Comments (8)
Hi. It seems like you did not install nuScenes properly. Please see how to download the dataset and install it here. Let me know if you have any questions.
from nuscenes-devkit.
I followed the instructions but still can't get it to work. I am sharing step by step procedure I followed, could you go over it and let me know what mistake I am committing.
`Step-by-step method for setting up the virtual environment for running the nuscenes-devkit.
- Update and Upgrade the packages and install python3.7 (the notebook is tested on python 3.7 and it is recommended to install python 3.7 for seamless and error free execution of the tutorial jupyter notebook)
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt-get update
sudo apt-get install python3.7
sudo apt install python-pip
-
Install the virtual environment wrapper:
sudo apt-get install
pip install virtualenvwrapper -
Open .bashrc using nano:
nano ~/.bashrc
and add these two lines in the bottom:
export WORKON_HOME=$HOME/.virtualenvs
source ~/.local/bin/virtualenvwrapper.sh
press ctrl+x-----> press y -----> press
exit the terminal to make the changes effective
- Create the virtual environment:
sudo pip install -U virtualenv
mkvirtualenv <name_of_Virtual_environment> --system-site-packages -p python3.7
- Activate the virtual environment:
workon <name_of_Virtual_environment>
- Make the proper file structure:
a) Place the nuscenes-devkit in the home folder
b) The structure should be as follows:
home
|_nuscenes-devkit
|_instructions.md
|_license.txt
|_README.md
|_requirements.txt
|_schema.md
|_setup.py
|_python-sdk
|_tutorial.ipynb
|
|_nuscenes
| |_nuscenes.py
| |init.py
| |_evals
| | |_create_split_logs.py
| | |eval_utils.py
| | | init.py
| | |_nuscenes_eval.py
| | |_README.md
| | |_test_eval.py
| |_export
| | |_export_egoposes_on_map.py
| | |_export_pointclouds_as_obj.py
| | |export_scene_videos.py
| | | int.py
| |_pycache
| | |_init.cpython-35.pyc
| | |___init.cpython-37.pyc
| | |_nuscenes.cpython-37.pyc
| |_utils
| |_data_classes.py
| |_geometry_utils.py
| |_init.py
| |_map_mask.py
| |_pycache
| |_data_classes.cpython-37.pyc
| |_geometry_utils.cpython-37.pyc
| |___init.cpython-37.pyc
| |_map_mask.cpython-37.pyc
|
|_data
|_nuscenes
|_README.pdf
|_README2.txt
|_maps
|_samples
| |_CAM_BACK
| |_CAM_BACK_LEFT
| |_CAM_BACK_RIGHT
| |_CAM_FRONT
| |_CAM_FRONT_LEFT
| |_CAM_FRONT_RIGHT
|_sweeps
| |_CAM_BACK
| |_CAM_BACK_LEFT
| |_CAM_BACK_RIGHT
| |_CAM_FRONT
| |_CAM_FRONT_LEFT
| |_CAM_FRONT_RIGHT
|_v0.1
|_attribute.json
|_calibrated_sensor.json
|_category.json
|_ego_pose.json
|_instance.json
|_log.json
|_map.json
|_sample.json
|_sample_annotation.json
|_sample_data.json
|_scene.json
|_sensor.json
|_visibility.json
*NOTE: It is necessary that the file structure should match otherwise the tutorial.ipynb won't execute.
- In the home directory execute the following command:
cd && git clone https://github.com/nutonomy/nuscenes-devkit.git
- Installing the required packages:
a)navigate to home/nuscenes-devkit using cd nuscenes-devkit (from the home directory)
b) Install the requirements by executing the following command:
pip install -r requirements.txt
- Add the python-sdk directory to PYTHONPATH environment varible by adding the following line to the bottom of BOTH ~/.virtualenvs/nuscenes/bin/postactivate (virtual environment) or ~/.bashrc (global):
a) type nano ~/.bashrc
add [export PYTHONPATH="${PYTHONPATH}:$HOME/nuscenes-devkit/python-sdk"] (excluding the []) to the bottom-most line press ctrl+x-->press y-->press
b) type nano ~/.virtualenvs/nuscenes/bin/postactivate (virtual environment)
add [export PYTHONPATH="${PYTHONPATH}:$HOME/nuscenes-devkit/python-sdk"] (excluding the []) to the bottom-most line press ctrl+x-->press y-->press
-
Deactivate the virtual environment and exit the terminal to make the changes effective.
-
Enter the virtual environment using the follow command:
workon <name_of_Virtual_environment>`
from nuscenes-devkit.
When unpacking the nuScenes data it seems that you flattened the folder structure:
|_data
|_nuscenes
|_maps
|_samples
These folders should not be on the same level. It should be /data/nuscenes/maps
, /data/nuscenes/samples
, etc.
from nuscenes-devkit.
The nuscenes-devkit is present in the home folder, inside the nuscenes-devkit, there are python-sdk, setup.py, requirements.txt, instructions.md, license.txt, README.md, scehma.md.
Inside python-sdk there is tutorial.ipynb, nuscenes(folder) and data(folder)
inside the data(folder) there is a nuscenes(folder). I am attaching a series of pictures of my file structure, let me know if there is an error in the structure.
from nuscenes-devkit.
The devkit should reside in ~/nuscenes-devkit
(which is correct).
The data should reside in /data/nuscenes
(which it doesn't for you).
from nuscenes-devkit.
could you please define the exact location from the home directory where should I place it?
Would really appreciate it.
from nuscenes-devkit.
Could you please tell me is this okay now?
from nuscenes-devkit.
The devkit should reside in
~/nuscenes-devkit
(which is correct).
The data should reside in/data/nuscenes
(which it doesn't for you).
The suggested location of the data is not in the home directory. It's at /data/nuscenes
.
But if you need to put it in the home folder, you can create the NuScenes object as:
nusc = NuScenes(dataroot='/home/username/nuscenes-devkit/data/nuscenes')
from nuscenes-devkit.
Related Issues (20)
- Memory Requirement - Reg HOT 3
- Coordinate system of radar point cloud and velocity information? HOT 1
- About coordinate and box_velocity HOT 4
- About sample['anns'] HOT 3
- about render_egoposes_on_map HOT 4
- translation matrix for camera sensors is with respect to the center of the rear axle? HOT 2
- How the point cloud semantically segmented file is encoded? HOT 1
- Problem with NuScenes format to KITTI format HOT 1
- Conert radar to lidar problems HOT 3
- Is 1000hz imu data available? HOT 1
- How to create and split NuScenes subsets into trainval and test like v1.0 HOT 4
- The number of points is inconsistent with the number of labels HOT 4
- Is there C++ version to read the data HOT 1
- Rotation problem of point cloud object detection HOT 2
- Alignment of multi-frame radar dynamic object data HOT 4
- When v1.1.13 will be released in PyPI ? HOT 2
- pip install failed HOT 5
- nuScenes-lidar Annotation file HOT 1
- Navigation. How can I get waypoints from (x1,y1) to (x2 y2) in nuscenes map HOT 5
- Cannot download anything HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nuscenes-devkit.