cnn text classification pytorch Unduh - cnn text classification pytorch

cnn text classification pytorch

ular piton

1.0.0

Unduh

Perkenalan

Ini adalah implementasi jaringan saraf konvolusional Kim untuk makalah klasifikasi kalimat di Pytorch.

Implementasi model Kim di Theano: https://github.com/yoonkim/cnn_sentence
Denny Britz memiliki implementasi di TensorFlow: https://github.com/dennybritz/cnn-text-classification-tf
Implementasi Alexander Rakhlin di Keras; https://github.com/alexander-rakhlin/cnn-for-sentence-classification-in-keras

Persyaratan

Python 3
Pytorch> 0,1
Torchtext> 0.1
Numpy

Hasil

Saya baru saja mencoba dua dataset, Mr dan SST.

Dataset	Ukuran kelas	Hasil terbaik	Hasil Kertas Kim
TN	2	77,5%(CNN-Rand-statis)	76,1%(CNN-Rand-nostatik)
SST	5	37,2%(CNN-Rand-statis)	45,0%(CNN-Rand-nostatik)

Saya belum menyesuaikan hiper-parameter untuk SST dengan serius.

Penggunaan

 ./main.py -h

atau

 python3 main.py -h

Anda akan mendapatkan:

 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

Kereta

 ./main.py

Anda akan mendapatkan:

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

Tes

Jika Anda telah membangun set tes, Anda membuat pengujian seperti:

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

Opsi snapshot berarti dari mana model Anda memuat. Jika Anda tidak menetapkannya, model akan dimulai dari awal.

Meramalkan

Contoh1

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

Anda akan mendapatkan:

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

Contoh2

 ./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"

Anda akan mendapatkan:

 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

Teks Anda harus dipisahkan oleh ruang, bahkan tanda baca. Dan, teks Anda harus lebih lama dari ukuran kernel maks.