Abhinav Garg comments

Results 16 comments of


                                            Abhinav Garg

Training two layer networks fails with gradient errors

I am facing the same problem.

acoustic_comp: the frame number of data stream lf0 is not consistent with others

Also the wav files must be of single channel i.e. mono waves

Error during step 2 of "02_prepare_labels.sh"

I got the ERROR [+2019] HCompV: Training data file name expected while running "02_prepare_labels.sh" and I have checked all the paths seems correct. The error is thrown at `check_call([HCompV, '-f',...

Error during step 2 of "02_prepare_labels.sh"

I copied the wave and text folders to the /merlin/egs/build_your_own_voice/s1/ directory and that seems to have resolved the issue

Error during step 2 of "02_prepare_labels.sh"

I also ended up with same error as @HandsomeDevilv112 ERROR [+7390] StepAlpha: Alpha prune failed sq(9) > qHi(8) at time 60116 FATAL ERROR - Terminating program ../merlin/tools/bin/htk/HERest Could it be...

Error during step 2 of "02_prepare_labels.sh"

Found some hints to resolve this issue: https://firojalam.wordpress.com/2014/01/23/herest-error-7390-stepalpha-alpha-prune-failed/ https://stackoverflow.com/questions/5463645/htk-herest-issue

Error during step 2 of "02_prepare_labels.sh"

I am stuck at hmm training step since more than half a day now. Any ideas how can I get the status of the training like usually some kind of...

Yolo returns uniformly placed detections (bboxes) with almost equal confidence.

@AlexeyAB Can I compile your version of yolo using Visual Studio 2012? I tried with VS2012 and I have changed include and library paths to my opencv 3.0.0 and CUDA...

Yolo returns uniformly placed detections (bboxes) with almost equal confidence.

the training was working but the trained weights file have some issues. It can not be re-used for further training. I cant remember if it was working for test. I...

Yolo returns uniformly placed detections (bboxes) with almost equal confidence.

I feel it has something to do with the way file is being written over windows. Most probably there is something wrong happening there. I remember trying different forks for...