base_/datasets/nus-3d.py 0 → 100644
View file @ 4cd43886
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-50, -50, -5, 50, 50, 3]
# For nuScenes we usually do 10-class detection
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
# Input modality for nuScenes dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectNameFilter', classes=class_names),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR'),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True,
box_type_3d='LiDAR'))
# For nuScenes dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 24. Please change the interval accordingly if you do not
# use a default schedule.
evaluation = dict(interval=24, pipeline=eval_pipeline)
projects/configs/_base_/datasets/nus-mono3d.py 0 → 100644
View file @ 4cd43886
dataset_type = 'CustomNuScenesMonoDataset'
data_root = 'data/nuscenes/'
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
# Input modality for nuScenes dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=False,
use_camera=True,
use_radar=False,
use_map=False,
use_external=False)
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=True,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1600, 900), keep_ratio=True),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'attr_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
test_pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='MultiScaleFlipAug',
scale_factor=1.0,
flip=False,
transforms=[
dict(type='RandomFlip3D'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['img']),
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['img'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train_mono3d.coco.json',
img_prefix=data_root,
classes=class_names,
pipeline=train_pipeline,
modality=input_modality,
test_mode=False,
box_type_3d='Camera'),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val_mono3d.coco.json',
img_prefix=data_root,
classes=class_names,
pipeline=test_pipeline,
modality=input_modality,
test_mode=True,
box_type_3d='Camera'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val_mono3d.coco.json',
img_prefix=data_root,
classes=class_names,
pipeline=test_pipeline,
modality=input_modality,
test_mode=True,
box_type_3d='Camera'))
evaluation = dict(interval=2)
projects/configs/_base_/datasets/range100_lyft-3d.py 0 → 100644
View file @ 4cd43886
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-100, -100, -5, 100, 100, 3]
# For Lyft we usually do 9-class detection
class_names = [
'car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle', 'motorcycle',
'bicycle', 'pedestrian', 'animal'
]
dataset_type = 'LyftDataset'
data_root = 'data/lyft/'
# Input modality for Lyft dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/lyft/': 's3://lyft/lyft/',
# 'data/lyft/': 's3://lyft/lyft/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_test.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True))
# For Lyft dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 24. Please change the interval accordingly if you do not
# use a default schedule.
evaluation = dict(interval=24, pipeline=eval_pipeline)
projects/configs/_base_/datasets/s3dis-3d-5class.py 0 → 100644
View file @ 4cd43886
# dataset settings
dataset_type = 'S3DISDataset'
data_root = './data/s3dis/'
class_names = ('table', 'chair', 'sofa', 'bookcase', 'board')
train_area = [1, 2, 3, 4, 6]
test_area = 5
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='PointSample', num_points=40000),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(
type='GlobalRotScaleTrans',
# following ScanNet dataset the rotation range is 5 degrees
rot_range=[-0.087266, 0.087266],
scale_ratio_range=[1.0, 1.0],
shift_height=True),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(type='PointSample', num_points=40000),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=8,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type='ConcatDataset',
datasets=[
dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + f's3dis_infos_Area_{i}.pkl',
pipeline=train_pipeline,
filter_empty_gt=False,
classes=class_names,
box_type_3d='Depth') for i in train_area
],
separate_eval=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + f's3dis_infos_Area_{test_area}.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True,
box_type_3d='Depth'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + f's3dis_infos_Area_{test_area}.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True,
box_type_3d='Depth'))
evaluation = dict(pipeline=eval_pipeline)
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