likejazz / Siamese Lstm
Siamese LSTM for evaluating semantic similarity between sentences of the Quora Question Pairs Dataset.
Stars: ✭ 217
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Siamese Lstm
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 (-18.89%)
Mutual labels: lstm
Screenshot To Code
A neural network that transforms a design mock-up into a static website.
Stars: ✭ 13,561 (+6149.31%)
Mutual labels: lstm
Speech Emotion Recognition
Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别
Stars: ✭ 181 (-16.59%)
Mutual labels: lstm
Lidc nodule detection
lidc nodule detection with CNN and LSTM network
Stars: ✭ 187 (-13.82%)
Mutual labels: lstm
Up Down Captioner
Automatic image captioning model based on Caffe, using features from bottom-up attention.
Stars: ✭ 195 (-10.14%)
Mutual labels: lstm
Machine Learning Is All You Need
🔥🌟《Machine Learning 格物志》: ML + DL + RL basic codes and notes by sklearn, PyTorch, TensorFlow, Keras & the most important, from scratch!💪 This repository is ALL You Need!
Stars: ✭ 173 (-20.28%)
Mutual labels: lstm
Stylenet
A cute multi-layer LSTM that can perform like a human 🎶
Stars: ✭ 187 (-13.82%)
Mutual labels: lstm
Icdar 2019 Sroie
ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction
Stars: ✭ 202 (-6.91%)
Mutual labels: lstm
Charades Algorithms
Activity Recognition Algorithms for the Charades Dataset
Stars: ✭ 181 (-16.59%)
Mutual labels: lstm
Datastories Semeval2017 Task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (-15.21%)
Mutual labels: lstm
Deepsleepnet
DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
Stars: ✭ 200 (-7.83%)
Mutual labels: lstm
Lstm anomaly thesis
Anomaly detection for temporal data using LSTMs
Stars: ✭ 178 (-17.97%)
Mutual labels: lstm
Graph convolutional lstm
Traffic Graph Convolutional Recurrent Neural Network
Stars: ✭ 210 (-3.23%)
Mutual labels: lstm
Deep Algotrading
A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading
Stars: ✭ 173 (-20.28%)
Mutual labels: lstm
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 (-11.52%)
Mutual labels: lstm
Sign Language Gesture Recognition
Sign Language Gesture Recognition From Video Sequences Using RNN And CNN
Stars: ✭ 214 (-1.38%)
Mutual labels: lstm
Tts Cube
End-2-end speech synthesis with recurrent neural networks
Stars: ✭ 213 (-1.84%)
Mutual labels: lstm
Chameleon recsys
Source code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (-6.91%)
Mutual labels: lstm
Siamese-LSTM
Using MaLSTM model(Siamese networks + LSTM with Manhattan distance) to detect semantic similarity between question pairs. Training dataset used is a subset of the original Quora Question Pairs Dataset(~363K pairs used).
It is Keras implementation based on Original Paper(PDF) and Excellent Medium Article.
Prerequisite
- Paper, Articles
- Data
- References
- aditya1503/Siamese-LSTM Original author's GitHub
- dhwajraj/deep-siamese-text-similarity TensorFlow based implementation
Kaggle's test.csv is too big, so I had extracted only the top 20 questions and created a file called test-20.csv and It is used in the predict.py.
You should put all data files to ./data directory.
How to Run
Training
$ python3 train.py
Predicting
It uses test-20.csv file mentioned above.
$ python3 predict.py
The Results
I have tried with various parameters such as number of hidden states of LSTM cell, activation function of LSTM cell and repeated count of epochs. I have used NVIDIA Tesla P40 GPU x 2 for training and 10% data was used as the validation set(batch size=1024*2). As a result, I have reached about 82.29% accuracy after 50 epochs about 10 mins later.
Epoch 50/50
363861/363861 [==============================] - 12s 33us/step - loss: 0.1172 - acc: 0.8486 - val_loss: 0.1315 - val_acc: 0.8229
Training time finished.
50 epochs in 601.24
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].