【发布时间】：2020-05-04 13:01:29
【问题描述】：
在我的 .NET 核心应用程序中使用 ML.net 我正在尝试使用导出到 ONNX 文件的 KERAS LSTM 模型。这是我的代码：
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Transforms.Onnx;
public void getmodel(mydata[] data1)
{
string modelPath = "C:\\MyStuff\\ONNXtest.onnx";
MLContext mlContext = new MLContext();
IDataView data = mlContext.Data.LoadFromEnumerable<mydata>(data1);
OnnxScoringEstimator pipeline = mlContext.Transforms.ApplyOnnxModel(new[] { "output" }, new[] { "input" }, modelPath);
IEnumerable<mydata> testdata = mlContext.Data.CreateEnumerable<mydata>(data, reuseRowObject: true);
foreach (mydata row in testdata)
{
System.Diagnostics.Debug.WriteLine(row.myval[0]);
System.Diagnostics.Debug.WriteLine(row.myval[1]);
System.Diagnostics.Debug.WriteLine(row.myval[2]);
System.Diagnostics.Debug.WriteLine(row.myval[3]);
System.Diagnostics.Debug.WriteLine(row.myval[4]);
}
OnnxTransformer test = pipeline.Fit(data);
IDataView transformedValues = test.Transform(data);
IEnumerable<float[]> results = transformedValues.GetColumn<float[]>("output");
double result = Convert.ToDouble(results.ElementAtOrDefault(0).GetValue(0));
}
这是 mydata 类的样子：
public class mydata
{
[VectorType(1,5,1)]
[ColumnName("input")]
public float[] myval { get; set; }
}
我想在模型中输入 5 个值并查看“System.Diagnostics.Debug.WriteLine”输出，似乎一切正常，并且 IDataView 数据包含 5 个输入模型的值。但是，pipeline.Fit(data) 行会导致 Microsoft.ML.OnnxTransformer.dll 中出现 "System.ArgumentOutOfRangeException" 错误。
这里也是用python训练和导出LSTM的代码：
regressor = Sequential()
regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1),name ='input'))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50))
regressor.add(Dropout(0.2))
regressor.add(Dense(units = 1,name ='output'))
regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')
regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)
from winmltools import convert_keras
model_onnx = convert_keras(regressor, 7, name='sequential_7')
from winmltools.utils import save_model
save_model(model_onnx, 'C:\\MyStuff\\ONNXtest.onnx')
这是导出的网络摘要：
Model: "sequential_7"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (LSTM) (None, 5, 50) 10400
_________________________________________________________________
dropout_25 (Dropout) (None, 5, 50) 0
_________________________________________________________________
lstm_21 (LSTM) (None, 5, 50) 20200
_________________________________________________________________
dropout_26 (Dropout) (None, 5, 50) 0
_________________________________________________________________
lstm_22 (LSTM) (None, 5, 50) 20200
_________________________________________________________________
dropout_27 (Dropout) (None, 5, 50) 0
_________________________________________________________________
lstm_23 (LSTM) (None, 50) 20200
_________________________________________________________________
dropout_28 (Dropout) (None, 50) 0
_________________________________________________________________
output (Dense) (None, 1) 51
=================================================================
Total params: 71,051
Trainable params: 71,051
Non-trainable params: 0
如果我只是在 Python 中使用该模型，它可以完美运行，并且前段时间非常相似的设置（实际上我认为它是相同的代码）在 ML.net 中完美运行。但现在我什至不确定我的错误是在 python 端还是在 c# 端。谁能帮我弄清楚如何处理这个错误？
【问题讨论】：
标签： python c# keras ml.net onnx