two_apples

When I use the onnxruntime（last main branch v1.1.4.0 ）with rocm provider to run the Yolo series network, I find that the fusion operator of conv+leakyrelu is still not working properly....

Fasterrcnn_resnet50_fpn cannot achieve dynamic reasoning in the batch dimension, but it can achieve dynamic reasoning in the h and w dimensions. If you want to achieve multi-batch reasoning, you need...

I also encountered this problem, and then I uninstalled the transformer (pip uninstall transformers), reinstalled it(pip install transformers==4.42.3 ), and the problem was solved