Comments (5)
Thank you I did setup gmsh incorrectly and after adding to the path variable correctly I now can run the provided training sessions.
The mistake I made was when I set my path variable it did not go from the root directory to the gmsh folder and instead went from the directory I started the singularity shell .
export PATH=$PATH:"path from root to gmsh bin folder"
from cylinder2dflowcontroldrl.
Have you run make_mesh.py first? See The Readme sections make a new mesh and to go further.
from cylinder2dflowcontroldrl.
So I tried running make_mesh.py and it outputs this error
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-1-c4ab53427a49> in <module>()
2
3 import env
----> 4 env.resume_env(plot=500, remesh=True)
/home/vagrant/vboxshare/Cylinder2DFlowControlDRL-master/Cylinder2DFlowControlWithRL/empty_simulation/env.pyc in resume_env(plot, step, dump, remesh, random_start, single_run)
179 reward_function=reward_function,
180 number_steps_execution=number_steps_execution,
--> 181 simu_name = simu_name)
182
183 return(env_2d_cylinder)
/home/vagrant/vboxshare/Cylinder2DFlowControlDRL-master/Cylinder2DFlowControlWithRL/empty_simulation/../Env2DCylinder.py in __init__(self, path_root, geometry_params, flow_params, solver_params, output_params, optimization_params, inspection_params, n_iter_make_ready, verbose, size_history, reward_function, size_time_state, number_steps_execution, simu_name)
130 self.initialized_visualization = False
131
--> 132 self.start_class(complete_reset=True)
133
134 printi("--- done init ---")
/home/vagrant/vboxshare/Cylinder2DFlowControlDRL-master/Cylinder2DFlowControlWithRL/empty_simulation/../Env2DCylinder.py in start_class(self, complete_reset)
181 printi("generate_mesh start...")
182
--> 183 generate_mesh(self.geometry_params, template=self.geometry_params['template'])
184
185 if self.verbose > 0:
/home/vagrant/vboxshare/Cylinder2DFlowControlDRL-master/Cylinder2DFlowControlWithRL/empty_simulation/../generate_msh.py in generate_mesh(args, template, dim)
48
49 unrolled = '_'.join([output, 'unrolled'])
---> 50 assert os.path.exists(unrolled)
51
52 return subprocess.call(['gmsh -%d -clscale %g %s' % (dim, scale, unrolled)], shell=True)
AssertionError:
I'm pretty sure that it means that the path at "unrolled" doesn't exist. but I can't tell where in the code that it is supposed to make a file at that path. I did some debugging to find what path unrolled pointing to
unrolled = 'mesh/turek_2d.geo_unrolled'
So the name for the path makes sense, however I don't know why there isn't a file there
from cylinder2dflowcontroldrl.
Ok. You do need to run this script (without error ^^ ) to generate the mesh and initial fields before you can train or anything else when you perform a new training 'on your own' with a specific configuration.
This error is because you do not use gmsh correctly / it is not set up correctly. See either the readme again, or this issue:
from cylinder2dflowcontroldrl.
from cylinder2dflowcontroldrl.
Related Issues (20)
- How to customize the .xdmf file for initial conditions? HOT 7
- How the reward function working HOT 3
- How to define Neumann boundary condition HOT 1
- symmetric case HOT 4
- Problem with creating a new mesh HOT 3
- about changing the geometry HOT 5
- could not connect to display ":0.0" HOT 9
- Can not get the "fenics-and-more.img" file HOT 5
- Could not open image; image format not recognized HOT 15
- Change the model and run singlerunner from Ann_ controlled_ flow_ Singlerun folder, did not get the same result HOT 3
- New airfoil model encountered mesh convertion probelm HOT 2
- About Q<0.06 HOT 1
- Lift fluctuations resulting from DRL training using the OpenFOAM platform HOT 2
- Negative drag values while training HOT 4
- issues about running single_runner.py HOT 10
- higher Reynolds problem HOT 1
- Download the Singularity container HOT 2
- problems about singularity container parts HOT 3
- Using Dolphin Expression HOT 2
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 cylinder2dflowcontroldrl.