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
Hello! In the function vxMapTensorPatch from OpenVX v1.3 calculations for the strides seem incorrect.
For example, for a tensor with data type VX_TYPE_INT16dimensions = {3, 1, 2, 2} and the function params view_start = {0, 0, 0, 0}, view_end = {3, 1, 2, 2} it calculates strides = {2, 2, 4, 8}:
for (vx_uint32 i = 1; i < number_of_dims; i++)
{
stride[i] = stride[i - 1] * (view_end[i] - view_start[i]);
}
I think that the strides should be calculated as:
for (vx_uint32 i = 1; i < number_of_dims; i++)
{
stride[i] = stride[i - 1] * (view_end[i - 1] - view_start[i - 1]);
}
and there are strides = {2, 6, 6, 12} for the given example.
The text was updated successfully, but these errors were encountered:
dvorotnev
pushed a commit
to dvorotnev/OpenVX-sample-impl
that referenced
this issue
May 19, 2020
actually I dont think it should calculate stride[] using view_end[] and view_start[]. I think it should simpl return the values in tensor->stride[] which are already initialized in ownInitTensor()
Hello! In the function
vxMapTensorPatch
from OpenVX v1.3 calculations for the strides seem incorrect.For example, for a tensor with data type
VX_TYPE_INT16
dimensions = {3, 1, 2, 2}
and the function paramsview_start = {0, 0, 0, 0}
,view_end = {3, 1, 2, 2}
it calculatesstrides = {2, 2, 4, 8}
:I think that the strides should be calculated as:
and there are
strides = {2, 6, 6, 12}
for the given example.The text was updated successfully, but these errors were encountered: