Closed My-Khan closed 3 years ago
How did you run Seq2SeqSharp ? Can you please share command line (config file), sample of training corpus with me ? I can take a look.
Many Zhong Kai for considering my issue here is my command-line arguments and some images Train -WordVectorSize 512 -HiddenSize 512 -LearningRate 0.001 -ModelFilePath seq2seq.model -TrainCorpusPath D:\Seq2SeqSharp-master (1)\Demo Data\1Train.txt -ValidCorpusPath D:\Seq2SeqSharp-master (1)\Demo Data\1valid.txt -SrcLang ENU -TgtLang CHS -BatchSize 256 -ProcessorType CPU -EncoderType BiLSTM -EncoderLayerDepth 6 -DecoderLayerDepth 2 -MultiHeadNum 8 -DeviceIds 0,1,2,3,4,5,6,7
Can you please try release package and see if it works for you.
Dear Zhong Many thanks i tried the new version , however when I try to load it VS 2015 it generates the below error messages:
D:\Zhong\Seq2SeqSharp-master\TensorSharp.CUDA\TensorSharp.CUDA.csproj : error : The default XML namespace of the project must be the MSBuild XML namespace. If the project is authored in the MSBuild 2003 format, please add xmlns="http://schemas.microsoft.com/developer/msbuild/2003" to the
Below are the images
Thanks @My-Khan
The Seq2SeqSharp is built by Visual Studio 2019 and dotnet core. So it seems VS 2015 is too old to support it. You may try to open it by Visual Studio Community or Visual Studio Code. They are all free to download and use.
Hello Zhong First I appreciate the contribution, Previously I have used RNNSharp successfully for NER task, I am curious to apply this new version too, however, when I try to run it generates huge error list e.g "IntPtr is a type but is used like a variable" especially in TensorSharp project in the following line of code using (NativeWrapper.BuildTensorRefPtr(input_i, out IntPtr input_iPtr)) using (NativeWrapper.BuildTensorRefPtr(output_i, out IntPtr output_iPtr)) using (NativeWrapper.BuildTensorRefPtr(indices_i, out IntPtr indices_iPtr)) { CpuOpsNative.TS_SpatialMaxPooling_updateOutput_frame(input_iPtr, output_iPtr, indices_iPtr, Thanks in Advance