Tencent/TPAT

tensorflow bert model can not build successfully, when to solve?

liukaiyueyuo opened this issue · 1 comments

tensorflow bert model(ckpt or pb or saved_model) can't build successfully by TPAT, the problem is that the nodes input & output of onnx model transformed by tf2onnx have no shape and dtype info(all are None). My current solution is to use onnxruntime generating another onnx which has shape and dtype info, and then use TPAT to generate TensorRT model. So, when do you have a plan to solve this problem?

Your way of handling it is great. TPAT will support tensorflow and pytorch as input( the same as onnx). But not soon. Maybe next month.