jongwook/onsets-and-frames

Issues

• Missing Sigmoid when calculating BCE loss / Activation function during inference

  #35 opened 10 months ago by guozixunnicolas
  1

• Stucked on 0%

  #32 opened 2 years ago by BisratGetnet
  2

• If only the onset dataset is trained, how accurate will it be

  #34 opened 2 years ago by water202232
  0

• If only the onset dataset is trained, how accurate will it be

  #33 opened 2 years ago by water202232
  0

• Suggest to loosen the dependency on sacred

  #31 opened 2 years ago by Agnes-U
  0

• results when replicate the code following Onsets and Frames: Dual-Objective Piano Transcription

  #28 opened 3 years ago by Dream-High
  3

• Training method enquiry and evaluation issue

  #29 opened 3 years ago by marypilataki
  1

• Checkpoint and possible fine-tuning on a custom dataset

  #23 opened 4 years ago by adrienchaton
  12

• RuntimeError: Tensor stacks

  #27 opened 3 years ago by SashaBurashnikova
  0

• Why is there a need for Torch implementation of STFT and MelSpectrogram?

  #16 opened 5 years ago by brihijoshi
  1

• Kouretchian

  #26 opened 4 years ago by mkouretchian
  1

• Gradient clipping in the wrong place?

  #24 opened 4 years ago by KinWaiCheuk
  1

• delete

  #22 opened 4 years ago by adrienchaton
  0

• Error while trying to retrain the model with MAPS dataset

  #20 opened 4 years ago by carlosholivan
  2

• RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

  #21 opened 4 years ago by ChekeLee
  1

• Expected results?

  #4 opened 5 years ago by brianc118
  20

• Linter/formatter?

  #19 opened 5 years ago by brianc118
  2

• Upload pretrained model to run inference

  #17 opened 5 years ago by greenbech
  3

• How to run inference on single wav file?

  #15 opened 5 years ago by GomuGomuGo
  6

• What is the reason of reading audio as int16 instead of float?

  #14 opened 5 years ago by KinWaiCheuk
  1

• Many warnings during training

  #10 opened 5 years ago by KinWaiCheuk
  3

• Is it possible to implement weighted frame loss?

  #13 opened 5 years ago by KinWaiCheuk
  1

• Discarding the last sample point from the audio?

  #12 opened 5 years ago by KinWaiCheuk
  1

• How are tsv files created?

  #11 opened 5 years ago by KinWaiCheuk
  1

• Subtract - not supported for PyTorch 1.3.1

  #9 opened 5 years ago by kme2698
  3

• Onset length as per the onset frames paper

  #6 opened 5 years ago by falaktheoptimist
  1

• Converting midi to txt

  #3 opened 6 years ago by andrei4b
  1

• Can this project convert wav format files into mid files?

  #2 opened 6 years ago by zhaoyuhsin
  4

• Errors in mir_eval library

  #1 opened 6 years ago by yuanshenli
  4