Using ColumnarModelData, a variant of MixedInputModel and a StructuredLearner with CrossEntropy loss function.
Using fit or lr_find or any function gives an error about the target shape
-> 1052 return torch._C._nn.nll_loss(input, target, weight, size_average, ignore_index, reduce)
1053 elif dim == 4:
1054 return torch._C._nn.nll_loss2d(input, target, weight, size_average, ignore_index, reduce)
RuntimeError: multi-target not supported at /opt/conda/conda-bld/pytorch_1518244421288/work/torch/lib/THNN/generic/ClassNLLCriterion.c:22
But am not able to check target dims at every point it might require.
The y being fed into ColumnarDataModel is np.array shape (NumRows,) with each value an int64 for the class. I believe a vector of this shape but with BatchSize instead of Numrows is what should go to the loss function but do not know where it gets off.