All Projects → bamtercelboo → Cnn Lstm Bilstm Deepcnn Clstm In Pytorch

bamtercelboo / Cnn Lstm Bilstm Deepcnn Clstm In Pytorch

Licence: apache-2.0
In PyTorch Learing Neural Networks Likes CNN(Convolutional Neural Networks for Sentence Classification (Y.Kim, EMNLP 2014) 、LSTM、BiLSTM、DeepCNN 、CLSTM、CNN and LSTM

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Cnn Lstm Bilstm Deepcnn Clstm In Pytorch

lmkit
language models toolkits with hierarchical softmax setting
Stars: ✭ 16 (-97.76%)
Mutual labels:  gru
Resnetcam Keras
Keras implementation of a ResNet-CAM model
Stars: ✭ 269 (-62.32%)
Mutual labels:  cnn-model
Baiduyun deeplearning competition
百度云魅族深度学习应用大赛
Stars: ✭ 393 (-44.96%)
Mutual labels:  gru
pytorch Highway Networks
Highway Networks implement in pytorch
Stars: ✭ 63 (-91.18%)
Mutual labels:  cnn-model
ms-convSTAR
[RSE21] Pytorch code for hierarchical time series classification with multi-stage convolutional RNN
Stars: ✭ 17 (-97.62%)
Mutual labels:  gru
Theano lstm
🔬 Nano size Theano LSTM module
Stars: ✭ 310 (-56.58%)
Mutual labels:  gru
CompareModels TRECQA
Compare six baseline deep learning models on TrecQA
Stars: ✭ 61 (-91.46%)
Mutual labels:  cnn-model
Evil
Optical Character Recognition in Swift for iOS&macOS. 银行卡、身份证、门牌号光学识别
Stars: ✭ 648 (-9.24%)
Mutual labels:  cnn-model
Pytorch-POS-Tagger
Part-of-Speech Tagger and custom implementations of LSTM, GRU and Vanilla RNN
Stars: ✭ 24 (-96.64%)
Mutual labels:  gru
Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (-48.6%)
Mutual labels:  gru
Deep-Learning-for-Expression-Recognition-in-Image-Sequences
The project uses state of the art deep learning on collected data for automatic analysis of emotions.
Stars: ✭ 26 (-96.36%)
Mutual labels:  gru
PyVGGFace
VGG-Face CNN descriptor in PyTorch.
Stars: ✭ 21 (-97.06%)
Mutual labels:  cnn-model
Deeptraffic
Deep Learning models for network traffic classification
Stars: ✭ 321 (-55.04%)
Mutual labels:  cnn-model
yolo-deepsort-flask
Target detection and multi target tracking platform based on Yolo DeepSort and Flask.
Stars: ✭ 29 (-95.94%)
Mutual labels:  cnn-model
Cryptocurrencyprediction
Predict Cryptocurrency Price with Deep Learning
Stars: ✭ 453 (-36.55%)
Mutual labels:  gru
dts
A Keras library for multi-step time-series forecasting.
Stars: ✭ 130 (-81.79%)
Mutual labels:  gru
Hands On Deep Learning Algorithms With Python
Master Deep Learning Algorithms with Extensive Math by Implementing them using TensorFlow
Stars: ✭ 272 (-61.9%)
Mutual labels:  gru
Captcha Tensorflow
Image Captcha Solving Using TensorFlow and CNN Model. Accuracy 90%+
Stars: ✭ 660 (-7.56%)
Mutual labels:  cnn-model
Nmt Keras
Neural Machine Translation with Keras
Stars: ✭ 501 (-29.83%)
Mutual labels:  gru
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (-50.28%)
Mutual labels:  cnn-model

Introduction

  • A classification task implement in pytorch, contains some neural networks in models.
  • Recenely, I've released the code.
    • old-version-17 release here
    • pytorch version == 0.3.1 release on here

Requirement

pyorch : 1.0.1
python : 3.6
torchtext: 0.2.1
cuda : 8.0 (support cuda speed up, can chose, default True)

Usage

modify the config file, see the Config directory(here) for detail.

1、python main.py
2、python main.py --config_file ./Config/config.cfg 
3、sh run.sh

Model

Contains some neural networks implement in pytorch, see the models for detail.

Data

SST-1 and SST-2.

Result

I haven't adjusted the hyper-parameters seriously, you can also see train log in here.

The following test set accuracy are based on the best dev set accuracy.

Data/Model % SST-1 % SST-2
CNN 46.1086 84.2943
Bi-LSTM 47.9186 86.3262
Bi-GRU 47.6923 86.7655

Reference

Question

  • if you have any question, you can open a issue or email [email protected]{gmail.com, 163.com}.

  • if you have any good suggestions, you can PR or email me.

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].