icoxfog417 / Tensorflow_qrnn
Licence: mit
QRNN implementation for TensorFlow
Stars: ✭ 241
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Tensorflow qrnn
Reside
EMNLP 2018: RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
Stars: ✭ 222 (-7.88%)
Mutual labels: natural-language-processing
Wordgcn
ACL 2019: Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Stars: ✭ 230 (-4.56%)
Mutual labels: natural-language-processing
Chazutsu
The tool to make NLP datasets ready to use
Stars: ✭ 238 (-1.24%)
Mutual labels: natural-language-processing
Spacy Api Docker
spaCy REST API, wrapped in a Docker container.
Stars: ✭ 222 (-7.88%)
Mutual labels: natural-language-processing
Machine Learning Resources
A curated list of awesome machine learning frameworks, libraries, courses, books and many more.
Stars: ✭ 226 (-6.22%)
Mutual labels: natural-language-processing
Spacy Services
💫 REST microservices for various spaCy-related tasks
Stars: ✭ 230 (-4.56%)
Mutual labels: natural-language-processing
Dilated Cnn Ner
Dilated CNNs for NER in TensorFlow
Stars: ✭ 222 (-7.88%)
Mutual labels: natural-language-processing
Cmrc2018
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
Stars: ✭ 238 (-1.24%)
Mutual labels: natural-language-processing
Pytorch Transformers Classification
Based on the Pytorch-Transformers library by HuggingFace. To be used as a starting point for employing Transformer models in text classification tasks. Contains code to easily train BERT, XLNet, RoBERTa, and XLM models for text classification.
Stars: ✭ 229 (-4.98%)
Mutual labels: natural-language-processing
Pytorch Bert Crf Ner
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Stars: ✭ 236 (-2.07%)
Mutual labels: natural-language-processing
Catalyst
Accelerated deep learning R&D
Stars: ✭ 2,804 (+1063.49%)
Mutual labels: natural-language-processing
Catalyst
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Stars: ✭ 224 (-7.05%)
Mutual labels: natural-language-processing
Deepnlp Models Pytorch
Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)
Stars: ✭ 2,760 (+1045.23%)
Mutual labels: natural-language-processing
Machine Learning Notebooks
Machine Learning notebooks for refreshing concepts.
Stars: ✭ 222 (-7.88%)
Mutual labels: natural-language-processing
Pykakasi
NLP: Convert Japanese Kana-kanji sentences into Kana-Roman in simple algorithm.
Stars: ✭ 238 (-1.24%)
Mutual labels: natural-language-processing
Bert4doc Classification
Code and source for paper ``How to Fine-Tune BERT for Text Classification?``
Stars: ✭ 220 (-8.71%)
Mutual labels: natural-language-processing
Prodigy Recipes
🍳 Recipes for the Prodigy, our fully scriptable annotation tool
Stars: ✭ 229 (-4.98%)
Mutual labels: natural-language-processing
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+1231.54%)
Mutual labels: natural-language-processing
Malaya
Natural Language Toolkit for bahasa Malaysia, https://malaya.readthedocs.io/
Stars: ✭ 239 (-0.83%)
Mutual labels: natural-language-processing
Mitie
MITIE: library and tools for information extraction
Stars: ✭ 2,693 (+1017.43%)
Mutual labels: natural-language-processing
Tensorflow QRNN
QRNN implementation for TensorFlow. Implementation refer to below blog.
New neural network building block allows faster and more accurate text understanding
Dependencies
- TensorFlow: 0.12.0
- scikit-learn: 0.18.1 (for working check)
How to run
Forward Test
To confirm forward propagation, run below script.
python test_tf_qrnn_forward.py
Working Check
To confirm the performance of QRNN compare with baseline(LSTM), run below script. Dataset is scikit-learn's digit dataset.
python test_tf_qrnn_work.py
You can check the calculation result by TensorBoard.
For example.
tensorboard --logdir=./summary/qrnn
Experiments
Baseline(LSTM) Working check
Iter 0: loss=2.473149299621582, accuracy=0.1171875
Iter 100: loss=0.31235527992248535, accuracy=0.921875
Iter 200: loss=0.1704500913619995, accuracy=0.9453125
Iter 300: loss=0.0782063901424408, accuracy=0.9765625
Iter 400: loss=0.04097321629524231, accuracy=1.0
Iter 500: loss=0.023687714710831642, accuracy=0.9921875
Iter 600: loss=0.07718617469072342, accuracy=0.9765625
Iter 700: loss=0.02005828730762005, accuracy=0.9921875
Iter 800: loss=0.006271282210946083, accuracy=1.0
Iter 900: loss=0.007853344082832336, accuracy=1.0
Testset Accuracy=0.9375
takes 15.83749008178711 seconds.
QRNN Working check
Iter 0: loss=6.942812919616699, accuracy=0.0703125
Iter 100: loss=1.6366937160491943, accuracy=0.59375
Iter 200: loss=0.7058627605438232, accuracy=0.796875
Iter 300: loss=0.3940553069114685, accuracy=0.8984375
Iter 400: loss=0.2623080909252167, accuracy=0.9375
Iter 500: loss=0.3940059542655945, accuracy=0.921875
Iter 600: loss=0.1395827978849411, accuracy=0.96875
Iter 700: loss=0.11944477260112762, accuracy=0.984375
Iter 800: loss=0.1389300674200058, accuracy=0.9765625
Iter 900: loss=0.09582504630088806, accuracy=0.96875
Testset Accuracy=0.9140625
takes 13.540465116500854 seconds.
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].