mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-04 23:59:56 +00:00
The implementation of QLinearConv internally does a transpose(NHWC)->im2col+GEMM->transpose(NCHW). This adds a graph transformer to change a model to use a com.microsoft.QLinearConv that supports NHWC natively to avoid unnecessary transposes. |
||
|---|---|---|
| .. | ||
| orttraining | ||
| pytorch_frontend_examples | ||
| tools | ||