I'm getting some weird crashes when running a simple Resnet model on a GTX 3080Ti in OPENCL backend.
The crash is a division by zero in:
|
M_ = num_output_ / group_; |
group_ is computed here
|
config.group = inputs[0].size[1] / umat_blobs[0].size[1]; |
In my case
inputs[0].size[1] equal 1 and
umat_blobs[0].size[1] equals 64
It is going to be a little difficult to provide a simple program reproducing this but maybe someone can already spot an obvious bug.
It seems that it will only crash once, the next run will use the cached kernels and work fine (group_=1)
I'm getting some weird crashes when running a simple Resnet model on a GTX 3080Ti in OPENCL backend.
The crash is a division by zero in:
opencv/modules/dnn/src/ocl4dnn/src/ocl4dnn_conv_spatial.cpp
Line 190 in 4dd3ab8
group_is computed hereopencv/modules/dnn/src/layers/convolution_layer.cpp
Line 1739 in 4dd3ab8
In my case
inputs[0].size[1]equal 1 andumat_blobs[0].size[1]equals 64It is going to be a little difficult to provide a simple program reproducing this but maybe someone can already spot an obvious bug.
It seems that it will only crash once, the next run will use the cached kernels and work fine (group_=1)