Longzhi Wang
Longzhi Wang
@Oceania2018 I have the same question too. Is this a mistake?
TensorFlow.NET support for Tflite is very lacking, so it seems that TensorFlow.NET cannot load your custom `.tflite` weights.
Is there any indispensable reasons to use `StackLayers`? Why not just keep this two embedding layers separate?
Would you mind provide a minimum code for reproduction? I remember someone said this issue has solved in issue #916.
Can this issue be closed? @asaf92
Hello, the implementation of class_weight and sample_weight has completed in #1187 #1189 Please let me know if there still exist some problems.
I'm very sorry, because the developer responsible for this api is busy recently, so it may not be so fast to solve this problem, I will let you know once...
> I can't call this method at all. I created a very basic model with the layers api, saved it, then tried to load it next iteration and I'm getting...
Hello, dose this bug still exist? If so, could you please provide a minimul example for reproduction?
Hello, due to distributed, sharded training is a big feature, so it is unlikely to be implemented in the near future. If this feature is implemented in TensorFlow.NET in the...