fuqiuai / TensorFlow-Deep-LearningLinks
用TensorFlow搭建CNN/RNN/LSTM/GRU/BiRNN/BiLSTM/BiGRU/Capsule Network等deep learning模型
☆60Updated 7 years ago
Alternatives and similar repositories for TensorFlow-Deep-Learning
Users that are interested in TensorFlow-Deep-Learning are comparing it to the libraries listed below
Sorting:
- CNN-BiGRU-Attention模型☆102Updated 3 years ago
- attention-based LSTM/Dense implemented by Keras☆300Updated 7 years ago
- LSTM, CNN, CNNLSTM, BiLSTM, MLP☆10Updated 7 years ago
- A PyTorch Tutorials of Sentiment Analysis Classification (RNN, LSTM, Bi-LSTM, LSTM+Attention, CNN)☆330Updated 2 years ago
- 基于Keras的LSTM多变量时间序列预测☆26Updated 8 years ago
- keras注意力机制☆19Updated 7 years ago
- ☆278Updated 3 years ago
- 文本分类, 双向lstm + attention 算法☆90Updated 5 years ago
- Using K-NN, SVM, Bayes, LSTM, and multi-variable LSTM models on time series forecasting☆53Updated 6 years ago
- the extension of https://github.com/philipperemy/keras-attention-mechanism , create a new scipt to add attetion to input dimensions rath…☆78Updated last year
- LSTM和SVM实现设备故障诊断☆51Updated 6 years ago
- CNN with attention and CNN_LSTM_attention(pytorch)☆18Updated 6 years ago
- 基于LSTM+CNN的自然语言处理,基于单维LSTM、多维LSTM时序预测算法和多元线性回归算法的预测模型☆11Updated 9 months ago
- 基于波士顿房屋租赁价格数据,使用lasso回归算法做特征选择后,分别使用线 性回归、Lasso回归、Ridge回归、Elasitic Net四类回归算法构建模型(分别测试1,2,3阶)☆13Updated 6 years ago
- ☆16Updated 3 years ago
- 基于深度学习的溶解氧时间序列预测模型☆31Updated 5 years ago
- 基于Keras的LSTM多变量时间序列预测☆185Updated 8 years ago
- 使用改良的Transformer模型应用于多维时间序列的分类任务上☆96Updated 4 years ago
- 建立SARIMA-LSTM混合模型预测时间序列问题。以PM2.5值为例,使用UCI公开的自2013年1月17日至2015年12月31日五大城市PM2.5小时检测数据,将数据按时间段划分,使用SARIMA过滤其线性趋势,再对过滤后的残差使用LSTM进行预测,最后对预测结果进行…☆84Updated 7 years ago
- Pytorch 实现RNN、LSTM、GRU模型☆81Updated 7 years ago
- Industry chain data test:Sentence classify Bi-GRU-att☆22Updated 7 years ago
- ☆166Updated 6 years ago
- ☆31Updated 6 years ago
- 不同时间序列预测方法对上海旅游规模进行预测☆19Updated 6 years ago
- 由时间空间成对组成的轨迹序列,通过循环神经网络lstm,自编码器auto-encode,时空密度聚类st-dbscan做异常检测☆74Updated 6 years ago
- BiLSTM 加普通Attention中文文本多分类Pytorch实现☆33Updated 4 years ago