- 博客(51)
- 收藏
- 关注
原创 cuDNN安装
4.InstallingcuDNNon Windows4.1.PrerequisitesEnsure you meet the following requirements before you installcuDNN.在安装cuDNN之前,请确保满足以下要求。A GPU of compute capability 3.0 or higher. To under...
2019-10-16 21:26:32
518
2
原创 彻底解决CUDA安装,从翻译文档开始_Compiling CUDA Programs
前面一番折腾解决了安装问题,懒得再走回头路去记录了,直接从这里开始吧3.Compiling CUDA Programs(编译CUDA程序)The project files in the CUDA Samples have been designed to provide simple, one-click builds of the programs that include all ...
2019-10-16 19:01:19
701
原创 彻底解决CUDA安装_ 被坑的几个要点
按照要求,安装驱动,安装CUDA,更改安装位置也没问题。照着干你可能已经安装成功了,但为什么你觉得不成功呢?2.5.Verify the InstallationBefore continuing, it is important to verify that the CUDA toolkit can find and communicate correctly with the CUD...
2019-10-16 16:24:34
5279
翻译 愉快的学习就从翻译开始吧_TA-Lib : Technical Analysis Library_Home
一个金融数据分析库,看看都有什么东东!Multi-Platform Tools for Market Analysis .../用于市场分析的多平台工具TA-Lib is widely used by trading software developers requiring to perform technical analysis of financial market data.TA-Lib...
2018-07-05 23:59:40
319
原创 用matplotlib画K线
参考:https://blog.csdn.net/u014281392/article/details/73611624import tushare as tsimport matplotlib.pyplot as pltimport mpl_finance as mpfimport matplotlib as mplfrom matplotlib.pylab import date2nu...
2018-07-01 12:43:54
1084
翻译 愉快的学习就从翻译开始吧_Multivariate Forecasting
Multivariate Forecasting/多变量预测Another important type of time series is called multivariate time series.另一种重要的时间序列类型被称为多变量时间序列This is where we may have observations of multiple different measures and a...
2018-06-30 19:12:57
240
翻译 愉快的学习就从翻译开始吧_Multi-Step or Sequence Forecasting
Multi-Step or Sequence Forecasting/A different type of forecasting problem is using past observations to forecast a sequence of future observations.另一种类型的预测问题是使用过去的观测来预测未来观测的序列。This may be called sequ...
2018-06-30 18:02:49
232
翻译 愉快的学习就从翻译开始吧_How to Convert a Time Series to a Supervised Learning Problem in Python_3
One-Step Univariate Forecasting/单步单变量预测It is standard practice in time series forecasting to use lagged observations (e.g. t-1) as input variables to forecast the current time step (t).时间序列预测的标准做法是使用滞...
2018-06-30 17:16:31
317
翻译 愉快的学习就从翻译开始吧_How to Convert a Time Series to a Supervised Learning Problem in Python_2
The series_to_supervised() Function/series_to_supervised()函数We can use the shift() function in Pandas to automatically create new framings of time series problems given the desired length of input and...
2018-06-30 11:03:14
313
翻译 愉快的学习就从翻译开始吧_How to Convert a Time Series to a Supervised Learning Problem in Python_1
Pandas shift() Function/Pandas shift()函数A key function to help transform time series data into a supervised learning problem is the Pandas shift() function.帮助将时间序列数据转换为监督学习问题的关键功能是Pandas shift()函数。Giv...
2018-06-29 23:55:37
310
翻译 愉快的学习就从翻译开始吧_How to Convert a Time Series to a Supervised Learning Problem in Python_0
数据处理对时序预测是很重要的,这篇文章很有帮助How to Convert a Time Series to a Supervised Learning Problem in Python/在Python中如何把时序转换为监督学习问题Machine learning methods like deep learning can be used for time series forecasting...
2018-06-29 21:52:52
458
翻译 愉快的学习就从翻译开始吧_traces_A Python library for unevenly-spaced time series analysis.
traces A Python library for unevenly-spaced time series analysis.用于非均匀间隔的时序分析Python库Why?Taking measurements at irregular intervals is common, but most tools are primarily designed for evenly-spaced...
2018-06-26 20:22:16
422
原创 终于中招了,python中的大坑
predict_price = supervised_predictpredict_price.append(last_predict)predict_position = new_positionpredict_position.append(last_predict_position)supervised_predict和predict_position是两个数组,赋值给predict_...
