leooo
leooo
> Forget about `NNOM_TRUNCATE` since you don't use RNN layers. Also, this macro is not about using the floating number, nnom currently only running on 8bit fixed-point data. > >...
> 您好，请问一下转换此模型的背景和目的可以描述一下吗 好的，主要是用于语音信号的降噪。 应用于嵌入式设备， 这种应用很广泛。
Thanks for your great job. I also want to get more information about AGC algorithm. Can you tell me more references? Looking forward to your reply.
> @liziru Have you finished all 200 epochs training? and what's the final val_loss? Thanks for your reply. This training won't stop until the early-stopping callback patience is exhausted. And...
> > Thanks for your wonderful job. @breizhn > > I use this project to retrain on DNS-challenge dataset that was updated recently. The denoised results of the retraining model...
> > > @liziru Have you finished all 200 epochs training? and what's the final val_loss? > > > > > > Thanks for your reply. > > This training...
> > > @liziru Have you finished all 200 epochs training? and what's the final val_loss? > > > > > > Thanks for your reply. > > This training...
> @liziru 您好，请问下你自己重新训练的模型大概是多少轮停的吖？我自己训练都是80多轮就停了，而且训练出来的模型参数大小是3990352，和预训练的参数量（norm 4003624 和 3989312）对不上啊 可以对比看一下降噪效果
> @liziru 降噪效果从波形图上看比这预训练效果差些，参数大小就是模型最后训练完成保存的大小，训练数据也是按照-5 ~25 生成的 训练数据不完全一样。我的结果也会差一点。
> Epoch 00095: val_loss did not improve from -16.76465 > 2021-01-21 00:24:52.466681: W tensorflow/core/kernels/data/generator_dataset_op.cc:107] Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process...