ehsanmok commented on code in PR #13163:
URL: https://github.com/apache/tvm/pull/13163#discussion_r1002119311
##########
python/tvm/topi/image/grid_sample.py:
##########
@@ -200,13 +200,13 @@ def _bilinear_sample(n, c, h, w):
def _nearest_sample(n, c, h, w):
y, x = _compute_source_index(n, h, w)
- y_new = te.round(y).astype("int32")
- x_new = te.round(x).astype("int32")
+ y_new = te.nearbyint(y).astype("int32")
Review Comment:
The `round` fails as for `nearest` in cpu as interpolation onnx uses
[`std::nearbyintf`](https://github.com/microsoft/onnxruntime/blob/62cc927f05580a8875af1fc93363d4b6d34bc2c6/onnxruntime/core/providers/cpu/tensor/grid_sample.cc#L189-L192)
but is flaky on cuda
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
