onnxruntime_backend icon indicating copy to clipboard operation
onnxruntime_backend copied to clipboard

InvalidArgumentError: The tensor Input (Input) of Slice op is not initialized.

Open qiu-pinggaizi opened this issue 2 years ago • 0 comments
trafficstars

I used the re model in paddleocr for inference, and the model can be loaded normally, but the inference report this error, what is the reason? Can you give me some advice. @fran6co @pranavsharma @DavidLangworthy @deadeyegoodwin @askhade

model path:https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layoutxlm_xfund_infer.tar error log: InvalidArgumentError: The tensor Input (Input) of Slice op is not initialized. [Hint: Expected in_tensor.IsInitialized() == true, but received in_tensor.IsInitialized():0 != true:1.] (at /opt/tritonserver/Paddle/paddle/fluid/operators/slice_op.cc:147)

qiu-pinggaizi avatar May 25 '23 03:05 qiu-pinggaizi