onnx2pytorch
onnx2pytorch copied to clipboard
Missing type STRINGS when parsing attributes
The current implementation doesn't support STRINGS as attribute type. Per ONNX sepc for LSTM, one of the attributes can be activations which is of type STRINGS. This leads to conversion error on LSTM models. Could you add STRINGS attribute type?
Hi @calvinmccarter-at-lightmatter and @Talmaj ,
As a follow-up to the original request, I understand that STRINGS attrib being missing might be related to the fact that activation attribute is not current supported (refers here). If possible, can we please add support for explicitly listed torch-compatible activations? Since some 3p-converter-generated onnx models by default specify the activation fields (e.g. ['Sigmoid','Tanh','Tanh'] for LSTM).
Attribute STRINGS added in v0.5.2, but I think the activations in LSTM or GRU are still not supported.