Hao Zhuang

有没有单纯支持数字的pinyin，输出。比如上面说到的“1234号房间： yi er san si hao fang jian”

Thanks @rdp23 for the question. Please try model_save_quantized_weights as this [example](https://github.com/google/qkeras/blob/ebc0964bf648bb97311dffd04edd8ee8f3a4cd46/examples/example_mnist.py#L151) Also in the [codelab](https://github.com/google/qkeras/blob/master/notebook/QKerasTutorial.ipynb), we explain it > "model_save_quantized_weights(model, filename) > > This function saves the quantized weights in...

are you able to use that example from [comment](https://github.com/google/qkeras/issues/60#issuecomment-748427609) and see the quantized weights?

thanks @thesps @rdp23 the default alpha during the training is auto_po2 for the weights.

close it for now. feel free to reopen it.

@thesps great and glad to see this helps! Yes, QDenseBatchnorm is one of our TODO items, but we have other higher priority tasks at this moment.

https://github.com/google/qkeras/pull/74

Hello @thesps, thank you for the PR! Could you also add file to demonstrate your usage and tests? I want more information to review this PR.

Hello @thesps, thank you for the PR! Could you also add file to demonstrate your usage and tests? I want more information to review this PR.

Hi, there are conflicts in utils.py. Please solve if you want to proceed. thanks!