搜索资源列表
rnnoise
- 改代码为音频降噪功能,是基于RNN的音频降噪算法。其中采用的是 GRU/LSTM 模型,支持wav格式。(The modified code is an audio denoising function, which is based on RNN's audio denoising algorithm. The GRU/LSTM model is adopted to support the wav format.)
tf-rnn-attention-master
- attention实现代码,应用python编写(Attention implementation code, written in python)
RNN_MATLAB-master
- 一种深度学习框架的matlab代码可用于训练时间序列对象(Can be used to train time series objects)
AbnormalBehaviorDetection-master
- 基于光流特征的监控视频异常行为检测 使用CNN,RNN在UCSD数据库中实现 使用Keras,python3.6(Abnormal Behavior Detection of Monitoring Video Based on Optical Flow Characteristics)
Elman
- 利用MATLAB实现循环神经网络的例子,便于大家更好的理解循环神经网络RNN的原理。((The example of recurrent neural network is implemented by MATLAB, so that you can have a better understanding of the principle of recurrent neural network RNN.))
lesson47-LSTM实战
- 长短期记忆网络(LSTM,Long Short-Term Memory)是一种时间循环神经网络,是为了解决一般的RNN(循环神经网络)存在的长期依赖问题而专门设计出来的,所有的RNN都具有一种重复神经网络模块的链式形式。在标准RNN中,这个重复的结构模块只有一个非常简单的结构,例如一个tanh层。(LSTM (Long Term short-term Memory) is a kind of time circulation neural network, which is specially
load_RNN
- python 电力负荷预测,rnn版本,python环境(Python power load forecasting, RNN version, python environment)
stock-rnn-master
- 用深度学习算法进行股票价格预测,文件中含有数据集(Using deep learning algorithm to forecast stock price, the file contains data set)
chatbot
- 聊天机器人 原理: 严谨的说叫 ”基于深度学习的开放域生成对话模型“,框架为Keras(Tensorflow的高层包装),方案为主流的RNN(循环神经网络)的变种LSTM(长短期记忆网络)+seq2seq(序列到序列模型),外加算法Attention Mechanism(注意力机制),分词工具为jieba,UI为Tkinter,基于”青云“语料(10万+闲聊对话)训练。 运行环境:python3.6以上,Tensorflow,pandas,numpy,jieba。(Chat Robot
lstm_tensorflow
- tensorflow2.0的Lstm实现(LSTM implementation of tensorflow 2.0)
ESNtools
- 一种新型的循环神经网络(RNN),在时序预测领域有广泛应用前景(A new type of recurrent neural network (RNN) has a wide application prospect in the field of time series prediction)