天勤量化开发包, 期货量化, 实时行情/历史数据/实盘交易

Overview

TqSdk 天勤量化交易策略程序开发包

TqSdk 是一个由信易科技发起并贡献主要代码的开源 python 库. 依托快期多年积累成熟的交易及行情服务器体系, TqSdk 支持用户使用极少的代码量构建各种类型的量化交易策略程序, 并提供包含期货、期权、股票的 历史数据-实时数据-开发调试-策略回测-模拟交易-实盘交易-运行监控-风险管理 全套解决方案.

from tqsdk import TqApi, TqAuth, TqAccount, TargetPosTask

api = TqApi(TqAccount("H海通期货", "4003242", "123456"), auth=TqAuth("信易账户", "账户密码"))      # 创建 TqApi 实例, 指定交易账户
q_1910 = api.get_quote("SHFE.rb1910")                         # 订阅近月合约行情
t_1910 = TargetPosTask(api, "SHFE.rb1910")                    # 创建近月合约调仓工具
q_2001 = api.get_quote("SHFE.rb2001")                         # 订阅远月合约行情
t_2001 = TargetPosTask(api, "SHFE.rb2001")                    # 创建远月合约调仓工具

while True:
  api.wait_update()                                           # 等待数据更新
  spread = q_1910["last_price"] - q_2001["last_price"]        # 计算近月合约-远月合约价差
  print("当前价差:", spread)
  if spread > 250:
    print("价差过高: 空近月,多远月")                            
    t_1910.set_target_volume(-1)                              # 要求把1910合约调整为空头1手
    t_2001.set_target_volume(1)                               # 要求把2001合约调整为多头1手
  elif spread < 200:
    print("价差回复: 清空持仓")                               # 要求把 1910 和 2001合约都调整为不持仓
    t_1910.set_target_volume(0)
    t_2001.set_target_volume(0)

要快速了解如何使用TqSdk, 可以访问我们的 十分钟快速入门指南.

Architecture

系统架构图

Features

TqSdk 提供的功能可以支持从简单到复杂的各类策略程序.

  • 公司级数据运维,提供当前所有可交易合约从上市开始的 全部Tick数据和K线数据
  • 支持市场上90%的期货公司 实盘交易
  • 支持 模拟交易
  • 支持 Tick级和K线级回测, 支持 复杂策略回测
  • 提供近百个 技术指标函数及源码
  • 用户无须建立和维护数据库, 行情和交易数据全在 内存数据库 , 无访问延迟
  • 优化支持 pandasnumpy
  • 无强制框架结构, 支持任意复杂度的策略, 在一个交易策略程序中使用多个品种的K线/实时行情并交易多个品种
  • 配合开发者支持工具,能够进行交易信号打点,支持自定义指标画图

Installation

TqSdk 仅支持 Python 3.6 及更高版本. 要安装 TqSdk, 可使用 pip:

$ pip install tqsdk

Documentation

在线阅读HTML版本文档: https://doc.shinnytech.com/tqsdk/latest

在线问答社区: https://www.shinnytech.com/qa

知乎账户【天勤量化】:https://www.zhihu.com/org/tian-qin-liang-hua/activities

用户交流QQ群: 619870862 (目前只允许给我们点过STAR的同学加入, 加群时请提供github用户名)

Gui

TqSdk本身自带的web_gui功能,简单一行参数即可支持调用图形化界面,详情参考web_gui TqSdk web_gui

About us

信易科技 是专业的期货软件供应商和交易所授权行情服务商. 旗下的快期系列产品已为市场服务超过10年. TqSdk 是公司开源计划的一部分.

Comments
  • 完善期权合约字段

    完善期权合约字段

    为了更好地调取期权合约,在tqsdk.objs.Quote中加入两个字段: product_id:用于识别基础现货资产 option_class:用于识别"认购" or "认沽" 上述字段来自于:"https://openmd.shinnytech.com/t/md/symbols/latest.json" 只是在python项目中没有调取。

    opened by gamcing 10
  • 关于 tq 的 K 线问题

    关于 tq 的 K 线问题

    最近用了一段时间 tq,也和周边其它产品对比过,发现 tq的 K 线有个问题: 跨区结束时间居然是在下一个时间段出现 ,例如11:30:00的结束 K 线是没有的,13:30:00才是11:30:00的结束线,同样,2:30和15:00的也是没有的, 例如30分钟线,TQ 的序列是这样的: 10:30:00 11:00:00 13:30:00 14:00:00 其它产品是这样的: 10:30:00 11:00:00 11:30:00 14:00:00

    我在 TQ回测中,收到13:30:00的 K 线,回测时间也是13:30:00,下单时间却是11:29:59.9999,结果就导致用将来的趋势去过去下单,出现了错误的利润。

    希望官方能告知解决办法!

    opened by zshchou 7
  • 下单后无法取到正确的成交价格,有无方法?

    下单后无法取到正确的成交价格,有无方法?

    如下的方法,下单后无法取到正确的成交价格, target_pos.set_target_volume(1) api.wait_update() while not api.is_changing(trade): 空 api.wait_update() 空 if True: #判断条件xxx 空 格 lot = position.pos 空 格 if lot>0 : 空 格 openPrice = position.open_price_long 空 格 elif lot<0: 空 格 openPrice = position.open_price_short 空 格 else: 空 格 openPrice = 0 空 格 print("openPrice",openPrice) 成交价格是延时一些毫秒后给出的。 api.is_changing(trade)触发后,position.open_price_short和position.open_price_long却没有及时更新。所以取到的价格是错误的。

    如何写判断条件xxx? 数据结构position,trade里都没有标志,是否已成交,且返回正确的成交价格。 希望能给出正确的案例。

    opened by victorzsl 5
  • [BUG?]在0.9.17的Position对象找不到pos_long和pos_short

    [BUG?]在0.9.17的Position对象找不到pos_long和pos_short

    文档写着: volume_long = None 期货公司查询的多头手数 (不推荐, 推荐使用pos_long)

    但是从0.9.17 tqsdk收到的Postion对象内容,完全找不到pos_long和pos_short,难道是漏了?

    这是收到的实际数据: <tqsdk.objs.Position object at 0x7fd54e8278d0>, D({'exchange_id': 'SHFE', 'instrument_id': 'ag1912', 'pos_long_his': 40, 'pos_long_today': 10, 'pos_short_his': 0, 'pos_short_today': 0, 'volume_long_today': 10, 'volume_long_his': 40, 'volume_long': 50, 'volume_long_frozen_today': 0, 'volume_long_frozen_his': 0, 'volume_long_frozen': 0, 'volume_short_today': 0, 'volume_short_his': 0, 'volume_short': 0, 'volume_short_frozen_today': 0, 'volume_short_frozen_his': 0, 'volume_short_frozen': 0, 'open_price_long': 4249.8, 'open_price_short': 0.0, 'open_cost_long': 3187350.0, 'open_cost_short': 0.0, 'position_price_long': 4569.8, 'position_price_short': 0.0, 'position_cost_long': 3427350.0, 'position_cost_short': 0.0, 'float_profit_long': 237150.0, 'float_profit_short': 0.0, 'float_profit': 237150.0, 'position_profit_long': -2850.0, 'position_profit_short': 0.0, 'position_profit': -2850.0, 'margin_long': 274380.0, 'margin_short': 0.0, 'margin': 274380.0, 'user_id': '135763', 'volume_long_yd': 50, 'volume_short_yd': 0, 'last_price': 4566.0})

    opened by archerhu77 5
  • 回测订阅tick后,在交易时间段刚开始下单,可能无法成交

    回测订阅tick后,在交易时间段刚开始下单,可能无法成交

    订阅了tick时,如果指定回测开始时间为一个交易时间段的开始时间 而tick未更新数据,则导致无法成交(在sim增加交易时间判断之后):当tick未更新时,quote时间停在上一个交易时间段,而回测时间在下一交易时间段开始,此时应成交 却报错”不在交易时间段内“.

    (如果订阅的是K线,或未订阅,此问题也能触发;但当quote生成频率修改为在K线生成时也同时生成,此问题则不存在。)

    opened by shinny-limin 3
  • 天勤终端的策略同品种实盘与回测 互相干扰?

    天勤终端的策略同品种实盘与回测 互相干扰?

    在天勤中运行simnow实盘, IF策略一直开启,未关闭。 前一交易日有持仓,position.pos=-1 次日,早盘前对策略进行了昨日数据的回测,检查开平仓是否一致。 检查结果近似一致,相差不大。也保留了持仓,position.pos=-1。

    随后删除回测。

    早开盘,策略继续运行, 发现持仓居然为2手空仓了。(策略每分钟打印持仓) position.pos=-2

    大约9:45的样子,策略满足平仓条件, 开始平仓,报告仅平仓1手,另1手失败。

    失败是正常的,因为simnow仅一手持仓。

    不正常的是回测似乎干扰了实盘的position.pos值。 这是否一个Bug?

    数据没有保留,请自行实验验证。

    opened by victorzsl 3
  • api.draw_line函数绘的图在天勤终端显示不正确?

    api.draw_line函数绘的图在天勤终端显示不正确?

    在策略中想利用api.draw_line绘制信号线(线段),打印日志显示开、平点数据都是正确的,但是显示出来的结果都是水平直线,不知道是sdk的bug还是天勤终端的bug,貌似“SEG”、“RAY”均不起作用,都会绘制成直线。 绘图语句示例: if longamt < prelongamt: #如果有平仓,则绘制信号线 api.draw_line(klines, lox, loy, kid, kclose, line_type="SEG", color=0xFF0000FF) print(f"cover long: lox:{lox}, loy:{loy}, lcx:{kid}, lcy:{kclose}") lox = None #开仓位置, long open x loy = None #开仓位置, long open y

    opened by xcgoo 3
  • Mac ssl 问题

    Mac ssl 问题

    使用mac mojave的时候,在pycharm中会ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1056)与 wss://openmd.shinnytech.com/t/md/front/mobile 的网络连接断开,请检查客户端及网络是否正常!!这个问题,请问一下,这个问题应该如何解决,谢谢。 image

    opened by kingdjf 3
  • 使用测试账号 TqSim,断网恢复以后数据没有自动更新

    使用测试账号 TqSim,断网恢复以后数据没有自动更新

    image

    版本:0.9.8 操作系统:阿里云 Centos 7

    代码:

    def main():
        symbol1 = "[email protected]"
        symbol2 = "[email protected]"
        api = TqApi(TqSim())
        account = api.get_account()
        main_x_symbol = ""
        main_y_symbol = ""
    
        k_x = api.get_kline_serial(symbol1, 60 * 60 * 24)
        k_y = api.get_kline_serial(symbol2, 60 * 60 * 24)
    
        quote_x = api.get_quote(symbol1)
        quote_y = api.get_quote(symbol2)
    
        target_pos_x = TargetPosTask(api, symbol1)
        target_pos_y = TargetPosTask(api, symbol2)
    
        count = 0
    
        with closing(api):
            while True:
                api.wait_update()
                if not api.is_changing(quote_x) and not api.is_changing(quote_y):
                    continue
                last_k_x = k_x.iloc[-1]
                last_k_y = k_y.iloc[-1]
    
                vx = last_k_x.close
                vy = last_k_y.close
                print(vx, vy)
    

    断网以后即使网络恢复了,api.wait_update() 以后代码不再被执行。

    opened by daijiahua 3
  • 最新价格监控

    最新价格监控

    quote和kline 里面都包含最新的价格, 如果只监控 最新价格的变化, 他们更新的频率是一样的吗?

    有这个需求是,如果频率一样,我就只需要关注kline里面价格的最新变化,kline结构数据比quote少很多,可能新的数据就更少了, 可以大大节约网络传输。

    但是不确定如果只关心最新价格,更新频率是否一样?

    opened by 4ever911 3
  • 如何取消合约数据的自动更新?

    如何取消合约数据的自动更新?

    比如说,

    q = api.get_quote("SHFE.cu1812")
    klines = api.get_kline_serial("SHFE.cu1812", 10)

    while api.wait_update() 等待后,q和klines就会自动更新,但是如果我监控的数据比较多,比如我只是临时用了几个合约 5/30/dayily kline数据, 因为没有函数取消这些合约的自动更新, 是否会造成数据太多,影响网络速度?

    opened by 4ever911 3
  • 官方文档的示例就跑不通 Task was destroyed but it is pending!

    官方文档的示例就跑不通 Task was destroyed but it is pending!

    在使用天勤量化之前,默认您已经知晓并同意以下免责条款,如果不同意请立即停止使用:https://www.shinnytech.com/blog/disclaimer/ 2022-06-18 12:09:01 - INFO - 通知 : 与 wss://free-api.shinnytech.com/t/nfmd/front/mobile 的网络连接已建立 204100.0 246 Task was destroyed but it is pending! task: <Task pending coro=<TqBaseApi._windows_patch() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseApi.py:119> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287C644A2E8>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<TqApi._notify_watcher() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\api.py:3604> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287CF30A8B8>()]> cb=[TqBaseApi._on_task_done()]> Exception ignored in: <coroutine object TqApi._notify_watcher at 0x00000287C63D35C8> Traceback (most recent call last): File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\api.py", line 3604, in _notify_watcher File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\channel.py", line 143, in anext File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\queues.py", line 161, in get File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseApi.py", line 50, in _call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 691, in call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 479, in _check_closed RuntimeError: Event loop is closed Task was destroyed but it is pending! task: <Task pending coro=<TqConnect._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py:176> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287CF30A9D8>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<TqReconnect._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py:261> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287C644A6D8>()]> cb=[TqBaseApi._on_task_done()]> Exception ignored in: <coroutine object TqConnect._run at 0x00000287C6374C48> Traceback (most recent call last): File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py", line 225, in _run File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\tasks.py", line 589, in sleep File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\events.py", line 726, in get_event_loop_policy File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\events.py", line 719, in _init_event_loop_policy ImportError: sys.meta_path is None, Python is likely shutting down sys:1: RuntimeWarning: coroutine 'WebSocketCommonProtocol.write_close_frame' was never awaited Task was destroyed but it is pending! task: <Task pending coro=<TqConnect._send_handler() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py:232> wait_for=> Exception ignored in: <coroutine object TqReconnect._run at 0x00000287E36762C8> Traceback (most recent call last): File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py", line 311, in _run File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseApi.py", line 50, in _call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 691, in call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 479, in _check_closed RuntimeError: Event loop is closed Task was destroyed but it is pending! task: <Task pending coro=<TqReconnect._send_handler() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\connect.py:315> wait_for=> Task was destroyed but it is pending! task: <Task pending coro=<TqSymbols._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\symbols.py:29> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287C644A9A8>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<TqTradingStatus._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\trading_status.py:26> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287C63DCE28>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<BaseSim._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\tradeable\sim\basesim.py:78> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287CC01F978>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<TqWebHelper._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\tqwebhelper.py:80> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287CF30AA98>()]> cb=[TqBaseApi._on_task_done()]> Task was destroyed but it is pending! task: <Task pending coro=<DataExtension._run() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\data_extension.py:82> wait_for=<Future pending cb=[<TaskWakeupMethWrapper object at 0x00000287CF30AD08>()]> cb=[TqBaseApi._on_task_done()]> Exception ignored in: <coroutine object TqSymbols._run at 0x00000287C63D36C8> Traceback (most recent call last): File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\symbols.py", line 63, in _run File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseApi.py", line 50, in _call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 691, in call_soon File "H:\A_software\Anaconda3\envs\pp212\lib\asyncio\base_events.py", line 479, in _check_closed RuntimeError: Event loop is closed Task was destroyed but it is pending! task: <Task pending coro=<TqSymbols._sim_handler() running at H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\symbols.py:68> wait_for=> Exception ignored in: <coroutine object TqTradingStatus._run at 0x00000287C63D37C8> Traceback (most recent call last): File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\trading_status.py", line 26, in _run File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseModule.py", line 47, in _run File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseModule.py", line 47, in File "H:\A_software\Anaconda3\envs\pp212\lib\site-packages\tqsdk\baseApi.py", line 50, in _call_soon File "H:\A_software\Anaconda3\

    opened by ArtificialZeng 1
  • Exception: 无法创建复盘服务器

    Exception: 无法创建复盘服务器

    ===简单描述=== 用文档里的代码示例,做复盘报错:Exception: 无法创建复盘服务器 (信易账户在试用有效期内,执行请求普通的行情数据没有问题)

    ===错误日志=== (py37_quant) [email protected]:/mnt/Data/Workspace/python/ats/003_tianqin$ cd /mnt/Data/Workspace/python/ats/003_tianqin ; /usr/bin/env /mnt/Data/System/Programs/anaconda3/envs/py37_quant/bin/python /home/xiao/.vscode/extensions/ms-python.python-2021.10.1317843341/pythonFiles/lib/python/debugpy/launcher 40143 -- /mnt/Data/Workspace/python/ats/003_tianqin/01_temp/pureTest.py 在使用天勤量化之前,默认您已经知晓并同意以下免责条款,如果不同意请立即停止使用:https://www.shinnytech.com/blog/disclaimer/ Traceback (most recent call last): File "/mnt/Data/Workspace/python/ats/003_tianqin/01_temp/pureTest.py", line 4, in api = TqApi(backtest = TqReplay(date(2019,12,23)), auth=TqAuth("listplot3d", "123456")) File "/mnt/Data/System/Programs/anaconda3/envs/py37_quant/lib/python3.7/site-packages/tqsdk/api.py", line 284, in init self._setup_connection() # 初始化通讯连接 File "/mnt/Data/System/Programs/anaconda3/envs/py37_quant/lib/python3.7/site-packages/tqsdk/api.py", line 2986, in _setup_connection self._ins_url, self._md_url = self._backtest._create_server(self) File "/mnt/Data/System/Programs/anaconda3/envs/py37_quant/lib/python3.7/site-packages/tqsdk/backtest.py", line 795, in _create_server raise Exception("无法创建复盘服务器,请检查复盘日期后重试。") Exception: 无法创建复盘服务器,请检查复盘日期后重试。 Task was destroyed but it is pending! task: <Task pending coro=<TqApi._notify_watcher() running at /mnt/Data/System/Programs/anaconda3/envs/py37_quant/lib/python3.7/site-packages/tqsdk/api.py:3442> cb=[TqBaseApi._on_task_done()]> sys:1: RuntimeWarning: coroutine 'TqApi._notify_watcher' was never awaited

    ===重现步骤=== 基于这里的代码:https://doc.shinnytech.com/tqsdk/latest/usage/replay.html?highlight=%E5%A4%8D%E7%9B%98,改成下面的代码,然后运行:

    from datetime import date from tqsdk import TqApi, TqReplay,TqAuth

    api = TqApi(backtest = TqReplay(date(2019,12,23)), auth=TqAuth("listplotd", "123456")) print("hello relay") api.close()

    opened by listplot3d 1
  • 在协程里用不了get_kline_serial?

    在协程里用不了get_kline_serial?

    我用的visual studio code 也提示: Exception: TqSdk 使用了 python3 的原生协程和异步通讯库 asyncio,您所使用的 IDE 不支持 asyncio, 请使用 pycharm 或其它支持 asyncio 的 IDE 我发现只要在协程里调用get_kline_serial就会提示,在协程外面调用就不会报这个错误。 我看了一下貌似tqsdk也依赖那个事件循环,我协程本来就运行在事件循环里面,就不能共用一个事件循环嘛?

    opened by kkqy 0
Releases(3.2.12)
Owner
信易科技
上海信易信息科技股份有限公司
信易科技
PyTorch implementation of Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Release Notes The official PyTorch implementation of Neural View S

Angtian Wang 20 Oct 09, 2022
PantheonRL is a package for training and testing multi-agent reinforcement learning environments.

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

Stanford Intelligent and Interactive Autonomous Systems Group 57 Dec 28, 2022
Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints Installation Run pipenv install (at your own risk with --skip-lo

Autonomous Learning Group 65 Dec 27, 2022
Label-Free Model Evaluation with Semi-Structured Dataset Representations

Label-Free Model Evaluation with Semi-Structured Dataset Representations Prerequisites This code uses the following libraries Python 3.7 NumPy PyTorch

8 Oct 06, 2022
🕹️ Official Implementation of Conditional Motion In-betweening (CMIB) 🏃

Conditional Motion In-Betweening (CMIB) Official implementation of paper: Conditional Motion In-betweeening. Paper(arXiv) | Project Page | YouTube in-

Jihoon Kim 81 Dec 22, 2022
The code for 'Deep Residual Fourier Transformation for Single Image Deblurring'

Deep Residual Fourier Transformation for Single Image Deblurring Xintian Mao, Yiming Liu, Wei Shen, Qingli Li and Yan Wang News 2021.12.5 Release Deep

145 Jan 05, 2023
A PyTorch port of the Neural 3D Mesh Renderer

Neural 3D Mesh Renderer (CVPR 2018) This repo contains a PyTorch implementation of the paper Neural 3D Mesh Renderer by Hiroharu Kato, Yoshitaka Ushik

Daniilidis Group University of Pennsylvania 1k Jan 09, 2023
Deep Probabilistic Programming Course @ DIKU

Deep Probabilistic Programming Course @ DIKU

52 May 14, 2022
Re-implementation of the vector capsule with dynamic routing

VectorCapsule Re-implementation of the vector capsule with dynamic routing We implement the vector capsule and dynamic routing via graph neural networ

ZhenchaoTang 10 Feb 10, 2022
Relative Uncertainty Learning for Facial Expression Recognition

Relative Uncertainty Learning for Facial Expression Recognition The official implementation of the following paper at NeurIPS2021: Title: Relative Unc

35 Dec 28, 2022
Character Controllers using Motion VAEs

Character Controllers using Motion VAEs This repo is the codebase for the SIGGRAPH 2020 paper with the title above. Please find the paper and demo at

Electronic Arts 165 Jan 03, 2023
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

RASP Setup Mac or Linux Run ./setup.sh . It will create a python3 virtual environment and install the dependencies for RASP. It will also try to insta

141 Jan 03, 2023
Reference code for the paper CAMS: Color-Aware Multi-Style Transfer.

CAMS: Color-Aware Multi-Style Transfer Mahmoud Afifi1, Abdullah Abuolaim*1, Mostafa Hussien*2, Marcus A. Brubaker1, Michael S. Brown1 1York University

Mahmoud Afifi 36 Dec 04, 2022
Python implementation of O-OFDMNet, a deep learning-based optical OFDM system,

O-OFDMNet This includes Python implementation of O-OFDMNet, a deep learning-based optical OFDM system, which uses neural networks for signal processin

Thien Luong 4 Sep 09, 2022
Paaster is a secure by default end-to-end encrypted pastebin built with the objective of simplicity.

Follow the development of our desktop client here Paaster Paaster is a secure by default end-to-end encrypted pastebin built with the objective of sim

Ward 211 Dec 25, 2022
Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

Photo-Realistic-Super-Resoluton Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" [Paper]

Harry Yang 199 Dec 01, 2022
This is the pytorch implementation for the paper: *Learning Accurate Performance Predictors for Ultrafast Automated Model Compression*, which is in submission to TPAMI

SeerNet This is the pytorch implementation for the paper: Learning Accurate Performance Predictors for Ultrafast Automated Model Compression, which is

3 May 01, 2022
Progressive Growing of GANs for Improved Quality, Stability, and Variation

Progressive Growing of GANs for Improved Quality, Stability, and Variation — Official TensorFlow implementation of the ICLR 2018 paper Tero Karras (NV

Tero Karras 5.9k Jan 05, 2023
Neural Caption Generator with Attention

Neural Caption Generator with Attention Tensorflow implementation of "Show

Taeksoo Kim 510 Nov 30, 2022
SOTA model in CIFAR10

A PyTorch Implementation of CIFAR Tricks 调研了CIFAR10数据集上各种trick,数据增强,正则化方法,并进行了实现。目前项目告一段落,如果有更好的想法,或者希望一起维护这个项目可以提issue或者在我的主页找到我的联系方式。 0. Requirement

PJDong 58 Dec 21, 2022