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
Dequantize linear defines the dequantization formula as y = (x - x_zero_point) * x_scale and that x and x_zero_point must have the same type dtype.
What is the intended behavior if x - x_zero_point is outside of the range of dtype?
Ask a Question
Question
Dequantize linear defines the dequantization formula as
y = (x - x_zero_point) * x_scale
and thatx
andx_zero_point
must have the same typedtype
.What is the intended behavior if
x - x_zero_point
is outside of the range ofdtype
?Further information
I noticed that the reference implementation converts to float32 before doing the subtraction, while the onnx runtime casts to int32_t.
The text was updated successfully, but these errors were encountered: