delzac
delzac
Userfunction cannot be saved as ONNX. And object detection has a few very specific functions that cannot be exported too. I suggest you use YOLO architecture instead.
Can you change the operation to equal and negate instead? It should give the same effect.
It will probably be very involved, but after loading the model file into cntk, you can probably swap out the notEqual node by getting the input and output node references.
You might want to try pypi instead
If you manage to successfully build it, i'll definitely be using it! I'm still stuck using GTX 1000 series cards, would love to upgrade. Unfortunately, i have zero experience in...
Thanks for sharing the info here @dmagee! Sounds like trying to setup cntk with the latest Cuda is a non trivial task.
@nietras Amazing work! Thank you for your contributions!!
@liqunfu @KeDengMS @BowenBao Like to request for review. Its a trivial change, but will allow weights from pre-trained models from other frameworks to be instantiated in cntk.
CNTK 2.7 runs on CUDA 10. RTX3000 series requires a higher version of CUDA. CNTK can run on 2000 series cards.
There is another loss that you can use that is similar to dice coefficient called fmeasure. Its available on cntk.