cnn text classification pytorch下載-CNN cnn text classification pytorch源代碼下載

cnn text classification pytorch

Python

1.0.0

下載

介紹

這是Kim在Pytorch中用於句子分類論文的捲積神經網絡的實施。

金在Theano中的模型實施：https：//github.com/yoonkim/cnn_sentence
丹尼·布里茲（Denny Britz
亞歷山大·拉克林（Alexander Rakhlin）在Keras的實施； https://github.com/alexander-rakhlin/cnn-for-sentence-classification-in-keras

要求

Python 3
pytorch> 0.1
火炬> 0.1
numpy

結果

我只是嘗試了兩個數據集，MR和SST。

數據集	班級大小	最好的結果	金的論文結果
先生	2	77.5％（CNN-Rand靜態）	76.1％（CNN-Rand-Nostatic）
SST	5	37.2％（CNN-Rand靜態）	45.0％（CNN-Rand-Nostatic）

我沒有認真對待SST的超參數。

用法

 ./main.py -h

或者

 python3 main.py -h

您會得到：

 CNN text classificer

optional arguments:
  -h, --help            show this help message and exit
  -batch-size N         batch size for training [default: 50]
  -lr LR                initial learning rate [default: 0.01]
  -epochs N             number of epochs for train [default: 10]
  -dropout              the probability for dropout [default: 0.5]
  -max_norm MAX_NORM    l2 constraint of parameters
  -cpu                  disable the gpu
  -device DEVICE        device to use for iterate data
  -embed-dim EMBED_DIM
  -static               fix the embedding
  -kernel-sizes KERNEL_SIZES
                        Comma-separated kernel size to use for convolution
  -kernel-num KERNEL_NUM
                        number of each kind of kernel
  -class-num CLASS_NUM  number of class
  -shuffle              shuffle the data every epoch
  -num-workers NUM_WORKERS
                        how many subprocesses to use for data loading
                        [default: 0]
  -log-interval LOG_INTERVAL
                        how many batches to wait before logging training
                        status
  -test-interval TEST_INTERVAL
                        how many epochs to wait before testing
  -save-interval SAVE_INTERVAL
                        how many epochs to wait before saving
  -predict PREDICT      predict the sentence given
  -snapshot SNAPSHOT    filename of model snapshot [default: None]
  -save-dir SAVE_DIR    where to save the checkpoint

火車

 ./main.py

您會得到：

 Batch[100] - loss: 0.655424  acc: 59.3750%
Evaluation - loss: 0.672396  acc: 57.6923%(615/1066)

測試

如果您的測試集構造了，則進行測試：

 /main.py -test -snapshot="./snapshot/2017-02-11_15-50-53/snapshot_steps1500.pt

快照選項表示您的模型加載位置。如果您不分配它，則該模型將從從頭開始。

預測

示例1

 ./main.py -predict="Hello my dear , I love you so much ." 
           -snapshot="./snapshot/2017-02-11_15-50-53/snapshot_steps1500.pt"

您會得到：

 Loading model from [./snapshot/2017-02-11_15-50-53/snapshot_steps1500.pt]...
 
 [Text]  Hello my dear , I love you so much .
 [Label] positive

示例2

 ./main.py -predict="You just make me so sad and I have to leave you ."
           -snapshot="./snapshot/2017-02-11_15-50-53/snapshot_steps1500.pt"

您會得到：

 Loading model from [./snapshot/2017-02-11_15-50-53/snapshot_steps1500.pt]...
 
 [Text]  You just make me so sad and I have to leave you .
 [Label] negative

您的文本必須用空間，甚至標點符號分隔。並且，您的文本應更長的時間更長的最大內核大小。