STgram-MFN
STgram-MFN copied to clipboard
A spectro-temporal fusion feature, STgram, with MobileFaceNet For more stable Anomalous Sound Detection
Snyk has created this PR to fix one or more vulnerable packages in the `pip` dependencies of this project. #### Changes included in this PR - Changes to the following...
May I ask why the num_class in the config file is 41 and what does this parameter do? thanks~
I find that the function which named "def log_mel_spect_to_vector" is not used. Did you just use MelSpectrogram?
> `Exception in user code: ------------------------------------------------------------ Traceback (most recent call last): File "/workspace/private/user-dataset-245759/envs/research/lib/python3.8/site-packages/urllib3/connection.py", line 174, in _new_conn conn = connection.create_connection( File "/workspace/private/user-dataset-245759/envs/research/lib/python3.8/site-packages/urllib3/util/connection.py", line 95, in create_connection raise err File "/workspace/private/user-dataset-245759/envs/research/lib/python3.8/site-packages/urllib3/util/connection.py",...
我下载好已经训练好的模型后不知道如何处理  
大佬,您好!我想请问一下,如果我只想识别id=00的正常声音和异常声音,那么我的num_class应该设置成多少?
你好,我想要把数据集替换成自己制作的数据集,但是他告诉我数据集有问题。如果您了解的话,能麻烦您告诉我一下这个数据集应该如何制作吗
Your paper stated that "The model is trained with 200 epochs". However, the config.yml file specified 300 epochs. Which one is correct? Thanks,