Comments (6)
It seems that the env-id
you used is not correct. Please refer to this page for the correct env-id
.
Specifically, the end-id
of the training environment is UnrealTrack-City1StefaniPath1-DiscreteColor-v1
in the ICML 2018, and the random room is UnrealTrack-RandoomRoom-DiscreteColor-v4
.
from gym-unrealcv.
It seems that the
env-id
you used is not correct. Please refer to this page for the correctenv-id
. Specifically, theend-id
of the training environment isUnrealTrack-City1StefaniPath1-DiscreteColor-v1
in the ICML 2018, and the random room isUnrealTrack-RandoomRoom-DiscreteColor-v4
.
Thank you for your reply! I make steps as you said, python train.py --num-workers=1 --env-id=UnrealTrack-City1StefaniPath1-DiscreteColor-v1 --env-val-id=UnrealTrack-City1StefaniPath1-DiscreteColor-v1 --model-id=convx2lstm --lr=0.00005 --log-dir=save/tmp --max-global-steps=250000000 --val-model-secs=-1 --max-val-episodes=40
. But new questions occured in tmux 1:w-0:
ERROR:init:205:Can not connect to ('127.0.0.1', 9000)
ERROR:init:206:Error [Errno 111] Connection refused
UnrealCV server is not running. Please try again
Can you give me some advice about it?
from gym-unrealcv.
It shows that the unrealcv client in python fails to connect to the unrealcv server in UE4 environment. Do you see any new windows appearing on your desktop?
from gym-unrealcv.
It shows that the unrealcv client in python fails to connect to the unrealcv server in UE4 environment. Do you see any new windows appearing on your desktop?
Thank you for your reply! I found that the error because the server did not have a monitor. I try it on another computer with a monitor. But new errors occured:
0:ps
~/hzt/flour/active_tracking_drl$ CUDA_VISIBLE_DEVICES= /home/dell/anaconda3/envs/tracker/bin/python worker.py --log-dir save/tmp --env-id UnrealTrack-City1StefaniPath1-DiscreteColor-v1 --model-id convx2lstm --num-workers 1 --max-global-steps 250000000 --lr 5e-05 --ent-factor 0.01 --egreedy -1.0 --explore-factor 1.0 --job-name ps
/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/autobahn/wamp/auth.py:40: CryptographyDeprecationWarning: Python 3.5 support will be dropped in the next release of cryptography. Please upgrade your Python.
from cryptography.hazmat.primitives.kdf.pbkdf2 import PBKDF2HMAC
/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/universe/runtimes/init.py:7: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
spec = yaml.load(f)
[2022-04-07 20:27:39,255] Writing logs to file: /tmp/universe-739626.log
I tensorflow/core/distributed_runtime/rpc/grpc_channel.cc:197] Initialize GrpcChannelCache for job ps -> {0 -> localhost:12222}
I tensorflow/core/distributed_runtime/rpc/grpc_channel.cc:197] Initialize GrpcChannelCache for job worker -> {0 -> 127.0.0.1:12223}
I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:211] Started server with target: grpc://localhost:12222
1:w-0
[2022-04-07 20:27:39,262] Making new env: UnrealTrack-City1StefaniPath1-DiscreteColor-v1
Running docker-free env, pid:739730
Please wait for a while to launch env......
exec nohup /home/dell/hzt/flour/gym-unrealcv/gym_unrealcv/envs/UnrealEnv/SplineCharacterF/SplineCharacterC/Binaries/Linux/SplineCharacterC
nohup: ignoring input and appending output to 'nohup.out'
127.0.0.1
INFO:init:192:Got connection confirm: b'connected to SplineCharacterC'
Traceback (most recent call last):
File "worker.py", line 268, in
tf.app.run()
File "/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "worker.py", line 257, in main
run_worker(args, server, cluster)
File "worker.py", line 36, in run_worker
env = create_env(args.env_id, client_id=str(args.task), remotes=args.remotes)
File "/home/dell/hzt/flour/active_tracking_drl/envs.py", line 49, in create_env
return create_unrealcv_env(env_full_name)
File "/home/dell/hzt/flour/active_tracking_drl/envs.py", line 120, in create_unrealcv_env
env = gym.make(env_full_name)
File "/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/gym/envs/registration.py", line 161, in make
return registry.make(id)
File "/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/gym/envs/registration.py", line 119, in make
env = spec.make()
File "/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/gym/envs/registration.py", line 86, in make
env = cls(**self._kwargs)
File "/home/dell/hzt/flour/gym-unrealcv/gym_unrealcv/envs/unrealcv_tracking_spline.py", line 70, in init
self.reward_function = reward.Reward(setting)
File "/home/dell/hzt/flour/gym-unrealcv/gym_unrealcv/envs/tracking/reward.py", line 11, in init
self.dis_min = setting['min_distance']
KeyError: 'min_distance'
2:w-val
/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/autobahn/wamp/auth.py:40: CryptographyDeprecationWarning: Python 3.5 support will be dropped in the next release of cryptography. Please upgrade your Python.
from cryptography.hazmat.primitives.kdf.pbkdf2 import PBKDF2HMAC
/home/dell/anaconda3/envs/tracker/lib/python3.5/site-packages/universe/runtimes/init.py:7: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
spec = yaml.load(f)
[2022-04-07 20:27:49,284] Writing logs to file: /tmp/universe-739772.log
[2022-04-07 20:27:49,286] worker_val: val_model_secs < 0, no validating, exit...
3:tb
(base) dell@dell: ~/hzt/flour/active_tracking_drl$ tensorboard --logdir save/tmp --port 12345
tensorboard: command not found
I also do not know the how to control the agent to move in a screen. The agent can only rely on the mouse to turn and can't move.
Hope for your reply!
from gym-unrealcv.
Sorry for the late reply!
I have updated the environment setting files (City1StefaniPath1.json and City2MalcomPath2.json), and the error (KeyError: 'min_distance'
) you reported should be fixed.
from gym-unrealcv.
Sorry for the late reply! I have updated the environment setting files (City1StefaniPath1.json and City2MalcomPath2.json), and the error (
KeyError: 'min_distance'
) you reported should be fixed.
Thank you for helping me!
from gym-unrealcv.
Related Issues (20)
- Windows Support HOT 2
- the realated env setting file about paper 'Towards Distraction-Robust Active Visual Tracking' HOT 1
- Multi agent setting HOT 6
- env.reset( ) NotImplementedError HOT 1
- What will 2D environments output HOT 2
- Errors on Towards Distraction-Robust Active Visual Tracking HOT 3
- The problem about the fine-tuning of meta strategy HOT 3
- Is a URDF model usable in gym-unrealcv?
- Can not connect to ('127.0.0.1', 9000) HOT 10
- textures is not available to your platform HOT 4
- Unable to run python3 random_agent.py -e UnrealTrack-City1StefaniPath1-DiscreteColor-v1 HOT 1
- textures path not found HOT 4
- Should you show the env you are running? HOT 2
- Which does tensorflow version match keras==1.2.0 HOT 1
- 关于unrealcv CTRL+C无法释放资源的问题 HOT 1
- The gui is so small HOT 2
- Can you add support for Unreal Engine 5.3?
- unrealcv_cmd not found HOT 2
- OpenGL窗口黑屏 HOT 8
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 gym-unrealcv.