#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import os
import dataloader as dd
from keras.optimizers import *
from keras.callbacks import *
itokens, otokens = dd.MakeS2SDict('en2de.s2s.examples.txt',
dict_file='en2de_word.txt')
print('seq 1 words:', itokens.num())
print('seq 2 words:', otokens.num())
from transformer import Transformer, LRSchedulerPerStep
d_model = 256
n_head = 4
s2s = Transformer(itokens, otokens, len_limit=500, d_model=d_model, d_inner_hid=1024, \
n_head=n_head, d_k=d_model//n_head, d_v=d_model//n_head, layers=3, dropout=0.1)
lr_scheduler = LRSchedulerPerStep(d_model, 4000)
model_saver = ModelCheckpoint('en2de.model.h5',
monitor='ppl',
save_best_only=True,
save_weights_only=True)
#s2s.model.summary()
import os, sys
import dataloader as dd
from keras.optimizers import *
from keras.callbacks import *
itokens, otokens = dd.MakeS2SDict('data/ara.txt',
dict_file='data/ara_word.txt')
Xtrain, Ytrain = dd.MakeS2SData('data/ara.txt',
itokens,
otokens,
h5_file='data/ara.h5')
Xvalid, Yvalid = dd.MakeS2SData('data/ara.txt',
itokens,
otokens,
h5_file='data/ara.valid.h5')
print('seq 1 words:', itokens.num())
print('seq 2 words:', otokens.num())
print('train shapes:', Xtrain.shape, Ytrain.shape)
print('valid shapes:', Xvalid.shape, Yvalid.shape)
'''
from rnn_s2s import RNNSeq2Seq
s2s = RNNSeq2Seq(itokens,otokens, 256)
s2s.compile('rmsprop')
s2s.model.fit([Xtrain, Ytrain], None, batch_size=64, epochs=30, validation_data=([Xvalid, Yvalid], None))
'''
from transformer import Transformer, LRSchedulerPerStep, LRSchedulerPerEpoch
d_model = 256
s2s = Transformer(itokens, otokens, len_limit=70, d_model=d_model, d_inner_hid=512, \
import os, sys
import dataloader as dd
from keras.optimizers import *
from keras.callbacks import *
itokens, otokens = dd.MakeS2SDict('data/en2de.s2s.txt', dict_file='data/en2de_word.txt')
Xtrain, Ytrain = dd.MakeS2SData('data/en2de.s2s.txt', itokens, otokens, h5_file='data/en2de.h5')
Xvalid, Yvalid = dd.MakeS2SData('data/en2de.s2s.valid.txt', itokens, otokens, h5_file='data/en2de.valid.h5')
print('seq 1 words:', itokens.num())
print('seq 2 words:', otokens.num())
print('train shapes:', Xtrain.shape, Ytrain.shape)
print('valid shapes:', Xvalid.shape, Yvalid.shape)
'''
from rnn_s2s import RNNSeq2Seq
s2s = RNNSeq2Seq(itokens,otokens, 256)
s2s.compile('rmsprop')
s2s.model.fit([Xtrain, Ytrain], None, batch_size=64, epochs=30, validation_data=([Xvalid, Yvalid], None))
'''
from transformer import Transformer, LRSchedulerPerStep, LRSchedulerPerEpoch
d_model = 256
s2s = Transformer(itokens, otokens, len_limit=70, d_model=d_model, d_inner_hid=512, \
n_head=4, d_k=64, d_v=64, layers=2, dropout=0.1)
mfile = 'models/en2de.model.h5'
lr_scheduler = LRSchedulerPerStep(d_model, 4000) # there is a warning that it is slow, however, it's ok.
#lr_scheduler = LRSchedulerPerEpoch(d_model, 4000, Xtrain.shape[0]/64) # this scheduler only update lr per epoch
#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import os
import dataloader as dd
from keras.optimizers import *
from keras.callbacks import *
itokens, otokens = dd.MakeS2SDict('pinyin.corpus.txt',
dict_file='pinyin_word.txt')
print('seq 1 words:', itokens.num())
print('seq 2 words:', otokens.num())
from transformer import Transformer, LRSchedulerPerStep
d_model = 256
n_head = 4
s2s = Transformer(itokens, otokens, len_limit=500, d_model=d_model, d_inner_hid=1024, \
n_head=n_head, d_k=d_model//n_head, d_v=d_model//n_head, layers=3, dropout=0.1)
lr_scheduler = LRSchedulerPerStep(d_model, 4000)
model_saver = ModelCheckpoint('pinyin.model.h5',
monitor='ppl',
save_best_only=True,
save_weights_only=True)
import os, sys
import dataloader as dd
from tensorflow.keras.optimizers import *
from tensorflow.keras.callbacks import *
itokens, otokens = dd.MakeS2SDict('data/pinyin.corpus.examples.txt',
dict_file='data/pinyin_word.txt')
print('seq 1 words:', itokens.num())
print('seq 2 words:', otokens.num())
from transformer import Transformer, LRSchedulerPerStep
d_model = 256
s2s = Transformer(itokens, otokens, len_limit=500, d_model=d_model, d_inner_hid=1024, \
n_head=4, layers=3, dropout=0.1)
mfile = 'models/pinyin.model.h5'
lr_scheduler = LRSchedulerPerStep(d_model, 4000)
model_saver = ModelCheckpoint(mfile,
monitor='ppl',
save_best_only=True,
save_weights_only=True)
#s2s.model.summary()
opt = Adam(0.001, 0.9, 0.98, epsilon=1e-9)
s2s.compile(opt)
try:
s2s.model.load_weights(mfile)
except:
