bwery
bwery
Just to indicate that this patch is very useful for me. Thank you for it.
I encounter a similar error when converting a model that has been produced with Caffe and has been converted to ONNX using CoreML and then onnxmltools. Looking to the code...
Hello, I am not sure on my side what is the best action to perform when dimension 3 input is present. I agree with the fact that this may be...
Hello, I am not used with the introduction of pull requests on Github. So, i would prefer somebody skilled makes the change ! Thank you anyway for your answer !
Thank you linmajia ! Seems to be the first step for resolution. It was not clear for me that mmdnn was requiring the frameworks to be present. This solve the...
I also encountered this problem. The patch by uhfband seems to solve it properly. Thank you uhfband !
@quic-ssiddego : Thank you for your attention ! Now, I have succeeded to install release 1.13.0 (let say imports are working. I have not tested further as I am discovering...
I encounter the same problem. So it would be nice if this operator can be supported in future !
@jiafatom: Having a look to your idea to use Transpose to modify the behaviour of a batch normalization layer into the behaviour of a layer normalization one, I feel there...
I have just created a small network derived from the faulty one, removing some layers and reducing their size to very small values. This network of course is not very...