Problems about nnets_model

[Lyu T]

When I try to reperform synthesis, I get this error: No such file or directory: ‘/Users/s1521115/Documents/ss_dnn/nnets_model/DNN_TANH_TANH_TANH_TANH_TANH_TANH_LINEAR__mgc_lf0_vuv_bap_0_6_1024_1024_1024_1024_1024_1024_330.199.train.30.0.004000.rnn.model’.
Actually, there is no file in the directory of nnets_model now but the steps before synthesis can run.

Anything I can handle it?

Thanks!

[Srikanth R]

Can you write in detailed what other steps were you able to run other than synthesis?

DNNGEN or MCD calculation?

[Lyu T]

I failed in DNNGEN and GENWAV and got this error. However, I read the code runlstm.py and found that the net model should be generated in feature composition and normalisation. Actually, I can run the code when I set NORMCMP and TRAINDNN as True. Is something wrong?

[Simon]

If there is no trained model, then check that you have actually run that stage:

TRAINDNN : True

[Lyu T]

I am sure I have run the stage. I can generate the model when I run the code run_dnn.py but cannot get the model when I run run_lstm.py at the stage of TrainDNN.

[Simon]

Do you get any error message?

[Lyu T]

No error and I can get the value of validation loss for each epoch.

[Simon]

Have you run out of disk quota (are you working on DICE or the iMacs)?

[Lyu T]

I am afraid not and I am working on the iMac.

[Srikanth R]

check for a if condition,which says “save the model only after epoch 5”. comment out that line thereby enabling save model at every epoch.

if epoch > 5: ## comment this line and use small learning rate.

Also, can you paste the validation and training errors somewhere in pastebin and give the link here.

[Author]

Posts