divamgupta / attention-translation-keras Goto Github PK

I followed the exact commands mentioned in your readme and before training i am getting the following errors

ValueError: Error when checking target: expected time_distributed_1 to have 3 dimensions, but got array with shape (1120, 40005)

Facing error while trying to create the preprocess data

python prep_data.py --text_A="data/parallel/IITB.en-hi.en" --text_B="data/parallel/IITB.en-hi.hi" --out_file="./data/nmt_hi_en_prepped.h5"
C:\Users\f.fernandes\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_init_.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "prep_data.py", line 16, in
eng_sents = (open( args.text_A ).read()).split("\n")[:-1]
File "C:\Users\f.fernandes\AppData\Local\Programs\Python\Python36\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 38387: character maps to

After modifying the files by adding encoding now faced with a new error
eng_sents = (open( args.text_A, encoding="utf8").read()).split("\n")[:-1]
hi_sents = (open( args.text_B, encoding="utf8").read()).split("\n")[:-1]

C:\F.Fernandes_DND_30Oct_Sidhartha\Francisco\Keras\data\attention-translation-keras-master>python prep_data.py --text_A="data/parallel/IITB.en-hi.en" --text_B="data/parallel/IITB.en-hi.hi" --out_file="./data/nmt_hi_en_prepped.h5"
C:\Users\f.fernandes\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_init_.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "prep_data.py", line 33, in
eng_sent_mat = getSentencesMat( eng_sents ,en_vocab , startEndTokens=True , tokenizer_fn=lambda x:x.split(' ') , maxSentenceL=100 )
File "C:\F.Fernandes_DND_30Oct_Sidhartha\Francisco\Keras\data\attention-translation-keras-master\utils.py", line 114, in getSentencesMat
tokenised = [ tokenise(s , startEndTokens=startEndTokens ,tokenizer_fn=tokenizer_fn ) for s in sentences ]
File "C:\F.Fernandes_DND_30Oct_Sidhartha\Francisco\Keras\data\attention-translation-keras-master\utils.py", line 114, in
tokenised = [ tokenise(s , startEndTokens=startEndTokens ,tokenizer_fn=tokenizer_fn ) for s in sentences ]
MemoryError

I was searching attention model implementation in keras. I have found your one. Can you tell me where did you get this implementation of attention model ?

Hi Divam

How much time it takes to train and i have train it as it is and when making predictions giving a empty response for the same query "This is red".
I have one query

for ep in range( 100 ):
print ("Epoch" , ep)
m.fit_generator( tr_gen , steps_per_epoch=1000 , epochs=1 )
m.save_weights( args.weights_path + "." + str(ep) )
m.save_weights( args.weights_path )
what is ep,epochs,steps_per_epoch
denotes here
is it training on 1 epoch only

Thank you for the code. New to this area so I'm finding it difficult to understand these terminologies.
Can you help by providing /suggesting a way to visualize the attention weights.