|
onnx2versal
|
QLinearSoftmax over INP_H chunks of INP_W_PAD vector. See https://github.com/onnx/onnx/blob/main/docs/Operators.md#Softmax Softmax(input, axis) = Exp(input) / ReduceSum(Exp(input), axis=axis, keepdims=1) More...

Modules | |
| QLinearSoftmaxKernels | |
Classes | |
| class | QLinearSoftmaxStreamGraph< PAD, QLINEARSOFTMAX, TT, INP_H, INP_W, INP_W_PAD > |
| Single instance graph. More... | |
| QLINEARSOFTMAX | QLinearSoftmax Kernel |
| TT | int8_t or uint8_t |
| INP_H | input height |
| INP_W | input width |
| INP_W_PAD | input width padded |