The two main uses of quantitative trading robots are to make markets through arbitrage;When the market is relatively cold,act as the corresponding seller or buyer,and activate trading volume in the market;After initializing the setting parameters,the quantitative trading robot will trade according to the strategy,automatically buying or selling when the set conditions are met,without the need for long-term trading;Strictly implement trading strategies based on the new market situation;Real time viewing of transaction conditions to ensure real-time execution of transactions;Try to avoid adverse effects caused by human subjective factors as much as possible.

　　量化策略是指使用計算機作為工具，通過一套固定的邏輯來分析、判斷和決策。量

　　化策略既可以自動執(zhí)行，也可以人工執(zhí)行；開發(fā)策略及詳情唯：MrsFu123,從本質(zhì)上說，交易機器人是一種軟件程序，它直接與金融交易所進(jìn)行交互(通常使用API獲取和解釋相關(guān)信息)，并根據(jù)市場數(shù)據(jù)的解釋發(fā)出買賣訂單。

　　這是一個PPQ量化的入口腳本，將你的模型和數(shù)據(jù)按要求進(jìn)行打包：

　　This file will show you how to quantize your network with PPQ

　　You should prepare your model and calibration dataset as follow:

　　~/working/model.onnx<--your model

　　~/working/data/*.npy or~/working/data/*.bin<--your dataset

　　if you are using caffe model:

　　~/working/model.caffemdoel<--your model

　　~/working/model.prototext<--your model

　　###MAKE SURE YOUR INPUT LAYOUT IS[N,C,H,W]or[C,H,W]###

　　quantized model will be generated at:~/working/quantized.onnx

　　"""

　　from ppq import*

　　from ppq.api import*

　　import os

　　#modify configuration below:

　　WORKING_DIRECTORY='working'#choose your working directory

　　TARGET_PLATFORM=TargetPlatform.PPL_CUDA_INT8#choose your target platform

　　MODEL_TYPE=NetworkFramework.ONNX#or NetworkFramework.CAFFE

　　INPUT_LAYOUT='chw'#input data layout,chw or hwc

　　NETWORK_INPUTSHAPE=[1,3,224,224]#input shape of your network

　　CALIBRATION_BATCHSIZE=16#batchsize of calibration dataset

　　EXECUTING_DEVICE='cuda'#'cuda'or'cpu'.

　　REQUIRE_ANALYSE=False

　　DUMP_RESULT=False#是否需要Finetuning一下你的網(wǎng)絡(luò)

　　#SETTING對象用于控制PPQ的量化邏輯

　　#當(dāng)你的網(wǎng)絡(luò)量化誤差過高時，你需要修改SETTING對象中的參數(shù)進(jìn)行特定的優(yōu)化

　　SETTING=UnbelievableUserFriendlyQuantizationSetting(

　　platform=TARGET_PLATFORM,finetune_steps=2500,

　　finetune_lr=1e-3,calibration='kl',#【改】量化算法可選'kl','pecentile','mse'

　　equalization=True,non_quantable_op=None)

　　SETTING=SETTING.convert_to_daddy_setting()

　　print('正準(zhǔn)備量化你的網(wǎng)絡(luò)，檢查下列設(shè)置:')

　　print(f'WORKING DIRECTORY:{WORKING_DIRECTORY}')

　　print(f'TARGET PLATFORM:{TARGET_PLATFORM.name}')

　　print(f'NETWORK INPUTSHAPE:{NETWORK_INPUTSHAPE}')

　　print(f'CALIBRATION BATCHSIZE:{CALIBRATION_BATCHSIZE}')

　　#此腳本針對單輸入模型，輸入數(shù)據(jù)必須是圖像數(shù)據(jù)layout:[n,c,h,w]

　　#如果你的模型具有更復(fù)雜的輸入格式，你可以重寫下面的load_calibration_dataset函數(shù)

　　#請注意，任何可遍歷對象都可以作為PPQ的數(shù)據(jù)集作為輸入

　　dataloader=load_calibration_dataset(

　　directory=WORKING_DIRECTORY,

　　input_shape=NETWORK_INPUTSHAPE,

　　batchsize=CALIBRATION_BATCHSIZE,

　　input_format=INPUT_LAYOUT)

　　print('網(wǎng)絡(luò)正量化中，根據(jù)你的量化配置，這將需要一段時間:')

　　quantized=quantize(

　　working_directory=WORKING_DIRECTORY,setting=SETTING,

　　model_type=MODEL_TYPE,executing_device=EXECUTING_DEVICE,

　　input_shape=NETWORK_INPUTSHAPE,target_platform=TARGET_PLATFORM,

　　dataloader=dataloader,calib_steps=32)