Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, x86, x64, ARM), multimodal model for text and images and so on.
Other
193
stars
38
forks
source link
The checkpoint to save the model regularly should not depend on validation #74
If we configure the training without validation (for example, choosing high RunValidEveryUpdates value), then the model will never be saved during the training. The checkpoint to save the model regularly should be validation independent.
If we configure the training without validation (for example, choosing high RunValidEveryUpdates value), then the model will never be saved during the training. The checkpoint to save the model regularly should be validation independent.