Josef

Results 5 comments of Josef
trafficstars

Face Training Time Too Long

I' training the model on celebA data and it takes about 12 minutes for a single epoch I have GeForce GTX 1050 4GB

Question: how to integrate RNNLM into speech2text ctc with lm decoder?

I think one of the ways is to extend the method _compute_loss inside MultiTaskCTCEntropyLoss class with RNNLM loss

for key in ['met','params','layers']: assert key in mcn.keys()

@albanie, can you please share the versions of the libs you are using? scipy and etc. EDIT: Ok I managed out how to fix it: replace lines 49-54 with this...

Re-train by using the ckeckpoint

Hi, If I stop my training and re-run from the latest checkpoint the bleu score for dev/test sets is increased. What is the reason for that? Should I update the...

get alignments using attention

Hi @kmario23 , Have you solved it? Thanks