indiejoseph / Doc Han Att
Hierarchical Attention Networks for Chinese Sentiment Classification
Stars: ✭ 206
Projects that are alternatives of or similar to Doc Han Att
Pytorch Seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+1559.22%)
Mutual labels: jupyter-notebook, rnn, attention
Tensorflow2 Docs Zh
TF2.0 / TensorFlow 2.0 / TensorFlow2.0 官方文档中文版
Stars: ✭ 177 (-14.08%)
Mutual labels: document, jupyter-notebook, rnn
Chinese Chatbot
中文聊天机器人，基于10万组对白训练而成，采用注意力机制，对一般问题都会生成一个有意义的答复。已上传模型，可直接运行，跑不起来直播吃键盘。
Stars: ✭ 124 (-39.81%)
Mutual labels: jupyter-notebook, rnn, attention
Attentive Neural Processes
implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
Stars: ✭ 33 (-83.98%)
Mutual labels: jupyter-notebook, rnn, attention
Rnn For Joint Nlu
Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (-14.56%)
Mutual labels: jupyter-notebook, rnn, attention
Machine Learning
My Attempt(s) In The World Of ML/DL....
Stars: ✭ 78 (-62.14%)
Mutual labels: jupyter-notebook, rnn, attention
Multihead Siamese Nets
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
Stars: ✭ 144 (-30.1%)
Mutual labels: jupyter-notebook, attention
Hey Jetson
Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.
Stars: ✭ 161 (-21.84%)
Mutual labels: jupyter-notebook, attention
Char Rnn Pytorch
使用PyTorch实现Char RNN生成古诗和周杰伦的歌词
Stars: ✭ 114 (-44.66%)
Mutual labels: jupyter-notebook, rnn
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (-22.33%)
Mutual labels: jupyter-notebook, rnn
Attentionn
All about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.
Stars: ✭ 175 (-15.05%)
Mutual labels: jupyter-notebook, attention
Linear Attention Recurrent Neural Network
A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)
Stars: ✭ 119 (-42.23%)
Mutual labels: jupyter-notebook, rnn
Nlp Models Tensorflow
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
Stars: ✭ 1,603 (+678.16%)
Mutual labels: jupyter-notebook, attention
Stylenet
A cute multi-layer LSTM that can perform like a human 🎶
Stars: ✭ 187 (-9.22%)
Mutual labels: jupyter-notebook, rnn
Graph attention pool
Attention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)
Stars: ✭ 186 (-9.71%)
Mutual labels: jupyter-notebook, attention
Char Rnn Chinese
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
Stars: ✭ 192 (-6.8%)
Mutual labels: chinese, rnn
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-5.34%)
Mutual labels: jupyter-notebook, rnn
Ml Ai Experiments
All my experiments with AI and ML
Stars: ✭ 107 (-48.06%)
Mutual labels: jupyter-notebook, rnn
Hierarchical Attention Networks for Chinese Sentiment Classification
This is HAN version of sentiment classification, with pre-trained character-level embedding, and used RAN instead of GRU.
Dataset
Downloaded from internet but i forget where is it ;p, the original dataset is in Simplified Chinese, i used opencc translated it into Traditional Chinese. After 100 epochs, the valid accuracy achieved 96.31%
Requirement
Tensorflow r1.1+
Attention Heatmap
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].