chinese_text_cnn
1.0.0
Réseaux de neurones convolutionnels pour la classification des phrases
https://github.com/embdding/chinese-word- vecteurs
(Le mot word2vec formé par zhihu_qa dans zhihu Q&A)
python3 main.py -hpython3 main.py python main.py Batch[1800] - loss: 0.009499 acc: 100.0000%(128/128)
Evaluation - loss: 0.000026 acc: 94.0000%(6616/7000)
early stop by 1000 steps, acc: 94.0000%
python main.py -static=true Batch[1900] - loss: 0.011894 acc: 100.0000%(128/128)
Evaluation - loss: 0.000018 acc: 95.0000%(6679/7000)
early stop by 1000 steps, acc: 95.0000%
python main.py -static=true -non-static=true Batch[1500] - loss: 0.008823 acc: 99.0000%(127/128))
Evaluation - loss: 0.000016 acc: 96.0000%(6729/7000)
early stop by 1000 steps, acc: 96.0000%
python main.py -static=true -non-static=true -multichannel=true Batch[1500] - loss: 0.023020 acc: 98.0000%(126/128))
Evaluation - loss: 0.000016 acc: 96.0000%(6744/7000)
early stop by 1000 steps, acc: 96.0000%