iamweiweishi

Results 23 issues of iamweiweishi

### Checklist - I have searched related issues but cannot get the expected help. - I have read related documents and don't know what to do. ### Describe the question...

你好,请问下如果需要做一个 可用的声纹识别模型用于verification(1:1),大概需要多大的数据量(ID数目,ID内的录音数目)?

According to my understanding, the weights of the trained model were not binarized directly. So, do I need to binarize the trained model with parameter 'scale' and then re-save the...

Hi, I have collected about 20000 images. And the HR-resolution is around 600*600. When the training starts, everything looks fine. After about 10000 iterations, the loss become larger and larger....

## Environment (Hardware) - Hardware: GPU. - Software: Ubuntu20.04. ## Project Name pj_tensorrt_seg_paddleseg_cityscapessota ## Issue Details I got a model with int32 output. And I added "#define TENSORTYPE_OUT TensorInfo::kTensorTypeInt32" as...

Thank you for your great work. Have you got some results, like WER on LibriSpeech? Many thanks. Best Regards

Prior to filing: check that this should be a bug instead of a feature request. Everything supported, including the compatible versions of TensorFlow, is listed in the overview page of...

bug

Thank you.

The face branch is not available now. Could you pls update the link or send me a copy of moon-loss? thank you

The raw gopro data are not in H5 format, so how to do this? Thank you.