keunwoochoi/music-auto_tagging-keras

Issues

• Cannot use CRNN with Theano backend

  #33 opened 7 years ago by franciscoaraposo
  27

• ValueError: Input dimension mis-match.

  #48 opened 4 years ago by byeolkady
  1

• compact cnn에서 tag추출하기 위한 pretrained model을 구할 수 있나요?

  #47 opened 4 years ago by wjy5446
  0

• Having trouble running the compact CNN model

  #46 opened 4 years ago by sohrabkhanbadr
  1

• I think the weight file for cnn_tensorflow is not the correct file.

  #42 opened 6 years ago by nimahamidi
  2

• too many syntax error in, say compact cnn

  #45 opened 5 years ago by wubinbai
  1

• Can i use MusicTaggerCRNN for extract feature from another feature audio like chromagram not mel-spectrogram?

  #44 opened 5 years ago by trangtv57
  1

• parameter problem

  #7 opened 8 years ago by gongqiang
  2

• FCN-4 Convolve problem

  #43 opened 5 years ago
  7

• Dockerfile for run experiments

  #41 opened 6 years ago by fitolobo
  1

• How did you get the actual mp3s ?

  #39 opened 6 years ago by gauthsvenkat
  1

• the npy for mp3 is not the same with the logamplitude melspectrogram I got using the code audio_processor.py

  #40 opened 6 years ago by lorashen
  1

• sound file duration

  #38 opened 6 years ago by zzstefan
  1

• Filters kernel

  #37 opened 6 years ago by gdf47
  1

• No backend error

  #35 opened 7 years ago by DAKSHSEMWAL
  2

• Please provide crnn training example

  #34 opened 7 years ago by Vital95
  2

• How to use compact_cnn for tagging?

  #30 opened 7 years ago by AmberLau
  1

• Can't run any of models with the latest python packages

  #21 opened 7 years ago by nartes
  4

• How do I train my CNN with my own dataset

  #20 opened 7 years ago by mv00147
  4

• Music similarity using music-auto_tagging for feature extraction

  #17 opened 7 years ago by srinidhikrs
  2

• Low AUC for MTT

  #18 opened 7 years ago by Rashmeet09
  6

• Epochs on MTT experiment

  #24 opened 7 years ago by rasikapawar12
  1

• compact cnn how to obtain the dominant tags ?

  #32 opened 7 years ago by emmanuelbernieri
  10

• problem with the model generation

  #31 opened 7 years ago by emmanuelbernieri
  4

• Why this error happens? -Input dimension mis-match

  #22 opened 8 years ago by exeex
  3

• Preview Audio files for training

  #29 opened 7 years ago by techscientist
  4

• Suggestion needed

  #26 opened 7 years ago by lvaleriu
  14

• What was the GPU that you used to train your model??

  #27 opened 7 years ago by kshitijchandna
  3

• Input file data shape of .npy file in compact_cnn

  #23 opened 8 years ago by exeex
  7

• Compact cnn training precision

  #28 opened 8 years ago by lvaleriu
  5

• Keras 2.0

  #25 opened 8 years ago by lvaleriu
  3

• Input dimension mismatch

  #16 opened 8 years ago by mv00147
  12

• No Normalization2D for compact_cnn?

  #19 opened 8 years ago by as641651
  1

• audio_processor.py bug

  #11 opened 8 years ago by dojochu
  1

• Audioread module

  #14 opened 8 years ago by mv00147
  3

• h5py error

  #15 opened 8 years ago by mv00147
  1

• Wrong Prediction with GTZAN Music Genre Dataset

  #12 opened 8 years ago by srinidhikrs
  1

• issue related to cost function

  #13 opened 8 years ago by sushien
  1

• Further elaboration on Permute/Reshape for CNN/RNN stack

  #9 opened 8 years ago by faroit
  9

• small error with argument 'by_name'

  #10 opened 8 years ago by fortunto2
  2

• Loss function and Optimizer

  #8 opened 8 years ago by jayavanth
  3

• Reproduce and how to avoid overfitting

  #6 opened 8 years ago by NickCJ83
  1

• what is the 29.1 file of million song?

  #5 opened 8 years ago by SeekPoint
  8

• Shapes are not compatible

  #2 opened 8 years ago by pribadihcr
  2

• Value Error

  #1 opened 8 years ago by crosofg
  7

• Weights shape for CRNN for TF are incorrect

  #4 opened 8 years ago by meetps
  1