Comments (9)
Please provide the information of your environment such as the version of paddle and parl.
from parl.
cuda 10.0, paddlepaddle-gpu=1.5.2.post107, parl=1.1.3
from parl.
Thanks. We have not tested the compatibility of this folder in Paddle1.5.2.
To run the code, I suggest you try again after installing Paddle 1.5.1.
We would not like to update the code to make it compatible with the newest Paddle, as it's hard the to guarantee its reproducity, especially for a sophisticated RL task like this challenge.
from parl.
Thanks. I tried 1.5.1.post107 and it works!
from parl.
Sorry for not giving any hints on the version here. We will be updating the readme in that folder.
Again, thanks for raising the issue.
from parl.
In my another environment I got this error. Do you know about this?
I1011 02:40:49.894224 5714 parallel_executor.cc:329] The number of CUDAPlace, which is used in ParallelExecutor, is 2. And the Program will be copied 2 copies
Traceback (most recent call last):
File "simulator_server.py", line 327, in <module>
simulator_server = SimulatorServer()
File "simulator_server.py", line 84, in __init__
self.agent = OpenSimAgent(alg, OBS_DIM, ACT_DIM, args.ensemble_num)
File "/Data/jianian/latest/PARL/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/opensim_agent.py", line 63, in __init__
share_vars_parallel_executor=self.learn_pe[i])
File "/Data/jianian/latest/PARL/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/multi_head_ddpg.py", line 121, in sync_target
share_vars_parallel_executor=share_vars_parallel_executor)
File "/usr/local/lib/python3.5/dist-packages/parl/core/fluid/model.py", line 177, in sync_weights_to
build_strategy=build_strategy,
File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/parallel_executor.py", line 175, in __init__
self._compiled_program._compile(place=self._place, scope=self._scope)
File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/compiler.py", line 368, in _compile
scope=self._scope)
File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/compiler.py", line 339, in _compile_data_parallel
self._exec_strategy, self._build_strategy, self._graph)
paddle.fluid.core_avx.EnforceNotMet: Enforce failed. Expected member_->places_.size() == local_scopes.size(), but received member_->places_.size():2 != local_scopes.size():1.
at [/paddle/paddle/fluid/framework/parallel_executor.cc:344]
PaddlePaddle Call Stacks:
0 0x7f71826f6d98p void paddle::platform::EnforceNotMet::Init<std::string>(std::string, char const*, int) + 360
1 0x7f71826f70e7p paddle::platform::EnforceNotMet::EnforceNotMet(std::string const&, char const*, int) + 87
2 0x7f71828d17d4p paddle::framework::ParallelExecutor::ParallelExecutor(std::vector<boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_>, std::allocator<boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> > > const&, std::vector<std::string, std::allocator<std::string> > const&, std::string const&, paddle::framework::Scope*, std::vector<paddle::framework::Scope*, std::allocator<paddle::framework::Scope*> > const&, paddle::framework::details::ExecutionStrategy const&, paddle::framework::details::BuildStrategy const&, paddle::framework::ir::Graph*) + 8852
3 0x7f7182789e78p
4 0x7f7182729186p
5 0x4ea117p PyCFunction_Call + 119
6 0x5bc037p PyObject_Call + 71
7 0x4f489ep
8 0x5bc037p PyObject_Call + 71
9 0x54e9b9p
10 0x55851cp
11 0x5bc037p PyObject_Call + 71
12 0x528cefp PyEval_EvalFrameEx + 20239
13 0x52d2b9p
14 0x528ee2p PyEval_EvalFrameEx + 20738
15 0x52d2b9p
16 0x529333p PyEval_EvalFrameEx + 21843
17 0x52e10bp PyEval_EvalCodeEx + 315
18 0x4ec487p
19 0x5bc037p PyObject_Call + 71
20 0x4f489ep
21 0x5bc037p PyObject_Call + 71
22 0x54e9b9p
23 0x55851cp
24 0x5bc037p PyObject_Call + 71
25 0x528cefp PyEval_EvalFrameEx + 20239
26 0x52d2b9p
27 0x528ee2p PyEval_EvalFrameEx + 20738
28 0x52d2b9p
29 0x528ee2p PyEval_EvalFrameEx + 20738
30 0x52e84ap PyEval_EvalCodeEx + 2170
31 0x4ec373p
32 0x5bc037p PyObject_Call + 71
33 0x4f489ep
34 0x5bc037p PyObject_Call + 71
35 0x54e9b9p
36 0x55851cp
37 0x5bc037p PyObject_Call + 71
38 0x528cefp PyEval_EvalFrameEx + 20239
39 0x52e10bp PyEval_EvalCodeEx + 315
40 0x4ec373p
41 0x5bc037p PyObject_Call + 71
42 0x4f489ep
43 0x5bc037p PyObject_Call + 71
44 0x54e9b9p
45 0x55851cp
46 0x5bc037p PyObject_Call + 71
47 0x528cefp PyEval_EvalFrameEx + 20239
48 0x52d2b9p
49 0x52dfbfp PyEval_EvalCode + 31
50 0x5fc652p
51 0x5feafap PyRun_FileExFlags + 154
52 0x5fececp PyRun_SimpleFileExFlags + 444
53 0x63ec96p Py_Main + 1110
54 0x4d02e1p main + 225
55 0x7f71fb4ba830p __libc_start_main + 240
56 0x5d4b99p _start + 41
from parl.
Could you try using only a GPU by running the following command:
export CUDA_VISIBLE_DEVICES="0"
from parl.
Sweet! This also works. Thanks a lot.
from parl.
Great!
Paddle tries to use multiple GPU at the same time, but in fact, we only need a GPU for this task.
from parl.
Related Issues (20)
- 运行lesson3的课件代码,无法显示平衡杆的图像效果 HOT 4
- PARL在MacOS系统上用pip安装的时候报错 HOT 2
- LESSON5中的DDPG,将PyCharm中提示未实现抽象函数的类都实现后,reward一直处于10左右
- 救命,安装需要的环境包的时候没有一个包安得上,换了ali的源也一样,ubuntu18.04
- pip安装parl时报错
- 电气研究生跨考控制之我真是小白!!! HOT 1
- import parl时RuntimeError HOT 2
- 询问gym库中OBS对象属性的问题
- 使用python train.py运行tutorials中的代码没有反应
- 渲染图像render=True时,代码报错,图像框一下子闪退 Windows10 HOT 1
- torch的选择问题? HOT 2
- DDPG mujoco error
- It seems `fluid` is absent from paddlepaddle after 2.5, causing issue with backend detection on Windows HOT 1
- Attributerror HOT 6
- pip安装问题 HOT 4
- 分发本地文件如何同步更新呢 HOT 1
- Remaining issues of CI HOT 1
- pettingzoo.utils.deprecated_module.DeprecatedEnv: simple_speaker_listener_v3 is now deprecated, use simple_speaker_listener_v4 instead
- WRN No deep learning framework was found, but it's ok for parallel computation. HOT 1
- ValueError: optimizer got an empty parameter list HOT 1
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 parl.