You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In fpgaConvNet, Gemm layer is implemented as InnerProductLayer. However, the main difference is that Gemm layer supports more parameters (Boolean flags transA, transB, scalars alpha, beta).
For the current model, all four parameters haven't been considered when the model is parsed from Onnx form to fpgaConvNet.
The text was updated successfully, but these errors were encountered:
In fpgaConvNet,
Gemm layer
is implemented asInnerProductLayer
. However, the main difference is that Gemm layer supports more parameters (Boolean flagstransA
,transB
, scalarsalpha
,beta
).For the current model, all four parameters haven't been considered when the model is parsed from Onnx form to fpgaConvNet.
The text was updated successfully, but these errors were encountered: