huangfu/scenarionet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
147 Commits 1 Branch 0 Tags
32910a3a1b51ef9e8d4a79a0a27b8066bd1214c9
Commit Graph

9 Commits

Author SHA1 Message Date
Hidde Boekema
32910a3a1b Add View-of-Delft Prediction (VoD-P) dataset (#99)
Some checks failed
test / code_style (push) Has been cancelled
Details
test / test_functionality (push) Has been cancelled
Details
test / test_ipynb (push) Has been cancelled
Details 
* Create main branch

* Initial commit

* add setup.py

* move tools from md

* solve import conflict

* refactor

* get a unified func

* rename

* batch convert nuscenes

* change summary file to json

* remove set as well

* move writing summary to metadrive

* show import error

* nuplan ok

* clean example

* waymo

* all convert is ready now

* source file to data

* update get nuplan parameters

* get all scenarios

* format

* add pg converter

* fix nuplan bug

* suppres tf warning

* combine dataset function

* test script

* add test to github page

* add test script

* test script

* add step condition to verofy

* test scenarios

* remove logging information

* filter function

* test filter

* sdc filter test

* add filter test

* finish filter

* multiprocess verify

* multi_processing test

* small dataset test!

* multi-processing test

* format

* auto reduce worker num

* use is_scenario_file to determine

* build new dataset from error logs

* add new test

* add common utils

* move all test genrtaed file to tmp, add genertae error set test

* provide scripts

* add test

* reanme

* scale up test

* add script for parsing data

* disable info output

* multi processing get files

* multi-process writing

* test waymo converter

* add local test for generating local dataset

* set waymo origin path

* merge automatically

* batch generation

* add combine API

* fix combine bug

* test combine data

* add more test

* fix bug

* more test

* add num works to script arguments

* fix bug

* add dataset to gitignore

* test more scripts

* update error message

* .sh

* fix bug

* fix bug

* 16 workers

* remove annotation

* install md for github test

* fix bug

* fix CI

* fix test

* add filters to combine script

* fix test

* Fix bug for generating dataset (#2)

* update parameters for scripts

* update write function

* modify waymo script

* use exist ok instead of overwrite

* remove TODO

* rename to comvine_dataset

* use exist_ok and force_overwrite together

* format

* test

* creat env for each thread

* restore

* fix bug

* fix pg bug

* fix

* fix bug

* add assert

* don't return done info

* to dict

* add test

* only compare sdc

* no store mao

* release memory

* add start index to argumen

* test

* format some settings/flags

* add tmp path

* add tmp dir

* test all scripts

* suppress warning

* suppress warning

* format

* test memory leak

* fix memory leak

* remove useless functions

* imap

* thread-1 process for avoiding memory leak

* add list()

* rename

* verify existence

* verify completeness

* test

* add test

* add default value

* add limit

* use script

* add anotation

* test script

* fix bug

* fix bug

* add author4

* add overwrite

* fix bug

* fix

* combine overwrite

* fix bug

* gpu007

* add result save dir

* adjust sequence

* fix test bug

* disable bash scri[t

* add episode length limit

* move scripts to root dir

* format

* fix test

* Readme (#3)

* rename to merge dataset

* add -d for operation

* test move

* add move function

* test remove

* format

* dataset -> database

* add readme

* format.sh

* test assert

* rename to database in .sh

* Update README.md

* rename scripts and update readme

* remove repeat calculation

* update radius

* Add come updates for Neurips paper (#4)

* scenarionet training

* wandb

* train utils

* fix callback

* run PPO

* use pg test

* save path

* use torch

* add dependency

* update ignore

* update training

* large model

* use curriculum training

* add time to exp name

* storage_path

* restore

* update training

* use my key

* add log message

* check seed

* restore callback

* restore call bacl

* add log message

* add logging message

* restore ray1.4

* length 500

* ray 100

* wandb

* use tf

* more levels

* add callback

* 10 worker

* show level

* no env horizon

* callback result level

* more call back

* add diffuculty

* add mroen stat

* mroe stat

* show levels

* add callback

* new

* ep len 600

* fix setup

* fix stepup

* fix to 3.8

* update setup

* parallel worker!

* new exp

* add callback

* lateral dist

* pg dataset

* evaluate

* modify config

* align config

* train single RL

* update training script

* 100w eval

* less eval to reveal

* 2000 env eval

* new trianing

* eval 1000

* update eval

* more workers

* more worker

* 20 worker

* dataset to database

* split tool!

* split dataset

* try fix

* train 003

* fix mapping

* fix test

* add waymo tqdm

* utils

* fix bug

* fix bug

* waymo

* int type

* 8 worker read

* disable

* read file

* add log message

* check existence

* dist 0

* int

* check num

* suprass warning

* add filter API

* filter

* store map false

* new

* ablation

* filter

* fix

* update filyter

* reanme to from

* random select

* add overlapping checj

* fix

* new training sceheme

* new reward

* add waymo train script

* waymo different config

* copy raw data

* fix bug

* add tqdm

* update readme

* waymo

* pg

* max lateral dist 3

* pg

* crash_done instead of penalty

* no crash done

* gpu

* update eval script

* steering range penalty

* evaluate

* finish pg

* update setup

* fix bug

* test

* fix

* add on line

* train nuplan

* generate sensor

* udpate training

* static obj

* multi worker eval

* filx bug

* use ray for testing

* eval!

* filter senario

* id filter

* fox bug

* dist = 2

* filter

* eval

* eval ret

* ok

* update training pg

* test before use

* store data=False

* collect figures

* capture pic

---------

Co-authored-by: Quanyi Li <quanyi@bolei-gpu02.cs.ucla.edu>

* Make video (#5)

* generate accident scene

* construction PG

* no object

* accident prob

* capture script

* update nuscenes toolds

* make video

* format

* fix test

* update readme

* update readme

* format

* format

* Update video/webpage/code

* Update env (#7)

* add capture script

* gymnasium API

* training with gymnasium API

* update readme (#9)

* Rebuttal (#15)

* pg+nuplan train

* Need map

* use gym wrapper

* use createGymWrapper

* doc

* use all scenarios!

* update 80000 scenario

* train script

* config readthedocs

* format

* fix doc

* add requirement

* fix path

* readthedocs

* doc

* reactive traffic example

* Doc-example (#18)

* reactive traffic example

* structure

* structure

* waymo example

* rename and add doc

* finish example

* example

* start from 2

* fix build error

* Update doc (#20)

* Add list.py and desc

* add operations

* add structure

* update readme

* format

* update readme

* more doc

* toc tree

* waymo example

* add PG

* PG+waymo+nuscenes

* add nuPlan setup instruction

* fix command style by removing .py

* Colab exp (#22)

* add example

* add new workflow

* fix bug

* pull asset automatically

* add colab

* fix test

* add colab to readme

* Update README.md (#23)

* Update readme (#24)

* update figure

* add colab to doc

* More info (#28)

* boundary to exterior

* rename copy to cp, avoiding bugs

* add connectivity and sidewalk/cross for nuscenes

* update lane type

* add semantic renderer

* restore

* nuplan works

* format

* md versio>=0.4.1.2

* Loose numpy version (#30)

* disable using pip extra requirement installation

* loose numpy

* waymo

* waymo version

* add numpy hint

* restore

* Add to note

* add hint

* Update document, add a colab example for reading data, upgrade numpy dependency (#34)

* Minor update to docs

* WIP

* adjust numpy requirement

* prepare example for reading data from SN dataset

* prepare example for reading data from SN dataset

* clean

* Update Citation information (#37)

* Update Sensor API in scripts (#39)

* add semantic cam

* update API

* format

* Update the citation in README.md (#40)

* Optimize waymo converter (#44)

* use generator for waymo

* :wqadd preprocessor

* use generator

* Use Waymo Protos Directly (#38)

* use protos directly

* format protos

---------

Co-authored-by: Quanyi Li <quanyili0057@gmail.com>

* rename to unix style

* Update nuScenes & Waymo Optimization (#47)

