yeyupiaoling/AudioClassification-Pytorch

Issues

• 跑多卡训练死机

  #33 opened 3 months ago by rookie0607
  1

• 是否可以分享下其他音频特征处理代码

  #32 opened 3 months ago by karryor
  1

• 是否需要统一特征长度？

  #31 opened 3 months ago by AICVHub
  1

• 模型训练完之后，如何使用onnxruntime部署？

  #30 opened 3 months ago by AICVHub
  4

• eval.py结果与测试集上使用predict得到的结果不相同

  #29 opened 3 months ago by gaoxc315
  1

• 做歌曲分类的话能有效果吗

  #27 opened 5 months ago by tingyuyan
  3

• cuda一定要使用11.6吗？安装CUDA 12.1后训练报错

  #28 opened 6 months ago by fangg2024
  1

• 如何提交并发量和减少cpu的资源

  #26 opened 8 months ago by tuocheng0824
  1

• 推理速度

  #7 opened 2 years ago by SSTato
  4

• 如何分类一个10毫秒左右的音频

  #25 opened 10 months ago by guijuzhejiang
  3

• can flac format be used as dataset

  #23 opened a year ago by huangp0600
  3

• RuntimeWarning when train

  #24 opened a year ago by huangp0600
  1

• How to detect and classify multiple sound at the same time?

  #22 opened a year ago by iotproductions
  2

• 自选数据集训练报错

  #21 opened a year ago by Fatcat688
  3

• Fixing A Broken Link

  #19 opened a year ago by shmuel44
  0

• 训练完成后，UrbanSound8K测试集的准确率可以达到多少

  #18 opened a year ago by PanJinquan
  2

• .

  #17 opened 2 years ago by wa1tzy
  0

• KeyError: 'n_mfcc'

  #16 opened 2 years ago by ben-8878
  2

• 没有 PANNS 模型

  #15 opened 2 years ago by tuxiaobei-scu
  2

• 预训练模型

  #14 opened 2 years ago by fuguanyu
  1

• Multi-gpu training RuntimeError

  #13 opened 2 years ago by JxuHenry
  0

• How to run with features MFCC

  #12 opened 2 years ago by JxuHenry
  2

• A same torchaudio warning issued repeatedly in trainning and infering

  #11 opened 2 years ago by sywee
  2

• 配置文件中的数据预处理参数有问题， feature_method: 'Spectrogram'，报错，参数解析有问题

  #10 opened 2 years ago by zsffuture
  3

• 训练自己的数据集

  #9 opened 2 years ago by SSTato
  4

• 训练次数

  #8 opened 2 years ago by SSTato
  10

• 这个训练出来的模型可以移植到嵌入式设备中使用吗

  #6 opened 2 years ago by 1191658517
  1

• 数据集里没有train_list.txt 和test_list.txt

  #5 opened 2 years ago by MARUIHAN123
  1

• learning

  #4 opened 2 years ago by sinofs
  1

• 您好， 利用音频分类方法能把一段语音中想要的语音字段能给分出来嘛

  #3 opened 3 years ago by zqlsnr
  1

• StepLr

  #2 opened 3 years ago by vodanhbk95
  1

• RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

  #1 opened 3 years ago by Bill-JLN
  7