yjiangling

> The underlying C++ code is threadsafe (and for that matter the mmap can share memory). I don't know enough about python though. Thanks a lot for the reply, I...

> Could you please add a call to tf.abs() following the tf.rfft() function? This behavior is By design, that tf2onnx cannot handle the case that tf RFFT op + Identity...

> Both of them are supported by tf2onnx already. Looks like this error was found in run_rewriters() which happened after the general conversion is done. > > Could you please...

> > > Both of them are supported by tf2onnx already. Looks like this error was found in run_rewriters() which happened after the general conversion is done. > > >...

The new model is put here: https://gh.ddlc.top/https://github.com/yjiangling/Test/releases/download/1.0/model.zip

https://github.com/yjiangling/Temp_Model/releases/download/1.0/model.zip Here is the address to get the ONNX model.

The error have been solved, but a new error occured as below: [01/03/2023-08:03:16] [E] [TRT] parsers/onnx/ModelImporter.cpp:783: --- End node --- [01/03/2023-08:03:16] [E] [TRT] parsers/onnx/ModelImporter.cpp:785: ERROR: parsers/onnx/ModelImporter.cpp:166 In function parseGraph: [6]...

same question, still no answer?

> > tensor2tensor/tensor2tensor/utils/avg_checkpoints.py > > i got a trouble in using average ckpt with tf2.0: > > a variable named 'xx/xx/.xx/xx' , how can it be save in ckpt? >...