#tensorflow related work(nlp and image related, text classification, image caption, seq2seq..)
mainly tf work, may do some pytorch related
Notice some examples like text-classification will move to deepiu
##./deepiu
main application root
###./deepiu/image-caption
image-caption related work now support
discriminant method:
bow,
rnn,
cnn(TODO)
generative method:
show_and_tell
show_attend_and_tell(TODO)
Input with both image and text(TODO)
###./deepiu/text-sum
app with long text as input(like image title, ct0) and predict shortter summary text(like click query)
supporting method:
seq2seq
seq2seq_attetion
seq2seq_attetion_copy(TODO)
###./deepiu/seq2seq
common seq2seq codes used for image-caption, text-sum and other applications
###./deepiu/util
common util for deepiu
##./util
###./util/gezi
common lib
###./util/melt
common tensorflow related lib, you can view it similar as tf.contrib
####./util/melt/flow
like tf.supervisor, make train and test flow easier,
main functions include, application only make graph and pass train_ops and evaluate_ops to flow
flow will do model save, log save(auto add all one dimentional shape tensors to tensorboard), show elapsed time ...
- gezi ./util/gezi
- melt ./util/melt
- hasky ./util/hasky
- deepiu ./deepiu