Yu Wu (吴俣) MarkWuNLP
jamiew
/ google_twunter_lol
Created
July 28, 2011 20:34
All the dirty words from Google's "what do you love" project: http://www.wdyl.com/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| easterEgg.BadWorder.list={ | |
| "4r5e":1, | |
| "5h1t":1, | |
| "5hit":1, | |
| a55:1, | |
| anal:1, | |
| anus:1, | |
| ar5e:1, | |
| arrse:1, | |
| arse:1, |
entron
/ imdb_cnn_kim_small_embedding.py
Last active
September 16, 2023 16:23
Keras implementation of Kim's paper "Convolutional Neural Networks for Sentence Classification" with a very small embedding size. The test accuracy is 0.853.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| '''This scripts implements Kim's paper "Convolutional Neural Networks for Sentence Classification" | |
| with a very small embedding size (20) than the commonly used values (100 - 300) as it gives better | |
| result with much less parameters. | |
| Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_cnn.py | |
| Get to 0.853 test accuracy after 5 epochs. 13s/epoch on Nvidia GTX980 GPU. | |
| ''' | |
| from __future__ import print_function |