zhongkaifu / RNNSharp

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.
BSD 3-Clause "New" or "Revised" License
285 stars 91 forks source link

Is there a way to further reduce file size of the model without affecting network size? #43

Open erotavlas opened 5 years ago

erotavlas commented 5 years ago

Hello, I found when training the NER sample you have provided in the Demo package, that the model.bin file size is very large, over 1GB. What exactly is inside this file, and is there any way to reduce the size of it?
Thanks