* update can bus

* Create LICENSE

* update waymo doc

* protobuf requirement

* just warning

* Add warning for proto

* update PR template

* fix length bug

* try sharing nusc

* imu heading

* fix 161 168

* add badge

* fix doc

* update doc

* format

* update cp

* update nuscenes interface

* update doc

* prediction nuscenes

* use drivable aread for nuscenes

* allow converting prediction

* format

* fix bug

* optimize

* clean RAM

* delete more

* restore to

* add only lane

* use token

* add warning

* format

* fix bug

* add simulation section

* Add support to AV2 (#48)

* add support to av2
---------

Co-authored-by: Alan-LanFeng <fenglan18@outook.com>

* add nuscenes tracks and av2 bound (#49)

* add nuscenes tracks to predict
* ad av2 boundary type

* 1. add back map center to restore original coordinate in nuScnes (#51)

* 1. add back map center to restore the original coordinate in nuScenes

* Use the utils from MetaDrive to update object summaries; update ScenarioDescription doc (#52)

* Update

* update

* update

* update

* add trigger (#57)

* Add test for waymo example (#58)

* add test script

* test first 10 scenarios

* add dependency

* add dependency

* Update the script for generating multi-sensors images (#61)

* fix broken script

* format code

* introduce offscreen rendering

* try debug

* fix

* fix

* up

* up

* remove fix

* fix

* WIP

* fix a bug in nusc converter (#60)

* fix a typo (#62)

* Update waymo.rst (#59)

* Update waymo.rst

* Update waymo.rst

* Fix a bug in Waymo conversion: GPU should be disable (#64)

* Update waymo.rst

* Update waymo.rst

* allow generate all data

* update readme

* update

* better logging info

* more info

* up

* fix

* add note on GPU

* better log

* format

* Fix nuscenes (#67)

* fix bug

* fix a potential bug

* update av2 documentation (#75)

* fix av2 sdc_track_indx (#72) (#76)

* Add View-of-Delft Prediction (VoD-P) dataset

* Reformat VoD code

* Add documentation for VoD dataset

* Reformat convert_vod.py

---------

Co-authored-by: Quanyi Li <785878978@qq.com>
Co-authored-by: QuanyiLi <quanyili0057@gmail.com>
Co-authored-by: Quanyi Li <quanyi@bolei-gpu02.cs.ucla.edu>
Co-authored-by: PENG Zhenghao <pzh@cs.ucla.edu>
Co-authored-by: Govind Pimpale <gpimpale29@gmail.com>
Co-authored-by: Alan <36124025+Alan-LanFeng@users.noreply.github.com>
Co-authored-by: Alan-LanFeng <fenglan18@outook.com>
Co-authored-by: Yunsong Zhou <75066007+ZhouYunsong-SJTU@users.noreply.github.com>
 2025-05-01 12:51:49 +01:00
Alan
ed2a9d3388 update av2 documentation (#75) 2024-03-27 15:31:36 +01:00
PENG Zhenghao
af9fe0a2aa Update document, add a colab example for reading data, upgrade numpy dependency (#34) 
* Minor update to docs

* WIP

* adjust numpy requirement

* prepare example for reading data from SN dataset

* prepare example for reading data from SN dataset

* clean
 2023-10-18 14:32:01 -07:00
QuanyiLi
518b9317d6 waymo example 2023-08-27 15:00:51 +01:00
QuanyiLi
f7e41bbf19 toc tree 2023-08-27 11:41:50 +01:00
QuanyiLi
23bac46826 more doc 2023-08-27 11:20:51 +01:00
Quanyi Li
4affa68a06 Update doc (#20) 
* Add list.py and desc

* add operations

* add structure

* update readme

* format

* update readme
 2023-08-26 22:29:54 +01:00
Quanyi Li
e9d816ddd8 Doc-example (#18) 
* reactive traffic example

* structure

* structure

* waymo example

* rename and add doc

* finish example

* example

* start from 2
 2023-08-25 18:35:46 +01:00
QuanyiLi
ef5621b38a readthedocs 2023-08-08 18:16:31 +01:00