Objects classification

[Peter2121]

I have a NN pre-trained in Pytorch. I would like to load it using gotch, evaluate the performance and re-train it with new data.
The data is a float slice with length of 10, the result is binary classification (0/1).
I have no problems to load the NN and evaluate the performance, looping the slices of data:

	test_data := ts.MustOfSlice(line, ts.WithDType(gotch.Float))
	result := m.ForwardT(test_data, false)

where line is []float32 slice with length of [10].

Now I would like to prepare a 2D tensor to use in train routine, so I call ts.MustOfSlice with the whole dataset:

train_data := ts.MustOfSlice(train_records, ts.WithDType(gotch.Float))

where train_records is [][]float32 with length of [250][10]

This call is failed:

GoKind2DType() failed: no corresponding DType to given Go reflect.Kind slice

Reading the code of ts.OfSlice, it seems that it wants 1D slice as input, but cannot work with 2D slices.

I cannot find any example using the 'brut' slices for training.

Please, explain how can I train such network with my data using gotch.