2018-06-25 00:39:40
841
翻译 愉快的学习就从翻译开始吧_A Gentle Introduction to RNN Unrolling
Recurrent neural networks are a type of neural network where the outputs from previous time steps are fed as input to the current time step.递归神经网络是一种前一步的输出作为现在步输入的一种神经网络。This creates a network graph o...
2018-06-23 21:37:20
828
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_11_Multi-Step LSTM Network_Invert Transforms
Invert Transforms/翻转变换After the forecasts have been made, we need to invert the transforms to return the values back into the original scale.预测完成后,我们需要反转变换以将值返回到原始比例。This is needed so that we can calc...
2018-06-19 16:52:54
283
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_13_Multi-Step LSTM Network_Extensions&Summary
Extensions/扩展There are some extensions you may consider if you are looking to push beyond this tutorial.如果您希望超越本教程,可以考虑一些扩展。Update LSTM. Change the example to refit or update the LSTM as new data is m...
2018-06-19 13:57:40
401
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_12_Multi-Step LSTM Network_Complete Example
Complete Example/完整的例子We can tie all of these pieces together and fit an LSTM network to the multi-step time series forecasting problem.我们可以将所有这些部分组合在一起,并将LSTM网络应用于多步时间序列预测问题。The complete code listing...
2018-06-19 12:29:05
795
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_10_Multi-Step LSTM Network_Make LSTM Forecasts
Make LSTM Forecasts/让LSTM预测The next step is to use the fit LSTM network to make forecasts.下一步是用拟合的LSTM网络来做预测A single forecast can be made with the fit LSTM network by calling model.predict(). Again, t...
2018-06-19 12:12:38
361
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_9_Multi-Step LSTM Network_Fit LSTM Network
Fit LSTM Network/拟合LSTM网络Next, we need to fit an LSTM network model to the training data.接下来,我们需要将LSTM网络模型拟合到训练数据中。This first requires that the training dataset be transformed from a 2D array [samples...
2018-06-19 00:20:28
433
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_8_Multi-Step LSTM Network_Prepare Data
Multi-Step LSTM Network/多步LSTM网络In this section, we will use the persistence example as a starting point and look at the changes needed to fit an LSTM to the training data and make multi-step forecast...
2018-06-18 21:57:38
487
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_7_Persistence Model_Complete Example
Complete Example/完成例子We can put all of these pieces together.我们可以将所有这些片放在一起The complete code example for the multi-step persistence forecast is listed below.多步持续预测的完整代码示例如下:from pandas import DataFram...
2018-06-18 19:44:09
315
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_6_Persistence Model_Evaluate Forecasts
The final step is to evaluate the forecasts.最后一步是评估预测。We can do that by calculating the RMSE for each time step of the multi-step forecast, in this case giving us 3 RMSE scores. The function below, ev...
2018-06-18 18:41:05
284
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_5_Persistence Model_Make Forecasts
Make Forecasts/进行预测The next step is to make persistence forecasts.下一步是进行持续预测We can implement the persistence forecast easily in a function named persistence() that takes the last observation and the n...
2018-06-18 12:53:36
322
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_4_Persistence Model_Prepare data
Persistence Model/持续性模型A good baseline for time series forecasting is the persistence model.时序预测的好基准是持续性模型This is a forecasting model where the last observation is persisted forward. Because of its si...
2018-06-17 23:53:10
773
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting_3_Data Preparation and Model Evaluation
Data Preparation and Model Evaluation/数据准备和模型评估This section describes data preparation and model evaluation used in this tutorial本节描述本教程中用到的数据准备和模型评估Data Split/数据分割We will split the Shampoo Sales data...
2018-06-17 18:43:32
292
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting _2_Shampoo Sales Dataset
Shampoo Sales Dataset/洗发水销售数据集This dataset describes the monthly number of sales of shampoo over a 3-year period.这个数据集描述了三年期间每月的洗发水销售数字The units are a sales count and there are 36 observations. The or...
2018-06-17 17:25:55
804
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting with Long Short-Term Memory Networks in Python_1
Tutorial Overview/教程概述This tutorial is broken down into 4 parts; they are:本教程分为四部分,他们是Shampoo Sales Dataset洗发水数据集Data Preparation and Model Evaluation数据准备和模型评估Persistence Model持续性模型Multi-Step LSTM多步LS...
2018-06-17 16:02:05
424
翻译 愉快的学习就从翻译开始吧_Multi-step Time Series Forecasting with Long Short-Term Memory Networks in Python_0
The Long Short-Term Memory network or LSTM is a recurrent neural network that can learn and forecast long sequences.长短期记忆网络或者LSTM是一种可以学习和预测长序列的递归神经网络A benefit of LSTMs in addition to learning long seq...
2018-06-17 15:50:21
319
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_8_Further Reading&Summary
Further Reading/进一步阅读This section provides more resources on the topic if you are looking go deeper.如果您想更深入研究,本节将提供更多有关该主题的资源。Beijing PM2.5 Data Set on the UCI Machine Learning RepositoryThe 5 Step Li...
2018-06-17 12:06:44
260
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_7_Update:Train On Multiple Lag
吐槽,CSDN的标题长度怎么不能再长点呀,小标题都没法写全了本来还想把前面第一个洗发水的例子每篇都在加个小标题的,看来也没法弄了Update: Train On Multiple Lag Timesteps Example更新,在多个滞后时间步上训练的例子There have been many requests for advice on how to adapt the above examp...
2018-06-17 11:59:02
552
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_6_Complete Example
The complete example is listed below.完整的示例如下:NOTE: This example assumes you have prepared the data correctly, e.g. converted the downloaded “raw.csv” to the prepared “pollution.csv“. See the first par...
2018-06-16 18:20:02
312
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_5_Evaluate Model
After the model is fit, we can forecast for the entire test dataset.模型被拟合后,我们就能在整个测试数据集上预测We combine the forecast with the test dataset and invert the scaling. We also invert scaling on the test datas...
2018-06-16 17:34:39
214
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_4_Define and Fit Model
In this section, we will fit an LSTM on the multivariate input data.本章,我们将在多变量输入数据上拟合LSTMFirst, we must split the prepared dataset into train and test sets. To speed up the training of the model for t...
2018-06-16 15:10:51
356
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_3_Multivariate LSTM Forecast
3. Multivariate LSTM Forecast Model/多变量LSTM预测模型In this section, we will fit an LSTM to the problem.本章我们将一个LSTM拟合到这个问题LSTM Data Preparation/LSTM 数据准备The first step is to prepare the pollution dataset f...
2018-06-15 23:22:32
1093
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_2_Basic Data Preparation
2. Basic Data Preparation/基本数据准备The data is not ready to use. We must prepare it first.数据没有准备好来用,我们必须先准备好它(说处理多好理解)Below are the first few rows of the raw dataset.123456No,year,month,day,hour,pm2.5,DE...
2018-06-15 14:02:32
284
原创 更新anacaonda后,HDF5 header version与HDF5 library不匹配问题的解决
How to Setup a Python Environment for Machine Learning and Deep Learning with Anaconda昨晚照着这个连接一通更新anaconda,结果就报错了Warning! ***HDF5 library version mismatched error***The HDF5 header files used to comp...
2018-06-15 10:27:56
15770
34
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_1_Air Pollution Forecasting
1. Air Pollution Forecasting/空气污染预测In this tutorial, we are going to use the Air Quality dataset.本教程中我们将使用空气质量数据集This is a dataset that reports on the weather and the level of pollution each hour for ...
2018-06-14 22:40:26
489
翻译 愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_0
Multivariate Time Series Forecasting with LSTMs in Keras/Keras中多变量时序预测Neural networks like Long Short-Term Memory (LSTM) recurrent neural networks are able to almost seamlessly model problems with mul...
2018-06-14 21:24:52
515
原创 愉快的学习就从翻译开始吧_12-例子中的一些问题
前面的例子作者将数据做了差分,然后又搞了个逆差分,我觉得非常的烦,决定把它改为非差分的,看下结果如何
2018-06-14 11:16:37
234
翻译 愉快的学习就从翻译开始吧_11-Time Series Forecasting with the Long Short-Term Memory Network in Python
Summary/总结In this tutorial, you discovered how to develop an LSTM model for time series forecasting.本教程中,你了解了如何开发用于时间序列预测的LSTM模型Specifically, you learned:特别是,你学到了:How to prepare time series data for d...
2018-06-13 10:32:16
165
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人