EinsumNetworks
EinsumNetworks copied to clipboard
cambridge-mlg
Hi, I would like to know if we can specify different exponential families as leaf distributions for different random variables. This would be helpful in modelling tabular data, which typically...
I have seen that ARt-SPN can be classified, and I plan to conduct the same classification in EinsumNetworks, but the training accuracy is very low, I can't find the reason,...
This issue was originally discovered by Fabrizio Ventola (@fabriziov). Signed-off-by: Steven Lang
When the input for `CategoricalArray` was `len(x.shape)==3`, the `reshape` operation for the `stats` variable was missing the `num_var` variable and resulted in a wrong output shape (i.e. the `-1` as...
By setting `use_em=False` (e.g., to use SGD), the `reparam` function is created as a local function which cannot be readily pickled. This means that `torch.load` and `torch.save` (which are using...
Replacing `reparam_function` with a `reparam` function as a direct instance method, in order to avoid local function objects that cannot be pickled. See Issue #1 (This pr shall not include...