napsternxg / Deepsequenceclassification
Licence: gpl-2.0
Deep neural network based model for sequence to sequence classification
Stars: ✭ 76
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Deepsequenceclassification
Neuronlp2
Deep neural models for core NLP tasks (Pytorch version)
Stars: ✭ 397 (+422.37%)
Mutual labels: deep-neural-networks, named-entity-recognition
Ner Lstm
Named Entity Recognition using multilayered bidirectional LSTM
Stars: ✭ 532 (+600%)
Mutual labels: deep-neural-networks, named-entity-recognition
Deeppavlov
An open source library for deep learning end-to-end dialog systems and chatbots.
Stars: ✭ 5,525 (+7169.74%)
Mutual labels: deep-neural-networks, named-entity-recognition
Deeplearning4j
All DeepLearning4j projects go here.
Stars: ✭ 68 (-10.53%)
Mutual labels: deep-neural-networks
Seq2annotation
基于 TensorFlow & PaddlePaddle 的通用序列标注算法库(目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和 IDCNN+CRF,更多算法正在持续添加中)实现中文分词(Tokenizer / segmentation)、词性标注(Part Of Speech, POS)和命名实体识别(Named Entity Recognition, NER)等序列标注任务。
Stars: ✭ 70 (-7.89%)
Mutual labels: named-entity-recognition
Sarcasm Detection
Detecting Sarcasm on Twitter using both traditonal machine learning and deep learning techniques.
Stars: ✭ 73 (-3.95%)
Mutual labels: deep-neural-networks
Swae
Implementation of the Sliced Wasserstein Autoencoders
Stars: ✭ 75 (-1.32%)
Mutual labels: deep-neural-networks
Satellite Image Deep Learning
Resources for deep learning with satellite & aerial imagery
Stars: ✭ 1,141 (+1401.32%)
Mutual labels: deep-neural-networks
Caffe2
Caffe2 is a lightweight, modular, and scalable deep learning framework.
Stars: ✭ 8,409 (+10964.47%)
Mutual labels: deep-neural-networks
Rnn Trajmodel
The source of the IJCAI2017 paper "Modeling Trajectory with Recurrent Neural Networks"
Stars: ✭ 72 (-5.26%)
Mutual labels: deep-neural-networks
Noreward Rl
[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning
Stars: ✭ 1,176 (+1447.37%)
Mutual labels: deep-neural-networks
Gluon2pytorch
Gluon to PyTorch deep neural network model converter
Stars: ✭ 70 (-7.89%)
Mutual labels: deep-neural-networks
Awesome System For Machine Learning
A curated list of research in machine learning system. I also summarize some papers if I think they are really interesting.
Stars: ✭ 1,185 (+1459.21%)
Mutual labels: deep-neural-networks
Blinkdl
A minimalist deep learning library in Javascript using WebGL + asm.js. Run convolutional neural network in your browser.
Stars: ✭ 69 (-9.21%)
Mutual labels: deep-neural-networks
Tfjs Core
WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.
Stars: ✭ 8,514 (+11102.63%)
Mutual labels: deep-neural-networks
Onnx Scala
An ONNX (Open Neural Network eXchange) API and Backend for Typeful, Functional Deep Learning in Scala
Stars: ✭ 68 (-10.53%)
Mutual labels: deep-neural-networks
Mit 6.s094
MIT-6.S094: Deep Learning for Self-Driving Cars Assignments solutions
Stars: ✭ 74 (-2.63%)
Mutual labels: deep-neural-networks
My Journey In The Data Science World
📢 Ready to learn or review your knowledge!
Stars: ✭ 1,175 (+1446.05%)
Mutual labels: deep-neural-networks
Cs231n
My Solution to Assignments of CS231n in Winter2016
Stars: ✭ 71 (-6.58%)
Mutual labels: deep-neural-networks
Channelnets
Tensorflow Implementation of ChannelNets (NeurIPS 18)
Stars: ✭ 73 (-3.95%)
Mutual labels: deep-neural-networks
Deep Sequence Classification
Generic library for training models for deep neural networks for text sequence classification tasks.
Usage:
-
Create a json file
config.json
(default name) using the template inconfig.json.sample
and specify the parameters for your training. -
Best strategy is to save the training and test files in vector format in advance and then give their paths in
data_vectors
parameter in the file. -
Train a model:
python model.py --config config_multitask.json --verbose 1
- Resume training from saved weights:
python model.py --config config_multitask.json --verbose 1 --weights output/models/model_multi_brnn_multitask_h2-45.h5 --base_epochs 45
Preprocessing:
- Currently, we support the preprocessing for the following file formats:
<ROOT><DOC>
<DOCNO> DOCUMENT 1 </DOCNO>
For <TIME TYPE="DATE:DATE">six years</TIME> , <ENTITY TYPE="PERSON">Shubhanshu A. B. Mishra</ENTITY> has made several programming projects after being inspired by <ENTITY TYPE="PERSON">Linus Torvalds</ENTITY>, a very renowned programmer.
</DOC></ROOT>
- Each file can contain multiple
DOCNO
. - The dir structure consists of many folders of data split for cross validation. It is as follows:
data/
data/CV_files
data/CV_files/1/file1.xml
data/CV_files/1/file2.xml
data/CV_files/1/file3.xml
...
data/CV_files/5/file1.xml
data/CV_files/5/file2.xml
Supports:
- Boundary and Category Detection
- Simple RNN and Bidirectional RNN
- Multi task sequence learning (Boundary + Category trained using same model)
- CNN + BRNN
Coming Up:
Use Cases:
- Named Entity Recognition
- POS Tagging
- Dependency Parsing
Author:
- Shubhanshu Mishra
Dependencies:
- Theano
- Keras
- BeautifulSoup (with lxml)
- numpy
- lxml (requires libxml2, libxslt and libxml2-dev)
Install theano and keras using the following commands:
pip install --user --upgrade --no-deps git+git://github.com/Theano/Theano.git
pip install --user --upgrade --no-deps git+git://github.com/fchollet/keras.git
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].