Repo:
https://github.com/sisl/AutonomousRiskFramework.jl
Environment:
Windows 11, VS Code, Miniconda, Jalia 1.11.5, CARLA 0.9.13, scenario_runner 0.9.13
- Set up
juliacommand in the PowerShell temporarily or persistently.
Set-Alias julia "D:\software\julia-1.11.5-win64\julia-1.11.5\bin\julia.exe" Or run notepad $PROFILE, add the following lines.
Set-Alias julia "D:\software\julia-1.11.5-win64\julia-1.11.5\bin\julia.exe"
Write-Host "Custom profile loaded."
- On GitHub, fork the
POMDPStressTesting.jlrepo to
https://github.com/nov05/Stanford-POMDPStressTesting.jl
Then modify theProject.tomlfile, relax the version requirements forCUDAandFlux.
[compat]
# CUDA = "3"
CUDA = "3, 4, 5" ## Nov05
# Flux = "0.10, 0.11, 0.12, 0.13"
Flux = "0.10, 0.11, 0.12, 0.13, 0.14" ## Nov05
- On GitHub, fork the
AutonomousRiskFramework.jlrepo.
In Windows PowerShell,git clonethe repo to the local machine.
cd D:\\github
git clone https://github.com/nov05/Stanford-AutonomousRiskFramework.jl.git
cd Stanford-AutonomousRiskFramework.jl - Add the following lines in the
/Stanford-AutonomousRiskFramework.jl/install.jlfile.
packages = [
## Nov05 2025-05-31
PackageSpec(url="https://github.com/nov05/Stanford-POMDPStressTesting.jl")
]
...
Pkg.add("cuDNN")
-
Install CARLA
DownloadCARLA_0.9.13.zipfor Windows 11 from https://github.com/carla-simulator/carla/releases/tag/0.9.13
Exact toD:\softwareand add system variableUE4_ROOT=D:\software\CARLA_0.9.13
InstallDirectX 9.29.1974.1✅
Verify the installation by run"D:\software\CARLA_0.9.13\WindowsNoEditor\CarlaUE4.exe".
You are supposed to see the following window.
Installscenario_runner 0.9.13cd D:\software\CARLA_0.9.13\WindowsNoEditor\PythonAPI git clone --branch v0.9.13 --depth 1 https://github.com/carla-simulator/scenario_runner.git conda create -n arf_py375 python=3.7.5 conda activate arf_py375 cd scenario_runner pip install -r requirements.txt ✅ cd D:\github\Stanford-AutonomousRiskFramework.jl\CARLAIntegration\adversarial_carla_env pip install -r requirements.txt ✅
Modify the
setup.pyas the code below.from setuptools import setup, find_packages setup(name='adv_carla', version='0.0.1', packages=find_packages(include=['adv_carla', 'adv_carla.*']), ## added by nov05 install_requires=['gym']) # TODO: other reqs.
pip install -e . ✅ Install adv-carla-v0 gym environment pip install wandbAdd system variables in Windows.
CARLA_ROOT = D:\software\CARLA_0.9.13 SCENARIO_RUNNER_ROOT = %CARLA_ROOT%\PythonAPI\scenario_runner PYTHONPATH (append) := ;%CARLA_ROOT%\PythonAPI\carla\agents;%CARLA_ROOT%\PythonAPI\carla;%CARLA_ROOT%\PythonAPIAdd the following line to
D:\software\julia-1.11.5-win64\julia-1.11.5\etc\julia\startup.jl# This file should contain site-specific commands to be executed on Julia startup; # Users may store their own personal commands in `~/.julia/config/startup.jl`. ENV["PYTHON"] = "D:/Users/guido/miniconda3/envs/arf_py375/python.exe"
Restart PowerShell terminal
cd D:\github\Stanford-AA228VProjects\project_final conda activate arf_py375 julia julia> import Pkg; Pkg.activate(@__DIR__) julia> Pkg.build("PyCall") ✅ julia> using PyCall; PyCall.python "D:/Users/guido/miniconda3/envs/arf_py375/python.exe" julia> pyimport("adv_carla") PyObject <module 'adv_carla' from 'd:\\github\\stanford-autonomousriskframework.jl\\carlaintegration\\adversarial_carla_env\\adv_carla\\__init__.py'> julia> pyimport("wandb") PyObject <module 'wandb' from 'D:\\Users\\guido\\miniconda3\\envs\\arf_py375\\lib\\site-packages\\wandb\\__init__.py'> -
Install the
Autonomous Risk Frameworkpackage. Check the result.
cd D:\github\Stanford-AutonomousRiskFramework.jl ❌
julia install.jl ❌ This would install all the pacakges in the Julia v1.11 environment.
cd D:\github\Stanford-AA228VProjects\project_final
julia
julia> Pkg.activate("D:\\github\\Stanford-AutonomousRiskFramework.jl") ❌
julia> cd("D:/github/Stanford-AA228VProjects/project_final")
julia> import Pkg; Pkg.activate(@__DIR__) ✅ This would create Project.toml and Manifest.toml in this dir.
julia> import Pkg; Pkg.upgrade_manifest()
Updated Format of manifest file at `D:\github\Stanford-AA228VProjects\project_final\Manifest.toml` updated from v1.0 to v2.0
julia> include("D:/github/Stanford-AutonomousRiskFramework.jl/install.jl")
- Rebuild
import Pkg
Pkg.instantiate()
Pkg.precompile()
Pkg.status()
D:\Users\guido\.julia\packages\WeightsAndBiasLogger\fr2H9\deps\and the filejulia configure_pycall.jlis not missing.D:\Users\guido\.julia\packages\WeightsAndBiasLogger\fr2H9\deps\build.jlfile.ChatGPT
You're seeing this error because the build script for
WeightsAndBiasLoggeris trying to run a Julia file namedconfigure_pycall.jl, but it cannot find it:🔍 Cause
The build script
build.jlinWeightsAndBiasLoggerruns:But the file
configure_pycall.jldoes not exist in the expected location (deps/, usually). This results in a fatal error when trying toPkg.develop.✅ Solution
Option 1: Fix the package itself
Check this folder:
If
configure_pycall.jlis missing:Check if the file is in the original Git repository (e.g., on GitHub).
If yes, the repo might have been incorrectly cloned or corrupted. Try:
Or delete manually:
and re-develop the package.
Option 2: Fix the build script to use full path
If the file
configure_pycall.jlexists but isn't in the current working directory during build, the script must use the correct path.Open:
Change line 1 from:
To:
This ensures it looks for the file relative to the build script, not the current shell directory.
Option 3: Suppress build
If
WeightsAndBiasLoggeris non-essential and you just want to skip the build, you can manually disable it:Or edit
build.jlto an empty file temporarily.🛠 You may also want to check:
configure_pycall.jlshould have been generated by another script or downloaded.wandborPyCallare already set up.Would you like me to help you write a corrected
build.jlfile or locate a proper upstream version ofWeightsAndBiasLogger?