AI Rank
EN
← 开源
alexander-rakhlin

CNN-for-Sentence-Classification-in-Keras

Convolutional Neural Networks for Sentence Classification in Keras

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
593
Star
203
Fork
+0
本周
3
贡献者
创建于 2016-03-19 · 更新于 2026-09-16 · 今日第 16409 名
主要开发者
alexander-rakhlinandrewyatesShellbye

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 排名第 16,409，有 593 个星标。

同类别比较

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 排名第 16,409，此处有 8 个同类条目；fxia22/stn.pytorch 排名第 16,412。

同类别比较
名称排名指标
facebookresearch/FiD16,387
语言:
Python
星标数:
595
分叉数:
110
简介:
Fusion-in-Decoder
hirofumi0810/neural_sp16,388
语言:
Python
星标数:
595
分叉数:
132
简介:
End-to-end ASR/LM implementation with PyTorch
karpathy/pytorch-made16,390
语言:
Python
星标数:
595
分叉数:
93
简介:
MADE (Masked Autoencoder Density Estimation) implementation in PyTorch
miguelvr/dropblock16,393
语言:
Python
星标数:
595
分叉数:
95
简介:
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
fxia22/stn.pytorch16,412
语言:
Jupyter Notebook
星标数:
593
分叉数:
87
简介:
pytorch version of spatial transformer networks
timbmg/Sentence-VAE16,415
语言:
Python
星标数:
593
分叉数:
158
简介:
PyTorch Re-Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349
FluxML/FastAI.jl16,416
语言:
Julia
星标数:
592
分叉数:
49
简介:
Repository of best practices for deep learning in Julia, inspired by fastai
RingBDStack/SocialED16,420
语言:
Python
星标数:
592
分叉数:
45
简介:
A python library for social event detection
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数593
分叉数203
贡献者3
创建日期2016-03-19
更新日期2026-09-16
1 天星标数0
7 天星标数0
排名16,409
上次排名16,200
排名变化-209
7 天星标排名15,514
上次 7 天星标排名15,525
7 天星标排名变化11
总星标排名16,936
上次总星标排名16,909
总星标排名变化-27
README 摘录

Convolutional Neural Networks for Sentence Classification Train convolutional network for sentiment analysis. Based on "Convolutional Neural Networks for Sentence Classification" by Yoon Kim, link. Inspired by Denny Britz article "Implementing a CNN for Text Classification in TensorFlow", link. For "CNN-rand" and "CNN-non-static" gets to 88-90%, and "CNN-static" - 85% Some difference from original article: larger IMDB corpus, longer sentences; sentence length is very important, just like data size smaller embedding dimension, 20 instead of 300 2

filter sizes instead of original 3 much fewer filters; experiments show that 3-10 is enough; original work uses 100 random initialization is no worse than word2vec init on IMDB corpus sliding Max Pooling instead of original Global Pooling Dependencies The Keras Deep Learning library and most recent Theano backend should be installed. Not tested with TensorFlow, but should work.

常见问题

记录了多少星标和分叉？

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 有 593 个星标和 203 个分叉。

仓库排名是多少？

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 排名第 16,409。

记录的语言和类别是什么？

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 有 593 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras 与 fxia22/stn.pytorch 比较，后者排名第 16,412，有 593 个星标。

README

Convolutional Neural Networks for Sentence Classification

Train convolutional network for sentiment analysis. Based on "Convolutional Neural Networks for Sentence Classification" by Yoon Kim, link. Inspired by Denny Britz article "Implementing a CNN for Text Classification in TensorFlow", link. For "CNN-rand" and "CNN-non-static" gets to 88-90%, and "CNN-static" - 85%

Some difference from original article:

  • larger IMDB corpus, longer sentences; sentence length is very important, just like data size
  • smaller embedding dimension, 20 instead of 300
  • 2 filter sizes instead of original 3
  • much fewer filters; experiments show that 3-10 is enough; original work uses 100
  • random initialization is no worse than word2vec init on IMDB corpus
  • sliding Max Pooling instead of original Global Pooling

Dependencies

  • The Keras Deep Learning library and most recent Theano backend should be installed. You can use pip for that. Not tested with TensorFlow, but should work.
排名相邻
同类项目