https://github.com/floodsung/wechat_jump_end_to_end
Playing Wechat Jump Game with End-to-End Convolutional Neural Networks
https://github.com/floodsung/wechat_jump_end_to_end
deep-learning wechat-jump-game
Last synced: 12 months ago
JSON representation
Playing Wechat Jump Game with End-to-End Convolutional Neural Networks
- Host: GitHub
- URL: https://github.com/floodsung/wechat_jump_end_to_end
- Owner: floodsung
- License: mit
- Created: 2018-01-09T14:46:02.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-02-03T03:05:00.000Z (over 8 years ago)
- Last Synced: 2025-04-02T14:21:32.596Z (about 1 year ago)
- Topics: deep-learning, wechat-jump-game
- Language: Python
- Size: 1.32 MB
- Stars: 180
- Watchers: 13
- Forks: 36
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Wechat_Jump_End_to_End
## Prerequisite
pytorch
## How to use it
Connect your iPhone or Android to your computer, follow this guide:
[Android and iOS connection guide](https://github.com/wangshub/wechat_jump_game/wiki/Android-%E5%92%8C-iOS-%E6%93%8D%E4%BD%9C%E6%AD%A5%E9%AA%A4)
Then:
```
python run_ios.py
or
python run_android.py
```
## Note
The code is tested on iPhone 6s and Xiaomi Note3.
Due to different screen pixels on different phones, you have to adjust SCALE value in the code so as to run successfully on your device.
Just adjust SCALE value in [0.9,1.1].
Have Fun!
## About Training
If you are interested in how to train this model, please check this git: [wechat_jump_end_to_end_train](https://github.com/songrotek/wechat_jump_end_to_end_train)